Neural Natural Language Inference Models Enhanced with External Knowledge

Abstract

Modeling natural language inference is a very challenging task. With the availability of large annotated data, it has recently become feasible to train complex models such as neural-network-based inference models, which have shown to achieve the state-of-the-art performance. Although there exist relatively large annotated data, can machines learn all knowledge needed to perform natural language inference (NLI) from these data? If not, how can neural-network-based NLI models benefit from external knowledge and how to build NLI models to leverage it? In this paper, we enrich the state-of-the-art neural natural language inference models with external knowledge. We demonstrate that the proposed models improve neural NLI models to achieve the state-of-the-art performance on the SNLI and MultiNLI datasets.

Accepted by ACL 2018

References in corpus (15)

• Adam: A Method for Stochastic Optimization
• Semantic Similarity Based on Corpus Statistics and Lexical Taxonomy
• A Structured Self-attentive Sentence Embedding
• Enhanced LSTM for Natural Language Inference
• Reasoning about Entailment with Neural Attention
• Learning Natural Language Inference using Bidirectional LSTM model and Inner-Attention
• Natural Language Inference over Interaction Space
• Long Short-Term Memory-Networks for Machine Reading
• Bilateral Multi-Perspective Matching for Natural Language Sentences
• DiSAN: Directional Self-Attention Network for RNN/CNN-Free Language Understanding
• A Neural Knowledge Language Model
• Semantic Specialisation of Distributional Word Vector Spaces using Monolingual and Cross-Lingual Constraints
• Exploring Question Understanding and Adaptation in Neural-Network-Based Question Answering
• Knowledge as a Teacher: Knowledge-Guided Structural Attention Networks
• Memory-augmented Chinese-Uyghur Neural Machine Translation

Cited by in corpus (69)

• Deep Entity Matching with Pre-Trained Language Models
• A Question-Entailment Approach to Question Answering
• ERNIE: Enhanced Language Representation with Informative Entities
• Molecule Attention Transformer
• Graph Neural Networks for Natural Language Processing: A Survey
• Recent Advances in Natural Language Inference: A Survey of Benchmarks, Resources, and Approaches
• Enhancing Sentence Embedding with Generalized Pooling
• Two Stage Transformer Model for COVID-19 Fake News Detection and Fact Checking
• Using Prior Knowledge to Guide BERT's Attention in Semantic Textual Matching Tasks
• Semantic Sentence Matching with Densely-connected Recurrent and Co-attentive Information
• Incorporating Domain Knowledge into Medical NLI using Knowledge Graphs
• How Additional Knowledge can Improve Natural Language Commonsense Question Answering?
• Learning Semantic Textual Similarity from Conversations
• Sequential Attention-based Network for Noetic End-to-End Response Selection
• Pair-Level Supervised Contrastive Learning for Natural Language Inference
• Learning to Detect Relevant Contexts and Knowledge for Response Selection in Retrieval-based Dialogue Systems
• Knowledge Fusion and Semantic Knowledge Ranking for Open Domain Question Answering
• Explaining Deep Neural Networks
• FarsTail: A Persian Natural Language Inference Dataset
• Improving Natural Language Inference Using External Knowledge in the Science Questions Domain
• Deep Retrieval-Based Dialogue Systems: A Short Review
• Conditional Self-Attention for Query-based Summarization
• Commonsense for Generative Multi-Hop Question Answering Tasks
• Improving Question Answering by Commonsense-Based Pre-Training
• Knowledge Enhanced Contextual Word Representations
• Answering Science Exam Questions Using Query Rewriting with Background Knowledge
• An Exploration of Dropout with RNNs for Natural Language Inference
• Knowledge Enhanced Attention for Robust Natural Language Inference
• Towards Interpreting and Mitigating Shortcut Learning Behavior of NLU Models
• Learning to Deceive Knowledge Graph Augmented Models via Targeted Perturbation
• Breaking NLI Systems with Sentences that Require Simple Lexical Inferences
• Medical Knowledge Graph QA for Drug-Drug Interaction Prediction based on Multi-hop Machine Reading Comprehension
• Relational Graph Representation Learning for Open-Domain Question Answering
• Reasoning Over Virtual Knowledge Bases With Open Predicate Relations
• Bilinear Fusion of Commonsense Knowledge with Attention-Based NLI Models
• Benchmarking Knowledge-Enhanced Commonsense Question Answering via Knowledge-to-Text Transformation
• Several Experiments on Investigating Pretraining and Knowledge-Enhanced Models for Natural Language Inference
• Who did They Respond to? Conversation Structure Modeling using Masked Hierarchical Transformer
• Can neural networks understand monotonicity reasoning?
• Improving Generalization by Incorporating Coverage in Natural Language Inference
• Improving the Similarity Measure of Determinantal Point Processes for Extractive Multi-Document Summarization
• Augmenting Neural Networks with First-order Logic
• Path-Based Contextualization of Knowledge Graphs for Textual Entailment
• What If We Simply Swap the Two Text Fragments? A Straightforward yet Effective Way to Test the Robustness of Methods to Confounding Signals in Nature Language Inference Tasks
• Learning Fine-grained Fact-Article Correspondence in Legal Cases
• Guiding Extractive Summarization with Question-Answering Rewards
• Combining Axiom Injection and Knowledge Base Completion for Efficient Natural Language Inference
• Query-Variant Advertisement Text Generation with Association Knowledge
• Knowledge Efficient Deep Learning for Natural Language Processing
• On-The-Fly Information Retrieval Augmentation for Language Models
• A Template-guided Hybrid Pointer Network for Knowledge-basedTask-oriented Dialogue Systems
• Prediction, Selection, and Generation: Exploration of Knowledge-Driven Conversation System
• Program Enhanced Fact Verification with Verbalization and Graph Attention Network
• Knowledge-Empowered Representation Learning for Chinese Medical Reading Comprehension: Task, Model and Resources
• Discourse Marker Augmented Network with Reinforcement Learning for Natural Language Inference
• What's Missing: A Knowledge Gap Guided Approach for Multi-hop Question Answering
• Abductive Reasoning as Self-Supervision for Common Sense Question Answering
• AWE: Asymmetric Word Embedding for Textual Entailment
• Dropping Networks for Transfer Learning
• Unsupervised Pre-training with Structured Knowledge for Improving Natural Language Inference
• Knowledge-Enhanced Evidence Retrieval for Counterargument Generation
• COVIDRead: A Large-scale Question Answering Dataset on COVID-19
• Does External Knowledge Help Explainable Natural Language Inference? Automatic Evaluation vs. Human Ratings
• Exploring End-to-End Differentiable Natural Logic Modeling
• Automatic Distractor Generation for Multiple Choice Questions in Standard Tests
• Identify, Align, and Integrate: Matching Knowledge Graphs to Commonsense Reasoning Tasks
• Mining Knowledge for Natural Language Inference from Wikipedia Categories
• ExBERT: An External Knowledge Enhanced BERT for Natural Language Inference
• Multi-Perspective Inferrer: Reasoning Sentences Relationship from Holistic Perspective