Authors: Ankur P. Parikh , Oscar Täckström , Dipanjan Das , Jakob Uszkoreit - Conference on Empirical Methods in Natural Language Processing, EMNLP 2016 cited by 1,372
We propose a simple neural architecture for natural language inference. Our approach uses attention to decompose the problem into subproblems that can be solved separately, thus making it trivially parallelizable. On the Stanford Natural Language Inference (SNLI) dataset, we obtain state-of-the-art results with almost an order of magnitude fewer parameters than previous work and without relying on any word-order information. Adding intra-sentence attention that takes a minimum amount of order into account yields further improvements.
✨ Checking sign-in… PDF Cited by View BibTeX Hide BibTeX View BibTeX Cite
Long Short-Term Memory Long Short-Term Memory Learning to recognize features of valid… Learning to recognize features of valid textual entailments A Phrase-Based Alignment Model for Natural… A Phrase-Based Alignment Model for Natural Language Inference An extended model of natural logic An extended model of natural logic Adaptive Subgradient Methods for Online… Adaptive Subgradient Methods for Online Learning and Stochastic Optimization Glove: Global Vectors for Word Representation Glove: Global Vectors for Word Representation Dropout: a simple way to prevent neural networks… Dropout: a simple way to prevent neural networks from overfitting A large annotated corpus for learning natural… A large annotated corpus for learning natural language inference Neural Machine Translation by Jointly… Neural Machine Translation by Jointly Learning to Align and Translate Long Short-Term Memory-Networks for… Long Short-Term Memory-Networks for Machine Reading A Fast Unified Model for Parsing and Sentence… A Fast Unified Model for Parsing and Sentence Understanding ABCNN: Attention-Based Convolutional Neural… ABCNN: Attention-Based Convolutional Neural Network for Modeling Sentence Pairs openalex_id:w2949227999 openalex_id:w2949227999 Enhancing and Combining Sequential and Tree LST… Enhancing and Combining Sequential and Tree LSTM for Natural Language Inference Learning to Paraphrase for Question Answering Learning to Paraphrase for Question Answering Neural Tree Indexers for Text Understanding Neural Tree Indexers for Text Understanding A Broad-Coverage Challenge Corpus for… A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference Cross-Lingual Argumentative Relation… Cross-Lingual Argumentative Relation Identification: from English to Portuguese Answering Science Exam Questions Using Query… Answering Science Exam Questions Using Query Rewriting with Background Knowledge Self-Attention Graph Pooling Self-Attention Graph Pooling Natural Questions: a Benchmark for Question… Natural Questions: a Benchmark for Question Answering Research E3: Entailment-driven Extracting and Editing… E3: Entailment-driven Extracting and Editing for Conversational Machine Reading Asynchronous Deep Interaction Network for… Asynchronous Deep Interaction Network for Natural Language Inference Explaining Deep Neural Networks Explaining Deep Neural Networks A Decomposable Attention Model for Natural… A Decomposable Attention Model for Natural Language Inference Earlier references Focus paper Citing papers Older Newer Click a node to pin it, click the empty canvas to go back to this paper, or hover to preview. Open a node’s page from its title.
