Modeling Relational Information in Question-Answer Pairs with Convolutional Neural Networks

In this paper, we propose convolutional neural networks for learning an optimal representation of question and answer sentences. Their main aspect is the use of relational information given by the matches between words from the two members of the pair. The matches are encoded as embeddings with additional parameters (dimensions), which are tuned by the network. These allows for better capturing interactions between questions and answers, resulting in a significant boost in accuracy. We test our models on two widely used answer sentence selection benchmarks. The results clearly show the effectiveness of our relational information, which allows our relatively simple network to approach the state of the art.

• Publication year

  2016

• Venue

  arXiv.org

• Publication date

  2016-04-05

• Fields of study

  Computer Science

• Identifiers
  arXiv 1604.01178
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• FAQ-based Question Answering via Word Alignment

  2015cited by this paper
• Learning to Rank Short Text Pairs with Convolutional Deep Neural Networks

  2015cited by this paper
• SemEval-2015 Task 2: Semantic Textual Similarity, English, Spanish and Pilot on Interpretability

  2015cited by this paper
• ABCNN: Attention-Based Convolutional Neural Network for Modeling Sentence Pairs

  2015cited by this paper
• Neural Variational Inference for Text Processing

  2015influential reference
• WikiQA: A Challenge Dataset for Open-Domain Question Answering

  2015influential reference
• A Neural Network for Factoid Question Answering over Paragraphs

  2014cited by this paper
• A Convolutional Neural Network for Modelling Sentences

  2014cited by this paper
• Open Question Answering with Weakly Supervised Embedding Models

  2014cited by this paper
• Convolutional Neural Network Architectures for Matching Natural Language Sentences

  2014cited by this paper
• Semantic Parsing for Single-Relation Question Answering

  2014cited by this paper
• Convolutional Neural Networks for Sentence Classification

  2014influential reference
• Deep Learning for Answer Sentence Selection

  2014influential reference
• Modelling, Visualising and Summarising Documents with a Single Convolutional Neural Network

  2014cited by this paper
• Question Answering Using Enhanced Lexical Semantic Models

  2013influential reference
• Automatic Feature Engineering for Answer Selection and Extraction

  2013cited by this paper
• A Deep Architecture for Matching Short Texts

  2013cited by this paper
• Answer Extraction as Sequence Tagging with Tree Edit Distance

  2013cited by this paper
• Word Alignment Modeling with Context Dependent Deep Neural Network

  2013cited by this paper
• Distributed Representations of Words and Phrases and their Compositionality

  2013cited by this paper
• ADADELTA: An Adaptive Learning Rate Method

  2012cited by this paper
• Probabilistic Tree-Edit Models with Structured Latent Variables for Textual Entailment and Question Answering

  2010cited by this paper
• Rectified Linear Units Improve Restricted Boltzmann Machines

  2010cited by this paper
• Tree Edit Models for Recognizing Textual Entailments, Paraphrases, and Answers to Questions

  2010cited by this paper
• What is the Jeopardy Model? A Quasi-Synchronous Grammar for QA

  2007influential reference
• A Noisy-Channel Approach to Question Answering

  2003cited by this paper
• Compositionality

  1997cited by this paper

• Datasets for Multilingual Answer Sentence Selection

  2024cites this paper
• A Natural Language Processing Model for the Development of an Italian-Language Chatbot for Public Administration

  2024cites this paper
• Knowledge Graph Construction in Power Distribution Networks

  2023cites this paper
• Reranking Passages with Coarse-to-Fine Neural Retriever using List-Context Information

  2023influential citation
• Analysis of depression in social media texts through the Patient Health Questionnaire-9 and natural language processing

  2022cites this paper
• BRCNN: Chinese medical question answer selection based on BERT

  2022cites this paper
• Complex-valued Neural Network-based Quantum Language Models

  2022cites this paper
• QA4GIS: A novel approach learning to answer GIS developer questions with API documentation

  2021cites this paper
• Rap4DQ: Learning to recommend relevant API documentation for developer questions

  2021cites this paper
• A Collaborative AI-Enabled Pretrained Language Model for AIoT Domain Question Answering

  2021cites this paper
• Supervised Neural Clustering via Latent Structured Output Learning: Application to Question Intents

  2021cites this paper
• A Study on Efficiency, Accuracy and Document Structure for Answer Sentence Selection

  2020cites this paper
• Dialog-based Help Desk through Automated Question Answering and Intent Detection

  2020cites this paper
• Attention-based Convolutional Neural Network for Answer Selection using BERT

  2020cites this paper
• The Neural Network Conversation Model enables the Commonly Asked Student Query Agents

  2020cites this paper
• A Quantum Expectation Value Based Language Model with Application to Question Answering

  2020cites this paper
• Vertical intent prediction approach based on Doc2vec and convolutional neural networks for improving vertical selection in aggregated search

  2020cites this paper
• Improving the accuracy using pre-trained word embeddings on deep neural networks for Turkish text classification

  2020cites this paper
• Short Text Classification based on Feature Extension using Information in Images

  2019cites this paper
• Deformable Convolutional Matrix Factorization for Document Context-Aware Recommendation in Social Networks

  2019cites this paper
• A multi-approach to community question answering

  2019cites this paper
• Topic-Guided Coherence Modeling for Sentence Ordering by Preserving Global and Local Information

  2019cites this paper
• TANDA: Transfer and Adapt Pre-Trained Transformer Models for Answer Sentence Selection

  2019cites this paper
• Learning to answer programming questions with software documentation through social context embedding

  2018cites this paper
• End-to-End Quantum-like Language Models with Application to Question Answering

  2018cites this paper
• Cross-Pair Text Representations for Answer Sentence Selection

  2018cites this paper
• Semantic Linking in Convolutional Neural Networks for Answer Sentence Selection

  2018cites this paper
• A Quantum Many-body Wave Function Inspired Language Modeling Approach

  2018cites this paper
• Injecting Relational Structural Representation in Neural Networks for Question Similarity

  2018cites this paper
• Context-Aware Answer Sentence Selection With Hierarchical Gated Recurrent Neural Networks

  2018influential citation
• Recent Trends in Deep Learning Based Natural Language Processing [Review Article]

  2018cites this paper
• Unsupervised Sentence Embeddings for Answer Summarization in Non-factoid CQA

  2018cites this paper
• Adversarial Sampling and Training for Semi-Supervised Information Retrieval

  2018cites this paper
• Application of Convolutional Neural Network in Natural Language Processing

  2018cites this paper
• A Compare-Aggregate Model with Embedding Selector for Answer Selection

  2018influential citation
• Text Coherence Analysis Based on Deep Neural Network

  2017cites this paper
• Application of Deep learning Techniques to Natural Language Processing

  2017cites this paper
• Enhanced Embedding Based Attentive Pooling Network for Answer Selection

  2017cites this paper
• Semantic Search-by-Examples for Scientific Topic Corpus Expansion in Digital Libraries

  2017cites this paper
• YNUDLG at IJCNLP-2017 Task 5: A CNN-LSTM Model with Attention for Multi-choice Question Answering in Examinations

  2017cites this paper
• An Empirical Study on Incorporating Prior Knowledge into BLSTM Framework in Answer Selection

  2017cites this paper
• Recent Trends in Deep Learning Based Natural Language Processing

  2017cites this paper
• A Hybrid Framework for Text Modeling with Convolutional RNN

  2017cites this paper
• Sequence-to-sequence prediction of personal computer software by recurrent neural network

  2017cites this paper
• Deep Learning applied to NLP

  2017cites this paper
• An Enhanced Convolutional Neural Network Model for Answer Selection

  2017cites this paper
• Natural Language Comprehension with the EpiReader

  2016cites this paper
• Convolutional Neural Networks vs. Convolution Kernels: Feature Engineering for Answer Sentence Reranking

  2016cites this paper
• Crossword Puzzle Resolution in Italian using Distributional Models for Clue Similarity

  2016cites this paper