Beihang-MSRA at SemEval-2017 Task 3: A Ranking System with Neural Matching Features for Community Question Answering

This paper presents the system in SemEval-2017 Task 3, Community Question Answering (CQA). We develop a ranking system that is capable of capturing semantic relations between text pairs with little word overlap. In addition to traditional NLP features, we introduce several neural network based matching features which enable our system to measure text similarity beyond lexicons. Our system significantly outperforms baseline methods and holds the second place in Subtask A and the fifth place in Subtask B, which demonstrates its efficacy on answer selection and question retrieval.

• Publication year

  2017

• Venue

  International Workshop on Semantic Evaluation

• Publication date

  2017-08-01

• Fields of study

  Computer Science

• Identifiers
  DOI 10.18653/v1/S17-2045
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• SemEval-2017 Task 3: Community Question Answering

  2017influential reference
• Aggregating Inter-Sentence Information to Enhance Relation Extraction

  2016cited by this paper
• Expert Finding for Community-Based Question Answering via Ranking Metric Network Learning

  2016cited by this paper
• Community-Based Question Answering via Heterogeneous Social Network Learning

  2016cited by this paper
• XGBoost: A Scalable Tree Boosting System

  2016cited by this paper
• Knowledge Enhanced Hybrid Neural Network for Text Matching

  2016influential reference
• Learning Distributed Representations of Data in Community Question Answering for Question Retrieval

  2016cited by this paper
• Dropout: a simple way to prevent neural networks from overfitting

  2014cited by this paper
• Distributed Representations of Words and Phrases and their Compositionality

  2013cited by this paper
• Adaptive Subgradient Methods for Online Learning and Stochastic Optimization

  2011cited by this paper
• Rectified Linear Units Improve Restricted Boltzmann Machines

  2010cited by this paper
• Learning to rank for information retrieval

  2009cited by this paper
• Efficient Convolution Kernels for Dependency and Constituent Syntactic Trees

  2006cited by this paper
• NLTK: The Natural Language Toolkit

  2006cited by this paper
• Finding similar questions in large question and answer archives

  2005cited by this paper
• Fast Kernels for String and Tree Matching

  2004cited by this paper
• Accurate Unlexicalized Parsing

  2003cited by this paper
• New Ranking Algorithms for Parsing and Tagging: Kernels over Discrete Structures, and the Voted Perceptron

  2002cited by this paper
• Fast Kernels for String and Tree Matching

  2002cited by this paper
• Overfitting and neural networks: conjugate gradient and backpropagation

  2000cited by this paper
• Bidirectional recurrent neural networks

  1997influential reference
• Long Short-Term Memory

  1997cited by this paper
• Term-Weighting Approaches in Automatic Text Retrieval

  1988cited by this paper
• A Bit-String Longest-Common-Subsequence Algorithm

  1986cited by this paper

• HSM-QA: Question Answering System Based on Hierarchical Semantic Matching

  2023cites this paper
• Answer selection in community question answering exploiting knowledge graph and context information

  2022cites this paper
• Data Augmentation Methods for Semantic Similarity Detection in Vietnamese Questionnaire

  2022cites this paper
• DGQAN: Dual Graph Question-Answer Attention Networks for Answer Selection

  2022influential citation
• tBERT: Topic Models and BERT Joining Forces for Semantic Similarity Detection

  2020cites this paper
• Attentive User-Engaged Adversarial Neural Network for Community Question Answering

  2020cites this paper
• Better Early than Late: Fusing Topics with Word Embeddings for Neural Question Paraphrase Identification

  2020cites this paper
• GiBERT: Introducing Linguistic Knowledge into BERT through a Lightweight Gated Injection Method

  2020cites this paper
• Open Event Trigger Recognition Using Distant Supervision with Hierarchical Self-attentive Neural Network

  2020cites this paper
• AMQAN: Adaptive Multi-Attention Question-Answer Networks for Answer Selection

  2020cites this paper
• Focusing Attention Network for Answer Ranking

  2019cites this paper
• Learning pairwise patterns in Community Question Answering

  2019cites this paper
• Advanced community question answering by leveraging external knowledge and multi-task learning

  2019cites this paper
• CodeForTheChange at SemEval-2019 Task 8: Skip-Thoughts for Fact Checking in Community Question Answering

  2019cites this paper
• Fermi at SemEval-2019 Task 8: An elementary but effective approach to Question Discernment in Community QA Forums

  2019cites this paper
• Question Condensing Networks for Answer Selection in Community Question Answering

  2018cites this paper
• SemEval-2017 Task 3: Community Question Answering

  2017cites this paper
• Question Dependent Recurrent Entity Network for Question Answering

  2017cites this paper