Machine Comprehension Using Match-LSTM and Answer Pointer
arXiv:1608.07905
Abstract
Machine comprehension of text is an important problem in natural language processing. A recently released dataset, the Stanford Question Answering Dataset (SQuAD), offers a large number of real questions and their answers created by humans through crowdsourcing. SQuAD provides a challenging testbed for evaluating machine comprehension algorithms, partly because compared with previous datasets, in SQuAD the answers do not come from a small set of candidate answers and they have variable lengths. We propose an end-to-end neural architecture for the task. The architecture is based on match-LSTM, a model we proposed previously for textual entailment, and Pointer Net, a sequence-to-sequence model proposed by Vinyals et al.(2015) to constrain the output tokens to be from the input sequences. We propose two ways of using Pointer Net for our task. Our experiments show that both of our two models substantially outperform the best results obtained by Rajpurkar et al.(2016) using logistic regression and manually crafted features.
11 pages; 3 figures
References in corpus (6)
- SQuAD: 100,000+ Questions for Machine Comprehension of Text
- Incorporating Copying Mechanism in Sequence-to-Sequence Learning
- A Thorough Examination of the CNN/Daily Mail Reading Comprehension Task
- End-to-End Answer Chunk Extraction and Ranking for Reading Comprehension
- Consensus Attention-based Neural Networks for Chinese Reading Comprehension
- Attention-Based Convolutional Neural Network for Machine Comprehension
Cited by in corpus (130)
- SQuAD: 100,000+ Questions for Machine Comprehension of Text
- Dynamic Coattention Networks For Question Answering
- The Natural Language Decathlon: Multitask Learning as Question Answering
- ReasoNet: Learning to Stop Reading in Machine Comprehension
- Adversarial Examples for Evaluating Reading Comprehension Systems
- Learning Recurrent Span Representations for Extractive Question Answering
- Multi-Perspective Context Matching for Machine Comprehension
- Rethinking Search: Making Domain Experts out of Dilettantes
- R: Reinforced Reader-Ranker for Open-Domain Question Answering
- DCN+: Mixed Objective and Deep Residual Coattention for Question Answering
- Exploring Graph-structured Passage Representation for Multi-hop Reading Comprehension with Graph Neural Networks
- A Joint Model for Question Answering and Question Generation
- NewsQA: A Machine Comprehension Dataset
- Focal Visual-Text Attention for Visual Question Answering
- MEMEN: Multi-layer Embedding with Memory Networks for Machine Comprehension
- A Survey on Transfer Learning in Natural Language Processing
- A Unified MRC Framework for Named Entity Recognition
- DuReader: a Chinese Machine Reading Comprehension Dataset from Real-world Applications
- A Unified Query-based Generative Model for Question Generation and Question Answering
- Machine Reading Comprehension: The Role of Contextualized Language Models and Beyond
- Entity-Relation Extraction as Multi-Turn Question Answering
- S-Net: From Answer Extraction to Answer Generation for Machine Reading Comprehension
- Cross-Lingual Machine Reading Comprehension
- Words or Characters? Fine-grained Gating for Reading Comprehension
- End-to-End Answer Chunk Extraction and Ranking for Reading Comprehension
- Reinforced Mnemonic Reader for Machine Reading Comprehension
- Exploring Question Understanding and Adaptation in Neural-Network-Based Question Answering
- U-Net: Machine Reading Comprehension with Unanswerable Questions
- Neural Question Generation from Text: A Preliminary Study
- Multi-range Reasoning for Machine Comprehension
- Dice Loss for Data-imbalanced NLP Tasks
- Description Based Text Classification with Reinforcement Learning
- A Comparative Study of Word Embeddings for Reading Comprehension
- Hierarchical Graph Network for Multi-hop Question Answering
- Machine Reading Comprehension: a Literature Review
- Semi-Supervised QA with Generative Domain-Adaptive Nets
- Neural Machine Reading Comprehension: Methods and Trends
- Don't Take the Easy Way Out: Ensemble Based Methods for Avoiding Known Dataset Biases
- Towards a Robust Deep Neural Network in Texts: A Survey
- Is Retriever Merely an Approximator of Reader?
- Focused Hierarchical RNNs for Conditional Sequence Processing
- Event Extraction by Answering (Almost) Natural Questions
- Learning Loss Functions for Semi-supervised Learning via Discriminative Adversarial Networks
- MemexQA: Visual Memex Question Answering
- Multi-Cast Attention Networks for Retrieval-based Question Answering and Response Prediction
- Subword-augmented Embedding for Cloze Reading Comprehension
- The Effect of Natural Distribution Shift on Question Answering Models
- A Comparative Study of Transformer-Based Language Models on Extractive Question Answering
- A Survey on Neural Machine Reading Comprehension
- Robust Machine Comprehension Models via Adversarial Training
- QA4IE: A Question Answering based Framework for Information Extraction
- An End-to-end Approach for Handling Unknown Slot Values in Dialogue State Tracking
- Phase Conductor on Multi-layered Attentions for Machine Comprehension
- Question Answering through Transfer Learning from Large Fine-grained Supervision Data
- Stochastic Answer Networks for SQuAD 2.0
- Discriminative Sentence Modeling for Story Ending Prediction
- Structural Embedding of Syntactic Trees for Machine Comprehension
- Simple and Effective Curriculum Pointer-Generator Networks for Reading Comprehension over Long Narratives
- Span-based Localizing Network for Natural Language Video Localization
- Smarnet: Teaching Machines to Read and Comprehend Like Human
- Question Answering over Knowledge Base using Language Model Embeddings
- Inter-BIN: Interaction-based Cross-architecture IoT Binary Similarity Comparison
- Ruminating Reader: Reasoning with Gated Multi-Hop Attention
- Attention-Guided Answer Distillation for Machine Reading Comprehension
- An Attention-Based Word-Level Interaction Model: Relation Detection for Knowledge Base Question Answering
- One-Shot Learning for Text-to-SQL Generation
- Answering Science Exam Questions Using Query Rewriting with Background Knowledge
- Multi-Passage Machine Reading Comprehension with Cross-Passage Answer Verification
- Distributed Representation for Traditional Chinese Medicine Herb via Deep Learning Models
- Bidirectional Attentive Memory Networks for Question Answering over Knowledge Bases
- Interactive Language Learning by Question Answering
- Joint Training of Candidate Extraction and Answer Selection for Reading Comprehension
- Sequence-to-Nuggets: Nested Entity Mention Detection via Anchor-Region Networks
- Controlling Risk of Web Question Answering
- Two-Stage Synthesis Networks for Transfer Learning in Machine Comprehension
- RefNet: A Reference-aware Network for Background Based Conversation
- A Vietnamese Dataset for Evaluating Machine Reading Comprehension
- Making Neural Machine Reading Comprehension Faster
- Neural Semantic Parsing in Low-Resource Settings with Back-Translation and Meta-Learning
- Sequential Copying Networks
- HAS-QA: Hierarchical Answer Spans Model for Open-domain Question Answering
- Stress Test Evaluation of Transformer-based Models in Natural Language Understanding Tasks
- Multimodal Dialogue State Tracking By QA Approach with Data Augmentation
- Around the GLOBE: Numerical Aggregation Question-Answering on Heterogeneous Genealogical Knowledge Graphs with Deep Neural Networks
- Nugget Proposal Networks for Chinese Event Detection
- Cross-Attention End-to-End ASR for Two-Party Conversations
- Integrated Triaging for Fast Reading Comprehension
- Improving the Robustness of QA Models to Challenge Sets with Variational Question-Answer Pair Generation
- Look at the First Sentence: Position Bias in Question Answering
- Context-Sensitive Generation Network for Handing Unknown Slot Values in Dialogue State Tracking
- Graph-augmented Learning to Rank for Querying Large-scale Knowledge Graph
- Noisy Text Data: Achilles' Heel of popular transformer based NLP models
- Harvesting and Refining Question-Answer Pairs for Unsupervised QA
- Title-Guided Encoding for Keyphrase Generation
- Adaptations of ROUGE and BLEU to Better Evaluate Machine Reading Comprehension Task
- JEC-QA: A Legal-Domain Question Answering Dataset
- Phrase-Indexed Question Answering: A New Challenge for Scalable Document Comprehension
- Multi-Mention Learning for Reading Comprehension with Neural Cascades
- Attentive Convolution: Equipping CNNs with RNN-style Attention Mechanisms
- An Empirical Study of Content Understanding in Conversational Question Answering
- Spatio-temporal Video Re-localization by Warp LSTM
- Conditioning LSTM Decoder and Bi-directional Attention Based Question Answering System
- Deep Understanding based Multi-Document Machine Reading Comprehension
- Deriving Commonsense Inference Tasks from Interactive Fictions
- The Training of Neuromodels for Machine Comprehension of Text. Brain2Text Algorithm
- ZJUKLAB at SemEval-2021 Task 4: Negative Augmentation with Language Model for Reading Comprehension of Abstract Meaning
- Automatic learner summary assessment for reading comprehension
- Amanuensis: The Programmer's Apprentice
- Interactive Fiction Game Playing as Multi-Paragraph Reading Comprehension with Reinforcement Learning
- DuReader_robust: A Chinese Dataset Towards Evaluating Robustness and Generalization of Machine Reading Comprehension in Real-World Applications
- Query Tracking for E-commerce Conversational Search: A Machine Comprehension Perspective
- Implicit Argument Prediction as Reading Comprehension
- A Study of the Tasks and Models in Machine Reading Comprehension
- Pay More Attention - Neural Architectures for Question-Answering
- Query-Based Named Entity Recognition
- An Empirical Analysis of Multiple-Turn Reasoning Strategies in Reading Comprehension Tasks
- Towards User Friendly Medication Mapping Using Entity-Boosted Two-Tower Neural Network
- MCR-Net: A Multi-Step Co-Interactive Relation Network for Unanswerable Questions on Machine Reading Comprehension
- REGMAPR - Text Matching Made Easy
- Bi-directional Cognitive Thinking Network for Machine Reading Comprehension
- A3Net: Adversarial-and-Attention Network for Machine Reading Comprehension
- NOAHQA: Numerical Reasoning with Interpretable Graph Question Answering Dataset
- Semantic Conditioned Dynamic Modulation for Temporal Sentence Grounding in Videos
- Tag and Correct: Question aware Open Information Extraction with Two-stage Decoding
- Hierarchical Attention: What Really Counts in Various NLP Tasks
- Effective Character-augmented Word Embedding for Machine Reading Comprehension
- CAESAR: Context Awareness Enabled Summary-Attentive Reader
- Multi-Granularity Representations of Dialog
- Cross Copy Network for Dialogue Generation
- Question-Aware Sentence Gating Networks for Question and Answering