Deep Learning for Answer Sentence Selection

Abstract

Answer sentence selection is the task of identifying sentences that contain the answer to a given question. This is an important problem in its own right as well as in the larger context of open domain question answering. We propose a novel approach to solving this task via means of distributed representations, and learn to match questions with answers by considering their semantic encoding. This contrasts prior work on this task, which typically relies on classifiers with large numbers of hand-crafted syntactic and semantic features and various external resources. Our approach does not require any feature engineering nor does it involve specialist linguistic data, making this model easily applicable to a wide range of domains and languages. Experimental results on a standard benchmark dataset from TREC demonstrate that---despite its simplicity---our model matches state of the art performance on the answer sentence selection task.

9 pages, accepted by NIPS deep learning workshop

References in corpus (3)

• A Convolutional Neural Network for Modelling Sentences
• Question Answering with Subgraph Embeddings
• Open Question Answering with Weakly Supervised Embedding Models

Cited by in corpus (30)

• A Deep Reinforcement Learning Chatbot
• Question Answering and Question Generation as Dual Tasks
• Extraction of Salient Sentences from Labelled Documents
• Neural Information Retrieval: A Literature Review
• Legal Question Answering using Ranking SVM and Deep Convolutional Neural Network
• FAQ-based Question Answering via Word Alignment
• DeepStory: Video Story QA by Deep Embedded Memory Networks
• Learning for Biomedical Information Extraction: Methodological Review of Recent Advances
• CNM: An Interpretable Complex-valued Network for Matching
• Towards Scalable and Reliable Capsule Networks for Challenging NLP Applications
• Neural Matching Models for Question Retrieval and Next Question Prediction in Conversation
• Learning to Paraphrase for Question Answering
• Answer Sequence Learning with Neural Networks for Answer Selection in Community Question Answering
• Answer Interaction in Non-factoid Question Answering Systems
• Adversarial Domain Adaptation for Stance Detection
• On the Benefit of Combining Neural, Statistical and External Features for Fake News Identification
• Passage Ranking with Weak Supervision
• Emulating Human Conversations using Convolutional Neural Network-based IR
• A Deep Look into Neural Ranking Models for Information Retrieval
• A survey of Community Question Answering
• Cross Temporal Recurrent Networks for Ranking Question Answer Pairs
• Evaluating KGR10 Polish word embeddings in the recognition of temporal expressions using BiLSTM-CRF
• Hierarchical Question Answering for Long Documents
• Deep Feature Fusion Network for Answer Quality Prediction in Community Question Answering
• A Cross-Architecture Instruction Embedding Model for Natural Language Processing-Inspired Binary Code Analysis
• Lattice CNNs for Matching Based Chinese Question Answering
• Prepositions in Context
• Macquarie University at BioASQ 5b -- Query-based Summarisation Techniques for Selecting the Ideal Answers
• Discriminative Information Retrieval for Knowledge Discovery
• Attentive Recurrent Tensor Model for Community Question Answering