Natural Language Processing (almost) from Scratch

Abstract

We propose a unified neural network architecture and learning algorithm that can be applied to various natural language processing tasks including: part-of-speech tagging, chunking, named entity recognition, and semantic role labeling. This versatility is achieved by trying to avoid task-specific engineering and therefore disregarding a lot of prior knowledge. Instead of exploiting man-made input features carefully optimized for each task, our system learns internal representations on the basis of vast amounts of mostly unlabeled training data. This work is then used as a basis for building a freely available tagging system with good performance and minimal computational requirements.

References in corpus (2)

• Ranking the best instances
• Distributional Part-of-Speech Tagging

Cited by in corpus (725)

• Distributed Representations of Sentences and Documents
• An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
• Character-level Convolutional Networks for Text Classification
• Teaching Machines to Read and Comprehend
• Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
• Pre-trained Models for Natural Language Processing: A Survey
• Exploiting Similarities among Languages for Machine Translation
• Explaining NonLinear Classification Decisions with Deep Taylor Decomposition
• Recent Trends in Deep Learning Based Natural Language Processing
• Unsupervised Domain Adaptation with Residual Transfer Networks
• Word Embeddings Quantify 100 Years of Gender and Ethnic Stereotypes
• Character-Aware Neural Language Models
• Convolutional Neural Network Architectures for Matching Natural Language Sentences
• ProtVec: A Continuous Distributed Representation of Biological Sequences
• A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Network
• CTRL: A Conditional Transformer Language Model for Controllable Generation
• A C-LSTM Neural Network for Text Classification
• SeqSleepNet: End-to-End Hierarchical Recurrent Neural Network for Sequence-to-Sequence Automatic Sleep Staging
• DeepGO: Predicting protein functions from sequence and interactions using a deep ontology-aware classifier
• GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding
• A Survey on Recent Advances in Named Entity Recognition from Deep Learning models
• Joint entity recognition and relation extraction as a multi-head selection problem
• Text Understanding from Scratch
• Multi-Task Learning with Deep Neural Networks: A Survey
• Deep Learning Based Text Classification: A Comprehensive Review
• Learning to Generate Reviews and Discovering Sentiment
• The Natural Language Decathlon: Multitask Learning as Question Answering
• Evaluating Word Embedding Models: Methods and Experimental Results
• An Autoencoder Approach to Learning Bilingual Word Representations
• Recent Advances in Convolutional Neural Networks
• BilBOWA: Fast Bilingual Distributed Representations without Word Alignments
• Polyglot: Distributed Word Representations for Multilingual NLP
• Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges
• TransNets: Learning to Transform for Recommendation
• Ask the GRU: Multi-Task Learning for Deep Text Recommendations
• Convolutional Neural Networks over Tree Structures for Programming Language Processing
• Revisiting Semi-Supervised Learning with Graph Embeddings
• "What is Relevant in a Text Document?": An Interpretable Machine Learning Approach
• Optimal Hyperparameters for Deep LSTM-Networks for Sequence Labeling Tasks
• Fully Connected Deep Structured Networks
• Fast Convolutional Nets With fbfft: A GPU Performance Evaluation
• TENER: Adapting Transformer Encoder for Named Entity Recognition
• An Analysis of Hierarchical Text Classification Using Word Embeddings
• Self-Taught Convolutional Neural Networks for Short Text Clustering
• Deep Learning Autoencoder Approach for Handwritten Arabic Digits Recognition
• TI-CNN: Convolutional Neural Networks for Fake News Detection
• Source localization in an ocean waveguide using supervised machine learning
• Multi-Task Deep Neural Networks for Natural Language Understanding
• Unitary Evolution Recurrent Neural Networks
• Deep Models Under the GAN: Information Leakage from Collaborative Deep Learning
• End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF
• Perceiver IO: A General Architecture for Structured Inputs & Outputs
• AutoExtend: Extending Word Embeddings to Embeddings for Synsets and Lexemes
• Representation learning for very short texts using weighted word embedding aggregation
• Harnessing Deep Neural Networks with Logic Rules
• Natural Language Processing Advancements By Deep Learning: A Survey
• Multi-Task Cross-Lingual Sequence Tagging from Scratch
• Deep Residual Correction Network for Partial Domain Adaptation
• Deep-learning source localization using multi-frequency magnitude-only data
• Improving Multi-Task Deep Neural Networks via Knowledge Distillation for Natural Language Understanding
• Named Entity Recognition and Classification on Historical Documents: A Survey
• OpenTag: Open Attribute Value Extraction from Product Profiles [Deep Learning, Active Learning, Named Entity Recognition]
• An automated pipeline for the discovery of conspiracy and conspiracy theory narrative frameworks: Bridgegate, Pizzagate and storytelling on the web
• Neural Entity Linking: A Survey of Models Based on Deep Learning
• Causality Extraction based on Self-Attentive BiLSTM-CRF with Transferred Embeddings
• How to Prove Your Model Belongs to You: A Blind-Watermark based Framework to Protect Intellectual Property of DNN
• Training robust neural networks using Lipschitz bounds
• Tweet2Vec: Learning Tweet Embeddings Using Character-level CNN-LSTM Encoder-Decoder
• Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels
• When Are Tree Structures Necessary for Deep Learning of Representations?
• Finding Function in Form: Compositional Character Models for Open Vocabulary Word Representation
• Active Bias: Training More Accurate Neural Networks by Emphasizing High Variance Samples
• An Empirical Evaluation of Deep Learning for ICD-9 Code Assignment using MIMIC-III Clinical Notes
• An Integrated Transfer Learning and Multitask Learning Approach for Pharmacokinetic Parameter Prediction
• Curriculum Learning and Minibatch Bucketing in Neural Machine Translation
• Ultradense Word Embeddings by Orthogonal Transformation
• A Deep Network Model for Paraphrase Detection in Short Text Messages
• Deep Learning and Knowledge-Based Methods for Computer Aided Molecular Design -- Toward a Unified Approach: State-of-the-Art and Future Directions
• Learning Deep Structured Models
• Towards Universal Paraphrastic Sentence Embeddings
• Deep Transfer Learning with Joint Adaptation Networks
• Supervised and Unsupervised Neural Approaches to Text Readability
• Deep Learning of Representations: Looking Forward
• meProp: Sparsified Back Propagation for Accelerated Deep Learning with Reduced Overfitting
• Representation Learning: A Review and New Perspectives
• Mixout: Effective Regularization to Finetune Large-scale Pretrained Language Models
• Edge Intelligence: Paving the Last Mile of Artificial Intelligence with Edge Computing
• Latent Predictor Networks for Code Generation
• Multi-Grained Named Entity Recognition
• AttSum: Joint Learning of Focusing and Summarization with Neural Attention
• Learning Semantic Similarity for Very Short Texts
• Part-of-Speech Tagging with Bidirectional Long Short-Term Memory Recurrent Neural Network
• Trellis Networks for Sequence Modeling
• Leveraging Deep Neural Networks and Knowledge Graphs for Entity Disambiguation
• Improving Twitter Sentiment Classification via Multi-Level Sentiment-Enriched Word Embeddings
• A Deep Journey into Super-resolution: A survey
• Modelling, Visualising and Summarising Documents with a Single Convolutional Neural Network
• Tunable Efficient Unitary Neural Networks (EUNN) and their application to RNNs
• Neural Vector Spaces for Unsupervised Information Retrieval
• Joint Deep Modeling of Users and Items Using Reviews for Recommendation
• Comparative Study of Deep Learning Software Frameworks
• Open Question Answering with Weakly Supervised Embedding Models
• Neural Models for Information Retrieval
• Extraction of Salient Sentences from Labelled Documents
• A Joint Model for Question Answering and Question Generation
• Efficient Summarization with Read-Again and Copy Mechanism
• The Expressive Power of Word Embeddings
• Visual Madlibs: Fill in the blank Image Generation and Question Answering
• Probabilistic Reasoning via Deep Learning: Neural Association Models
• Dive into Deep Learning
• Jointly Learning Word Embeddings and Latent Topics
• Implicit Discourse Relation Classification via Multi-Task Neural Networks
• Analytic continuation via domain-knowledge free machine learning
• Dependency-based Convolutional Neural Networks for Sentence Embedding
• A Unified Tagging Solution: Bidirectional LSTM Recurrent Neural Network with Word Embedding
• ASTRAL: Adversarial Trained LSTM-CNN for Named Entity Recognition
• Do Convolutional Networks need to be Deep for Text Classification ?
• Applications of Online Deep Learning for Crisis Response Using Social Media Information
• Data driven approximation of parametrized PDEs by Reduced Basis and Neural Networks
• CNN+CNN: Convolutional Decoders for Image Captioning
• Character-based Joint Segmentation and POS Tagging for Chinese using Bidirectional RNN-CRF
• CAN-NER: Convolutional Attention Network for Chinese Named Entity Recognition
• Intelligent Wireless Communications Enabled by Cognitive Radio and Machine Learning
• Attending to Characters in Neural Sequence Labeling Models
• Neural Extractive Summarization with Side Information
• Improving Deep Learning for HAR with shallow LSTMs
• Well-calibrated Confidence Measures for Multi-label Text Classification with a Large Number of Labels
• Low-Resource Named Entity Recognition with Cross-Lingual, Character-Level Neural Conditional Random Fields
• Deep Learning over Multi-field Categorical Data: A Case Study on User Response Prediction
• Discriminative Neural Sentence Modeling by Tree-Based Convolution
• Multi-Task Learning for Sequence Tagging: An Empirical Study
• Partial Transfer Learning with Selective Adversarial Networks
• Unsupervised Hyperalignment for Multilingual Word Embeddings
• Separated by an Un-common Language: Towards Judgment Language Informed Vector Space Modeling
• Word Emdeddings through Hellinger PCA
• Notes on Noise Contrastive Estimation and Negative Sampling
• Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style
• Unsupervised Word and Dependency Path Embeddings for Aspect Term Extraction
• FlauBERT: Unsupervised Language Model Pre-training for French
• Distraction-Based Neural Networks for Document Summarization
• T-NER: An All-Round Python Library for Transformer-based Named Entity Recognition
• Fast Structured Decoding for Sequence Models
• Cross-lingual, Character-Level Neural Morphological Tagging
• A Convolutional Encoder Model for Neural Machine Translation
• Current Limitations in Cyberbullying Detection: on Evaluation Criteria, Reproducibility, and Data Scarcity
• Multimodal Convolutional Neural Networks for Matching Image and Sentence
• Unsupervised, Efficient and Semantic Expertise Retrieval
• A Comprehensive Survey on Hardware-Aware Neural Architecture Search
• A Dependency-Based Neural Network for Relation Classification
• A Survey of Safety and Trustworthiness of Deep Neural Networks: Verification, Testing, Adversarial Attack and Defence, and Interpretability
• Learning by Association - A versatile semi-supervised training method for neural networks
• Rethinking multiscale cardiac electrophysiology with machine learning and predictive modelling
• Deep Learning-based Sentiment Classification: A Comparative Survey
• Multi-GPU Training of ConvNets
• A Unified MRC Framework for Named Entity Recognition
• On Accurate and Reliable Anomaly Detection for Gas Turbine Combustors: A Deep Learning Approach
• Natural Language Understanding with Distributed Representation
• Self-Adaptive Hierarchical Sentence Model
• Multi-sense embeddings through a word sense disambiguation process
• Training Restricted Boltzmann Machines on Word Observations
• Limits of End-to-End Learning
• LSTM Recurrent Neural Networks for Cybersecurity Named Entity Recognition
• Aspect-Based Sentiment Analysis Using a Two-Step Neural Network Architecture
• Efficient Processing of Deep Neural Networks: A Tutorial and Survey
• FedNER: Privacy-preserving Medical Named Entity Recognition with Federated Learning
• Neural Information Retrieval: A Literature Review
• ReLeQ: A Reinforcement Learning Approach for Deep Quantization of Neural Networks
• Graph Convolutional Networks for Named Entity Recognition
• Leveraging Deep Graph-Based Text Representation for Sentiment Polarity Applications
• Word sense induction using word embeddings and community detection in complex networks
• DeepAPT: Nation-State APT Attribution Using End-to-End Deep Neural Networks
• Actionable and Political Text Classification using Word Embeddings and LSTM
• Joint Embedding of Hierarchical Categories and Entities for Concept Categorization and Dataless Classification
• Learning Multilingual Word Representations using a Bag-of-Words Autoencoder
• Rapid Classification of Crisis-Related Data on Social Networks using Convolutional Neural Networks
• Joint Word Representation Learning using a Corpus and a Semantic Lexicon
• Neural ranking models for document retrieval
• Joint Representation Learning of Text and Knowledge for Knowledge Graph Completion
• Neural Probabilistic Model for Non-projective MST Parsing
• End-to-end Phoneme Sequence Recognition using Convolutional Neural Networks
• Not All Neural Embeddings are Born Equal
• Bidirectional LSTM-CRF for Clinical Concept Extraction
• A General Framework for Information Extraction using Dynamic Span Graphs
• Learning from Few Samples: A Survey
• Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networks
• PatchNet: Hierarchical Deep Learning-Based Stable Patch Identification for the Linux Kernel
• Structured Prediction as Translation between Augmented Natural Languages
• Learning to Transfer Examples for Partial Domain Adaptation
• Combining Visual and Textual Features for Semantic Segmentation of Historical Newspapers
• A Discourse-Level Named Entity Recognition and Relation Extraction Dataset for Chinese Literature Text
• Drug-Drug Interaction Extraction from Biomedical Text Using Long Short Term Memory Network
• Thinking, Fast and Slow: Combining Vector Spaces and Knowledge Graphs
• Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networks
• Curriculum Audiovisual Learning
• An attentive neural architecture for joint segmentation and parsing and its application to real estate ads
• Learning for Biomedical Information Extraction: Methodological Review of Recent Advances
• Incorporating Both Distributional and Relational Semantics in Word Representations
• Position-Aware Self-Attention based Neural Sequence Labeling
• Neural Word Segmentation Learning for Chinese
• On the Decision Boundary of Deep Neural Networks
• WordRep: A Benchmark for Research on Learning Word Representations
• Real or Fake? Learning to Discriminate Machine from Human Generated Text
• Conspiracy in the Time of Corona: Automatic detection of Covid-19 Conspiracy Theories in Social Media and the News
• Inferring Interpersonal Relations in Narrative Summaries
• Beyond Word Embeddings: Learning Entity and Concept Representations from Large Scale Knowledge Bases
• Towards Making the Most of BERT in Neural Machine Translation
• Word Embeddings and Their Use In Sentence Classification Tasks
• Transfer Learning for Speech and Language Processing
• Shallow reading with Deep Learning: Predicting popularity of online content using only its title
• CREIME: A Convolutional Recurrent model for Earthquake Identification and Magnitude Estimation
• Exploring Segment Representations for Neural Segmentation Models
• CapsAcc: An Efficient Hardware Accelerator for CapsuleNets with Data Reuse
• Learning Semantic Representations for the Phrase Translation Model
• Convolutional Neural Networks for Toxic Comment Classification
• Partial Adversarial Domain Adaptation
• Structured prediction models for RNN based sequence labeling in clinical text
• Learning multi-faceted representations of individuals from heterogeneous evidence using neural networks
• Low-Resource Text Classification using Domain-Adversarial Learning
• Unifying Question Answering, Text Classification, and Regression via Span Extraction
• Investigating the Successes and Failures of BERT for Passage Re-Ranking
• Semantic projection: recovering human knowledge of multiple, distinct object features from word embeddings
• LMMS Reloaded: Transformer-based Sense Embeddings for Disambiguation and Beyond
• Spoken Language Intent Detection using Confusion2Vec
• A Deep Memory-based Architecture for Sequence-to-Sequence Learning
• Learning Semantic Script Knowledge with Event Embeddings
• Semantic Relation Classification via Convolutional Neural Networks with Simple Negative Sampling
• Attention over Parameters for Dialogue Systems
• Structural block driven - enhanced convolutional neural representation for relation extraction
• Perceive Your Users in Depth: Learning Universal User Representations from Multiple E-commerce Tasks
• Learning and Transferring IDs Representation in E-commerce
• Multilingual Language Processing From Bytes
• Learning Latent Representations in Neural Networks for Clustering through Pseudo Supervision and Graph-based Activity Regularization
• Understanding Convolutional Neural Networks for Text Classification
• Distance Metric Learning for Aspect Phrase Grouping
• Trust from the past: Bayesian Personalized Ranking based Link Prediction in Knowledge Graphs
• Towards Empathetic Human-Robot Interactions
• SHOMA at Parseme Shared Task on Automatic Identification of VMWEs: Neural Multiword Expression Tagging with High Generalisation
• Large-Scale User Modeling with Recurrent Neural Networks for Music Discovery on Multiple Time Scales
• IQA: Interactive Query Construction in Semantic Question Answering Systems
• Joint Text Embedding for Personalized Content-based Recommendation
• Call Attention to Rumors: Deep Attention Based Recurrent Neural Networks for Early Rumor Detection
• A Bi-LSTM-RNN Model for Relation Classification Using Low-Cost Sequence Features
• Bidirectional Recursive Neural Networks for Token-Level Labeling with Structure
• Contextual Word Representations: A Contextual Introduction
• Solving Verbal Comprehension Questions in IQ Test by Knowledge-Powered Word Embedding
• Local Translation Prediction with Global Sentence Representation
• Joint Learning of Correlated Sequence Labelling Tasks Using Bidirectional Recurrent Neural Networks
• Realised Volatility Forecasting: Machine Learning via Financial Word Embedding
• Using Error Decay Prediction to Overcome Practical Issues of Deep Active Learning for Named Entity Recognition
• Multichannel Variable-Size Convolution for Sentence Classification
• Named Entity Recognition as Dependency Parsing
• DeepSentiPers: Novel Deep Learning Models Trained Over Proposed Augmented Persian Sentiment Corpus
• End-to-end named entity extraction from speech
• Evaluating the visualization of what a Deep Neural Network has learned
• Robust Lexical Features for Improved Neural Network Named-Entity Recognition
• Character-level Convolutional Network for Text Classification Applied to Chinese Corpus
• An Embarrassingly Simple Approach for Transfer Learning from Pretrained Language Models
• BreakingNews: Article Annotation by Image and Text Processing
• Unsupervised POS Induction with Word Embeddings
• Efficient Exact Gradient Update for training Deep Networks with Very Large Sparse Targets
• Learning Sparse Sharing Architectures for Multiple Tasks
• Open Problems in Cooperative AI
• Data Sets: Word Embeddings Learned from Tweets and General Data
• MUST-CNN: A Multilayer Shift-and-Stitch Deep Convolutional Architecture for Sequence-based Protein Structure Prediction
• Distributed Multi-Task Learning with Shared Representation
• A Survey on Recent Advances in Sequence Labeling from Deep Learning Models
• Multimodal Grounding for Language Processing
• Multi-Task Attentive Residual Networks for Argument Mining
• Learning to Represent Words in Context with Multilingual Supervision
• Deep Multi-Instance Transfer Learning
• Structured Prediction Energy Networks
• Associate-3Ddet: Perceptual-to-Conceptual Association for 3D Point Cloud Object Detection
• Neural Bug Finding: A Study of Opportunities and Challenges
• Non-Intrusive Load Monitoring with Fully Convolutional Networks
• Exploiting Linguistic Resources for Neural Machine Translation Using Multi-task Learning
• Multimodal Joint Attribute Prediction and Value Extraction for E-commerce Product
• PharmKE: Knowledge Extraction Platform for Pharmaceutical Texts using Transfer Learning
• Knowledge Representation via Joint Learning of Sequential Text and Knowledge Graphs
• Constructing Deep Neural Networks by Bayesian Network Structure Learning
• The Microsoft Toolkit of Multi-Task Deep Neural Networks for Natural Language Understanding
• A Neural Multi-Task Learning Framework to Jointly Model Medical Named Entity Recognition and Normalization
• Exploiting Sentence and Context Representations in Deep Neural Models for Spoken Language Understanding
• ZEN: Pre-training Chinese Text Encoder Enhanced by N-gram Representations
• Simple and Effective Text Matching with Richer Alignment Features
• "When they say weed causes depression, but it's your fav antidepressant": Knowledge-aware Attention Framework for Relationship Extraction
• Memorized Sparse Backpropagation
• Building Program Vector Representations for Deep Learning
• Bidirectional Recurrent Neural Networks for Medical Event Detection in Electronic Health Records
• Lyrics-Based Music Genre Classification Using a Hierarchical Attention Network
• Controlled Experiments for Word Embeddings
• Syntactic Recurrent Neural Network for Authorship Attribution
• Self-attention-based BiGRU and capsule network for named entity recognition
• An empirical study on large scale text classification with skip-gram embeddings
• A Data-driven Neural Network Architecture for Sentiment Analysis
• Robust Multilingual Part-of-Speech Tagging via Adversarial Training
• GEDIT: Geographic-Enhanced and Dependency-Guided Tagging for Joint POI and Accessibility Extraction at Baidu Maps
• A Methodology for Automatic Selection of Activation Functions to Design Hybrid Deep Neural Networks
• Learning Document Embeddings by Predicting N-grams for Sentiment Classification of Long Movie Reviews
• Entity Recognition at First Sight: Improving NER with Eye Movement Information
• Distantly Supervised Named Entity Recognition using Positive-Unlabeled Learning
• Entity Linking Meets Deep Learning: Techniques and Solutions
• Improving Recurrent Neural Networks For Sequence Labelling
• Multi-level Gated Recurrent Neural Network for Dialog Act Classification
• No Need to Pay Attention: Simple Recurrent Neural Networks Work! (for Answering "Simple" Questions)
• End-to-end Recurrent Neural Network Models for Vietnamese Named Entity Recognition: Word-level vs. Character-level
• Deep Reinforcement Learning for Trading
• Semantic flow in language networks
• Redefining Context Windows for Word Embedding Models: An Experimental Study
• Prior Knowledge Driven Label Embedding for Slot Filling in Natural Language Understanding
• A Linear Dynamical System Model for Text
• LTSG: Latent Topical Skip-Gram for Mutually Learning Topic Model and Vector Representations
• A Full End-to-End Semantic Role Labeler, Syntax-agnostic Over Syntax-aware?
• Self-adaptive deep neural network: Numerical approximation to functions and PDEs
• Clinical Information Extraction via Convolutional Neural Network
• Bit Efficient Quantization for Deep Neural Networks
• Automated Enriched Medical Concept Generation for Chest X-ray Images
• Identifying Harm Events in Clinical Care through Medical Narratives
• Neural Tensor Factorization
• Freshman or Fresher? Quantifying the Geographic Variation of Internet Language
• Neural Graph Embedding Methods for Natural Language Processing
• Predictive Uncertainty Quantification with Compound Density Networks
• Using Neural Networks for Click Prediction of Sponsored Search
• SCARF: Self-Supervised Contrastive Learning using Random Feature Corruption
• GRN: Gated Relation Network to Enhance Convolutional Neural Network for Named Entity Recognition
• GCDT: A Global Context Enhanced Deep Transition Architecture for Sequence Labeling
• A hybrid deep learning approach for medical relation extraction
• Can You Tell Me How to Get Past Sesame Street? Sentence-Level Pretraining Beyond Language Modeling
• DBTagger: Multi-Task Learning for Keyword Mapping in NLIDBs Using Bi-Directional Recurrent Neural Networks
• BioNerFlair: biomedical named entity recognition using flair embedding and sequence tagger
• FGN: Fusion Glyph Network for Chinese Named Entity Recognition
• A Hybrid Variational Autoencoder for Collaborative Filtering
• Measuring relative opinion from location-based social media: A case study of the 2016 U.S. presidential election
• Survey on the Use of Typological Information in Natural Language Processing
• Bilingual Learning of Multi-sense Embeddings with Discrete Autoencoders
• Representing Documents and Queries as Sets of Word Embedded Vectors for Information Retrieval
• Adversarial Learning for Chinese NER from Crowd Annotations
• Distributed Representations for Compositional Semantics
• Characterizing Diseases from Unstructured Text: A Vocabulary Driven Word2vec Approach
• Layer-Parallel Training of Deep Residual Neural Networks
• A Re-ranking Model for Dependency Parser with Recursive Convolutional Neural Network
• Statistically Significant Detection of Linguistic Change
• Learning Distributed Word Representations for Natural Logic Reasoning
• Modeling Compositionality with Multiplicative Recurrent Neural Networks
• Recovery of simultaneous low rank and two-way sparse coefficient matrices, a nonconvex approach
• Generalize Symbolic Knowledge With Neural Rule Engine
• Learning from a Complementary-label Source Domain: Theory and Algorithms
• Learning to Infer Entities, Properties and their Relations from Clinical Conversations
• Machine Learning with World Knowledge: The Position and Survey
• Keystroke dynamics as signal for shallow syntactic parsing
• Revisiting Skip-Gram Negative Sampling Model with Rectification
• Still not there? Comparing Traditional Sequence-to-Sequence Models to Encoder-Decoder Neural Networks on Monotone String Translation Tasks
• Neural Baselines for Word Alignment
• We used Neural Networks to Detect Clickbaits: You won't believe what happened Next!
• A Financial Service Chatbot based on Deep Bidirectional Transformers
• Wireless for Machine Learning
• A Deep Causal Inference Approach to Measuring the Effects of Forming Group Loans in Online Non-profit Microfinance Platform
• An empirical assessment of deep learning approaches to task-oriented dialog management
• Sensitive Data Detection with High-Throughput Neural Network Models for Financial Institutions
• Alzheimer's Disease Detection from Spontaneous Speech through Combining Linguistic Complexity and (Dis)Fluency Features with Pretrained Language Models
• Deep Sequence Models for Text Classification Tasks
• Sequence embeddings help to identify fraudulent cases in healthcare insurance
• Analyzing the Perceived Severity of Cybersecurity Threats Reported on Social Media
• Gaussian Mixture Embeddings for Multiple Word Prototypes
• DAG-based Long Short-Term Memory for Neural Word Segmentation
• A Comparative Study on Regularization Strategies for Embedding-based Neural Networks
• Performance Evaluation of Deep Learning Tools in Docker Containers
• Recognizing Implicit Discourse Relations via Repeated Reading: Neural Networks with Multi-Level Attention
• Domain Adaptation for Named Entity Recognition in Online Media with Word Embeddings
• KNET: A General Framework for Learning Word Embedding using Morphological Knowledge
• A Context-Aware User-Item Representation Learning for Item Recommendation
• Neural Chinese Word Segmentation as Sequence to Sequence Translation
• Parareal Neural Networks Emulating a Parallel-in-time Algorithm
• Deploy Large-Scale Deep Neural Networks in Resource Constrained IoT Devices with Local Quantization Region
• Evaluation of taxonomic and neural embedding methods for calculating semantic similarity
• iCapsNets: Towards Interpretable Capsule Networks for Text Classification
• Opinion Recommendation using Neural Memory Model
• Word and Document Embeddings based on Neural Network Approaches
• On the Importance of Consistency in Training Deep Neural Networks
• Accelerating Minibatch Stochastic Gradient Descent using Typicality Sampling
• Biomedical Event Trigger Identification Using Bidirectional Recurrent Neural Network Based Models
• Aspect-based Opinion Summarization with Convolutional Neural Networks
• An Empirical Study on Sentiment Classification of Chinese Review using Word Embedding
• Better the Devil you Know: An Analysis of Evasion Attacks using Out-of-Distribution Adversarial Examples
• Generation-Distillation for Efficient Natural Language Understanding in Low-Data Settings
• Structured Query Construction via Knowledge Graph Embedding
• Event Identification as a Decision Process with Non-linear Representation of Text
• Category Enhanced Word Embedding
• Framing RNN as a kernel method: A neural ODE approach
• Improving Part-of-Speech Tagging for NLP Pipelines
• Sentiment Analysis Using Averaged Weighted Word Vector Features
• Structured Minimally Supervised Learning for Neural Relation Extraction
• An Attention-Gated Convolutional Neural Network for Sentence Classification
• Neural Named Entity Recognition from Subword Units
• Latent-Optimized Adversarial Neural Transfer for Sarcasm Detection
• On the Complementarity of Data Selection and Fine Tuning for Domain Adaptation
• Rethinking Generalization of Neural Models: A Named Entity Recognition Case Study
• Complex Structure Leads to Overfitting: A Structure Regularization Decoding Method for Natural Language Processing
• Multi-task Learning with Sample Re-weighting for Machine Reading Comprehension
• Classifying YouTube Comments Based on Sentiment and Type of Sentence
• HomeGuard: A Smart System to Deal with the Emergency Response of Domestic Violence Victims
• Named entity recognition in chemical patents using ensemble of contextual language models
• Does Higher Order LSTM Have Better Accuracy for Segmenting and Labeling Sequence Data?
• Studying Product Competition Using Representation Learning
• A Neural Transition-based Model for Nested Mention Recognition
• Bidirectional LSTM-CRF Attention-based Model for Chinese Word Segmentation
• Unpaired High-Resolution and Scalable Style Transfer Using Generative Adversarial Networks
• "The Sum of Its Parts": Joint Learning of Word and Phrase Representations with Autoencoders
• Syntax-aware Multilingual Semantic Role Labeling
• Using Chinese Glyphs for Named Entity Recognition
• F-SVM: Combination of Feature Transformation and SVM Learning via Convex Relaxation
• Improving Named Entity Recognition with Attentive Ensemble of Syntactic Information
• Reconstruction of training samples from loss functions
• Tutorial on Deep Learning for Human Activity Recognition
• Improving Portuguese Semantic Role Labeling with Transformers and Transfer Learning
• Light-Weighted CNN for Text Classification
• An Open-Source Dataset and A Multi-Task Model for Malay Named Entity Recognition
• SpeedRead: A Fast Named Entity Recognition Pipeline
• Learning Dense Representations of Phrases at Scale
• Real-Time Steganalysis for Stream Media Based on Multi-channel Convolutional Sliding Windows
• CM-Net: A Novel Collaborative Memory Network for Spoken Language Understanding
• A Unified Generative Framework for Various NER Subtasks
• Audio De-identification: A New Entity Recognition Task
• Jointly Trained Sequential Labeling and Classification by Sparse Attention Neural Networks
• Local Homology of Word Embeddings
• LanideNN: Multilingual Language Identification on Character Window
• A Joint Model for Word Embedding and Word Morphology
• Neural Cross-Lingual Transfer and Limited Annotated Data for Named Entity Recognition in Danish
• KoGuN: Accelerating Deep Reinforcement Learning via Integrating Human Suboptimal Knowledge
• Topology of Word Embeddings: Singularities Reflect Polysemy
• Evaluation of Greek Word Embeddings
• Multi-Stage Transfer Learning with an Application to Selection Process
• Multi-label Ranking: Mining Multi-label and Label Ranking Data
• A Survey On Neural Word Embeddings
• Modelling Latent Skills for Multitask Language Generation
• Supervised Fine Tuning for Word Embedding with Integrated Knowledge
• Exploring Different Dimensions of Attention for Uncertainty Detection
• Generalisation in Named Entity Recognition: A Quantitative Analysis
• Jointly Learning Semantic Parser and Natural Language Generator via Dual Information Maximization
• Learning Optimal Data Augmentation Policies via Bayesian Optimization for Image Classification Tasks
• Interpretable Text Classification Using CNN and Max-pooling
• Linking emotions to behaviors through deep transfer learning
• Language is Power: Representing States Using Natural Language in Reinforcement Learning
• Benchmarking BioRelEx for Entity Tagging and Relation Extraction
• HufuNet: Embedding the Left Piece as Watermark and Keeping the Right Piece for Ownership Verification in Deep Neural Networks
• RobOT: Robustness-Oriented Testing for Deep Learning Systems
• Towards More Fine-grained and Reliable NLP Performance Prediction
• Encoding Syntactic Knowledge in Transformer Encoder for Intent Detection and Slot Filling
• A hybrid deep-learning approach for complex biochemical named entity recognition
• Edge of chaos as a guiding principle for modern neural network training
• SpanNER: Named Entity Re-/Recognition as Span Prediction
• An MRC Framework for Semantic Role Labeling
• Sentiment and Emotion Classification of Epidemic Related Bilingual data from Social Media
• PatchX: Explaining Deep Models by Intelligible Pattern Patches for Time-series Classification
• Adversarial Attack and Defense of Structured Prediction Models
• Countering Language Drift with Seeded Iterated Learning
• Hybrid Neural Models For Sequence Modelling: The Best Of Three Worlds
• Low-Resource Name Tagging Learned with Weakly Labeled Data
• Exploring the importance of context and embeddings in neural NER models for task-oriented dialogue systems
• The Best of Both Worlds: Lexical Resources To Improve Low-Resource Part-of-Speech Tagging
• CIS at TAC Cold Start 2015: Neural Networks and Coreference Resolution for Slot Filling
• Multi Task Deep Morphological Analyzer: Context Aware Joint Morphological Tagging and Lemma Prediction
• Advancing PICO Element Detection in Biomedical Text via Deep Neural Networks
• Chinese User Service Intention Classification Based on Hybrid Neural Network
• Fast and Accurate Neural Word Segmentation for Chinese
• CB2CF: A Neural Multiview Content-to-Collaborative Filtering Model for Completely Cold Item Recommendations
• Topic Modeling Using Distributed Word Embeddings
• Words are not Equal: Graded Weighting Model for building Composite Document Vectors
• Streaming Punctuation: A Novel Punctuation Technique Leveraging Bidirectional Context for Continuous Speech Recognition
• Understanding Community Structure in Layered Neural Networks
• Emotion Recognition under Consideration of the Emotion Component Process Model
• Enhancing Sindhi Word Segmentation using Subword Representation Learning and Position-aware Self-attention
• An Aggressive Genetic Programming Approach for Searching Neural Network Structure Under Computational Constraints
• Cutting Recursive Autoencoder Trees
• Character-Level Feature Extraction with Densely Connected Networks
• Multiple Word Embeddings for Increased Diversity of Representation
• Multi-Label Sentiment Analysis on 100 Languages with Dynamic Weighting for Label Imbalance
• Investigating Meta-Learning Algorithms for Low-Resource Natural Language Understanding Tasks
• Bootstrapping NLU Models with Multi-task Learning
• Word Embedding Algorithms as Generalized Low Rank Models and their Canonical Form
• Comparing Convolutional Neural Networks to Traditional Models for Slot Filling
• Neural Semantic Role Labeling with Dependency Path Embeddings
• DSReg: Using Distant Supervision as a Regularizer
• Language Identification on Massive Datasets of Short Message using an Attention Mechanism CNN
• Exploring phrase-compositionality in skip-gram models
• Discovery of Latent Factors in High-dimensional Data Using Tensor Methods
• Integrated Inference and Learning of Neural Factors in Structural Support Vector Machines
• Multi-task Domain Adaptation for Sequence Tagging
• Thread Reconstruction in Conversational Data using Neural Coherence Models
• A Feature-Enriched Neural Model for Joint Chinese Word Segmentation and Part-of-Speech Tagging
• Transfer Deep Learning for Low-Resource Chinese Word Segmentation with a Novel Neural Network
• Modular Representation of Layered Neural Networks
• Masked Conditional Random Fields for Sequence Labeling
• Evaluation of Morphological Embeddings for the Russian Language
• Syntax-aware Neural Semantic Role Labeling
• Knowledge-Base Enriched Word Embeddings for Biomedical Domain
• Efficient Contextual Representation Learning Without Softmax Layer
• Multi-Task Learning of Keyphrase Boundary Classification
• Computation-Performance Optimization of Convolutional Neural Networks with Redundant Kernel Removal
• Experiments on transfer learning architectures for biomedical relation extraction
• Goal-driven Command Recommendations for Analysts
• Investigation on Data Adaptation Techniques for Neural Named Entity Recognition
• Data-driven models and computational tools for neurolinguistics: a language technology perspective
• Conceptual Text Summarizer: A new model in continuous vector space
• Attentive Convolution: Equipping CNNs with RNN-style Attention Mechanisms
• PAC-Bayes Analysis of Sentence Representation
• A Unified Neural Coherence Model
• Towards Coherent and Cohesive Long-form Text Generation
• Named Entity Recognition Only from Word Embeddings
• Combining Spans into Entities: A Neural Two-Stage Approach for Recognizing Discontiguous Entities
• Generalizing Natural Language Analysis through Span-relation Representations
• Neural Machine Translation: A Review and Survey
• Joint Multitask Learning for Community Question Answering Using Task-Specific Embeddings
• Comparing Attention-based Convolutional and Recurrent Neural Networks: Success and Limitations in Machine Reading Comprehension
• Bench-Marking Information Extraction in Semi-Structured Historical Handwritten Records
• Natural Language Processing for EHR-Based Computational Phenotyping
• Fake or Real? A Study of Arabic Satirical Fake News
• Modeling Fine-Grained Entity Types with Box Embeddings
• Knowledge Discovery from Layered Neural Networks based on Non-negative Task Decomposition
• A New Entity Extraction Method Based on Machine Reading Comprehension
• Crowdsourcing Evaluation of Saliency-based XAI Methods
• Asking Questions Like Educational Experts: Automatically Generating Question-Answer Pairs on Real-World Examination Data
• Autoencoding Improves Pre-trained Word Embeddings
• DiaLex: A Benchmark for Evaluating Multidialectal Arabic Word Embeddings
• RethinkCWS: Is Chinese Word Segmentation a Solved Task?
• I'm Sorry for Your Loss: Spectrally-Based Audio Distances Are Bad at Pitch
• Joint Space Neural Probabilistic Language Model for Statistical Machine Translation
• Evaluating Neural Word Embeddings for Sanskrit
• Principal Word Vectors
• Improved Word Sense Disambiguation Using Pre-Trained Contextualized Word Representations
• Joint Embeddings of Hierarchical Categories and Entities
• Bayesian nonparametric temporal dynamic clustering via autoregressive Dirichlet priors
• Dr.VOT : Measuring Positive and Negative Voice Onset Time in the Wild
• Neural Architectures for Named Entity Recognition
• Stack-propagation: Improved Representation Learning for Syntax
• Convolutional Neural Networks for Sentiment Analysis in Persian Social Media
• Information Extraction from Scientific Literature for Method Recommendation
• Exploring Semi-supervised Variational Autoencoders for Biomedical Relation Extraction
• Probabilistic Discriminative Learning with Layered Graphical Models
• A Smoother Way to Train Structured Prediction Models
• Multi-task Learning for Japanese Predicate Argument Structure Analysis
• How to best use Syntax in Semantic Role Labelling
• LTG-Oslo Hierarchical Multi-task Network: The importance of negation for document-level sentiment in Spanish
• Learning to Embed Words in Context for Syntactic Tasks
• Basic tasks of sentiment analysis
• Linking Tweets with Monolingual and Cross-Lingual News using Transformed Word Embeddings
• Efficient Inferencing of Compressed Deep Neural Networks
• Siamese convolutional networks based on phonetic features for cognate identification
• New word analogy corpus for exploring embeddings of Czech words
• Learning Word Embeddings from Intrinsic and Extrinsic Views
• Factorial Hidden Markov Models for Learning Representations of Natural Language
• Why Attention? Analyze BiLSTM Deficiency and Its Remedies in the Case of NER
• OCHADAI-KYOTO at SemEval-2021 Task 1: Enhancing Model Generalization and Robustness for Lexical Complexity Prediction
• Affinity Weighted Embedding
• A Factorized Recurrent Neural Network based architecture for medium to large vocabulary Language Modelling
• Dynamic texture and scene classification by transferring deep image features
• Sensitive Information Detection: Recursive Neural Networks for Encoding Context
• Character-level Deep Conflation for Business Data Analytics
• SNE: Signed Network Embedding
• Segmenting Messy Text: Detecting Boundaries in Text Derived from Historical Newspaper Images
• Co-Morbidity Exploration on Wearables Activity Data Using Unsupervised Pre-training and Multi-Task Learning
• Abstraction Learning
• Scaling Matters in Deep Structured-Prediction Models
• Syllable-based Neural Named Entity Recognition for Myanmar Language
• A Multilingual Encoding Method for Text Classification and Dialect Identification Using Convolutional Neural Network
• Expanding the Text Classification Toolbox with Cross-Lingual Embeddings
• Simplifying Neural Networks using Formal Verification
• A New Approach for Scalable Analysis of Microbial Communities
• Benchmarking Approximate Inference Methods for Neural Structured Prediction
• Exact gradient updates in time independent of output size for the spherical loss family
• Issue Framing in Online Discussion Fora
• Free as in Free Word Order: An Energy Based Model for Word Segmentation and Morphological Tagging in Sanskrit
• Deep Learning Approach for Intelligent Named Entity Recognition of Cyber Security
• A Multi-task Learning Approach for Named Entity Recognition using Local Detection
• Multi-Task Learning for Argumentation Mining
• Rumor Detection on Twitter with Claim-Guided Hierarchical Graph Attention Networks
• Learning Contextualized Music Semantics from Tags via a Siamese Network
• Sentiment Tagging with Partial Labels using Modular Architectures
• Exploiting Cross-Lingual Subword Similarities in Low-Resource Document Classification
• A Controller-Recognizer Framework: How necessary is recognition for control?
• Variational Sequential Labelers for Semi-Supervised Learning
• Radical-Enhanced Chinese Character Embedding
• Any-gram Kernels for Sentence Classification: A Sentiment Analysis Case Study
• Few-Shot Website Fingerprinting Attack
• NE-LP: Normalized Entropy and Loss Prediction based Sampling for Active Learning in Chinese Word Segmentation on EHRs
• Multi-Task Sequence Prediction For Tunisian Arabizi Multi-Level Annotation
• On computable abstractions (a conceptual introduction)
• Large Language Models for Few-Shot Named Entity Recognition
• PERS: A Personalized and Explainable POI Recommender System
• Locally-Contextual Nonlinear CRFs for Sequence Labeling
• Text classification with pixel embedding
• Word2Vec vs DBnary: Augmenting METEOR using Vector Representations or Lexical Resources?
• Query-Based Named Entity Recognition
• Identity-sensitive Word Embedding through Heterogeneous Networks
• Character-Level Neural Translation for Multilingual Media Monitoring in the SUMMA Project
• Resource-Size matters: Improving Neural Named Entity Recognition with Optimized Large Corpora
• Semantic Representation and Inference for NLP
• Embedding Lexical Features via Low-Rank Tensors
• Digital phase-only holography using deep conditional generative models
• A Convolutional Neural Network for Aspect Sentiment Classification
• Five lessons from building a deep neural network recommender
• On Architectures for Including Visual Information in Neural Language Models for Image Description
• A Hierarchical Deep Learning Natural Language Parser for Fashion
• Pronoun-Targeted Fine-tuning for NMT with Hybrid Losses
• IBM Deep Learning Service
• Semantic Role Labeling as Syntactic Dependency Parsing
• Seeing Colors: Learning Semantic Text Encoding for Classification
• A Survey on Why-Type Question Answering Systems
• Random Planted Forest: a directly interpretable tree ensemble
• Enhancing Sentence Relation Modeling with Auxiliary Character-level Embedding
• Hierarchical Multi Task Learning with Subword Contextual Embeddings for Languages with Rich Morphology
• Discovering topics with neural topic models built from PLSA assumptions
• Neural Latent Dependency Model for Sequence Labeling
• Exploiting Review Neighbors for Contextualized Helpfulness Prediction
• Examining and Mitigating Kernel Saturation in Convolutional Neural Networks using Negative Images
• Analyzing Structures in the Semantic Vector Space: A Framework for Decomposing Word Embeddings
• InverSynth: Deep Estimation of Synthesizer Parameter Configurations from Audio Signals
• Multiplex Word Embeddings for Selectional Preference Acquisition
• Hybrid Tiled Convolutional Neural Networks for Text Sentiment Classification
• Scalable Semantic Querying of Text
• The Visualization of Change in Word Meaning over Time using Temporal Word Embeddings
• Adma: A Flexible Loss Function for Neural Networks
• PyEuroVoc: A Tool for Multilingual Legal Document Classification with EuroVoc Descriptors
• Empirical Study of Named Entity Recognition Performance Using Distribution-aware Word Embedding
• Deep Learning Embeddings for Discontinuous Linguistic Units
• Linguistic Versus Latent Relations for Modeling Coherent Flow in Paragraphs
• Deep Neural Network for Analysis of DNA Methylation Data
• An Interpretable and Uncertainty Aware Multi-Task Framework for Multi-Aspect Sentiment Analysis
• Predicting User Engagement Status for Online Evaluation of Intelligent Assistants
• Analyzing the Surprising Variability in Word Embedding Stability Across Languages
• iobes: A Library for Span-Level Processing
• Leveraging Medical Sentiment to Understand Patients Health on Social Media
• Improving Neural Sequence Labelling using Additional Linguistic Information
• Corpus-level and Concept-based Explanations for Interpretable Document Classification
• Text Classification based on Multiple Block Convolutional Highways
• Low-Rank Hidden State Embeddings for Viterbi Sequence Labeling
• Leader: Prefixing a Length for Faster Word Vector Serialization
• Recurrent Neural Networks in Linguistic Theory: Revisiting Pinker and Prince (1988) and the Past Tense Debate
• AIN: Fast and Accurate Sequence Labeling with Approximate Inference Network
• REflex: Flexible Framework for Relation Extraction in Multiple Domains
• All Word Embeddings from One Embedding
• Emotion Detection with Neural Personal Discrimination
• Characterizing Partisan Political Narrative Frameworks about COVID-19 on Twitter
• Doc2Dict: Information Extraction as Text Generation
• Character-Level Models versus Morphology in Semantic Role Labeling
• SPOTS: An Accelerator for Sparse Convolutional Networks Leveraging Systolic General Matrix-Matrix Multiplication
• Beyond Fine-tuning: Few-Sample Sentence Embedding Transfer
• Compositional Network Embedding
• Towards Explainable Fact Checking
• AdaK-NER: An Adaptive Top-K Approach for Named Entity Recognition with Incomplete Annotations
• Toward a Standardized and More Accurate Indonesian Part-of-Speech Tagging
• Pushing on Text Readability Assessment: A Transformer Meets Handcrafted Linguistic Features
• CIKM AnalytiCup 2017 Lazada Product Title Quality Challenge An Ensemble of Deep and Shallow Learning to predict the Quality of Product Titles
• A Survey on Green Deep Learning
• In-depth Question classification using Convolutional Neural Networks
• Learning Structures for Deep Neural Networks
• Recognising Biomedical Names: Challenges and Solutions
• The data-driven localized wave solutions of the derivative nonlinear Schrodinger equation by using improved PINN approach
• Structural Guidance for Transformer Language Models
• #StayHome or #Marathon? Social Media Enhanced Pandemic Surveillance on Spatial-temporal Dynamic Graphs
• Convex Covariate Clustering for Classification
• Learning Energy-Based Approximate Inference Networks for Structured Applications in NLP
• Deep Stacking Networks for Low-Resource Chinese Word Segmentation with Transfer Learning
• Refining BERT Embeddings for Document Hashing via Mutual Information Maximization
• Integrating Approaches to Word Representation
• Modeling the Mind: A brief review
• Meta-Embedding as Auxiliary Task Regularization
• Deep neural network marketplace recommenders in online experiments
• Metadata Shaping: Natural Language Annotations for the Tail
• Phantom: A High-Performance Computational Core for Sparse Convolutional Neural Networks
• A $0.11-0.38$ pJ/cycle Differential Ring Oscillator in $65$ nm CMOS for Robust Neurocomputing
• An Investigation of Potential Function Designs for Neural CRF
• Deep Room Recognition Using Inaudible Echos
• Evaluating (and improving) the correspondence between deep neural networks and human representations
• A Corpus for Detecting High-Context Medical Conditions in Intensive Care Patient Notes Focusing on Frequently Readmitted Patients
• Computationally Efficient NER Taggers with Combined Embeddings and Constrained Decoding
• Uncertainty-Aware Label Refinement for Sequence Labeling
• Deformable Stacked Structure for Named Entity Recognition
• Changing the Narrative Perspective: From Deictic to Anaphoric Point of View
• TMR: Evaluating NER Recall on Tough Mentions
• Neural Data-to-Text Generation with Dynamic Content Planning
• Guarded Deep Learning using Scenario-Based Modeling
• Morphological Skip-Gram: Using morphological knowledge to improve word representation
• Deep Learning based, end-to-end metaphor detection in Greek language with Recurrent and Convolutional Neural Networks
• Word embedding and neural network on grammatical gender -- A case study of Swedish
• Neural Networks Models for Analyzing Magic: the Gathering Cards
• Syntax Role for Neural Semantic Role Labeling
• Generative latent neural models for automatic word alignment
• Multilevel Text Alignment with Cross-Document Attention
• Local Additivity Based Data Augmentation for Semi-supervised NER
• An Exploration of Arbitrary-Order Sequence Labeling via Energy-Based Inference Networks
• A Deep Learning-Based Approach for Measuring the Domain Similarity of Persian Texts
• Low-dimensional Query Projection based on Divergence Minimization Feedback Model for Ad-hoc Retrieval
• Concurrent Parsing of Constituency and Dependency
• Automatic Open Knowledge Acquisition via Long Short-Term Memory Networks with Feedback Negative Sampling
• Twitter Sentiment on Affordable Care Act using Score Embedding
• Linking artificial and human neural representations of language
• Distantly Supervised Question Parsing
• Pooling Hybrid Representations for Web Structured Data Annotation
• Bilingual Dictionary Induction for Bantu Languages
• Method of Tibetan Person Knowledge Extraction
• Sense Perception Common Sense Relationships
• Unnamed Entity Recognition of Sense Mentions
• Learning Contextualized Semantics from Co-occurring Terms via a Siamese Architecture
• Evaluating Pronominal Anaphora in Machine Translation: An Evaluation Measure and a Test Suite
• Pairwise Neural Machine Translation Evaluation
• Unity in Diversity: Learning Distributed Heterogeneous Sentence Representation for Extractive Summarization
• Semi-Implicit Back Propagation
• Alleviating Overfitting for Polysemous Words for Word Representation Estimation Using Lexicons
• Semantic Relatedness and Taxonomic Word Embeddings
• Text Classification with Lexicon from PreAttention Mechanism
• Search Intelligence: Deep Learning For Dominant Category Prediction
• Document Visualization using Topic Clouds
• Learning Sequence Neighbourhood Metrics
• Exploring the power of GPU's for training Polyglot language models
• Place classification with a graph regularized deep neural network model
• Adaptation of Hierarchical Structured Models for Speech Act Recognition in Asynchronous Conversation
• Distributional Models and Deep Learning Embeddings: Combining the Best of Both Worlds
• Deep Learning for Cross-Technology Communication Design
• Effective Context and Fragment Feature Usage for Named Entity Recognition
• Multi-hop Reading Comprehension via Deep Reinforcement Learning based Document Traversal
• FlexNER: A Flexible LSTM-CNN Stack Framework for Named Entity Recognition
• A WL-SPPIM Semantic Model for Document Classification
• CRNN: A Joint Neural Network for Redundancy Detection
• Neural Mention Detection
• Improve Lexicon-based Word Embeddings By Word Sense Disambiguation