A Compare-Aggregate Model for Matching Text Sequences

Abstract

Many NLP tasks including machine comprehension, answer selection and text entailment require the comparison between sequences. Matching the important units between sequences is a key to solve these problems. In this paper, we present a general "compare-aggregate" framework that performs word-level matching followed by aggregation using Convolutional Neural Networks. We particularly focus on the different comparison functions we can use to match two vectors. We use four different datasets to evaluate the model. We find that some simple comparison functions based on element-wise operations can work better than standard neural network and neural tensor network.

11 pages, 2 figures

Cited by in corpus (18)

• Rethinking Search: Making Domain Experts out of Dilettantes
• Deep Graph Matching and Searching for Semantic Code Retrieval
• Focal Visual-Text Attention for Visual Question Answering
• Neural ranking models for document retrieval
• TARN: Temporal Attentive Relation Network for Few-Shot and Zero-Shot Action Recognition
• A Deep Look into Neural Ranking Models for Information Retrieval
• Multi-turn Inference Matching Network for Natural Language Inference
• Interactive Matching Network for Multi-Turn Response Selection in Retrieval-Based Chatbots
• Learning to Respond with Your Favorite Stickers: A Framework of Unifying Multi-Modality and User Preference in Multi-Turn Dialog
• Modelling Domain Relationships for Transfer Learning on Retrieval-based Question Answering Systems in E-commerce
• Learning to Respond with Stickers: A Framework of Unifying Multi-Modality in Multi-Turn Dialog
• Matching Text with Deep Mutual Information Estimation
• Context-based Transformer Models for Answer Sentence Selection
• MS-Ranker: Accumulating Evidence from Potentially Correct Candidates for Answer Selection
• Answer Ranking for Product-Related Questions via Multiple Semantic Relations Modeling
• Entity Synonym Discovery via Multipiece Bilateral Context Matching
• Semantic Matching of Documents from Heterogeneous Collections: A Simple and Transparent Method for Practical Applications
• Hierarchical Ranking for Answer Selection