Match-SRNN: Modeling the Recursive Matching Structure with Spatial RNN
arXiv:1604.04378
Abstract
Semantic matching, which aims to determine the matching degree between two texts, is a fundamental problem for many NLP applications. Recently, deep learning approach has been applied to this problem and significant improvements have been achieved. In this paper, we propose to view the generation of the global interaction between two texts as a recursive process: i.e. the interaction of two texts at each position is a composition of the interactions between their prefixes as well as the word level interaction at the current position. Based on this idea, we propose a novel deep architecture, namely Match-SRNN, to model the recursive matching structure. Firstly, a tensor is constructed to capture the word level interactions. Then a spatial RNN is applied to integrate the local interactions recursively, with importance determined by four types of gates. Finally, the matching score is calculated based on the global interaction. We show that, after degenerated to the exact matching scenario, Match-SRNN can approximate the dynamic programming process of longest common subsequence. Thus, there exists a clear interpretation for Match-SRNN. Our experiments on two semantic matching tasks showed the effectiveness of Match-SRNN, and its ability of visualizing the learned matching structure.
Accepted by IJCAI-2016
References in corpus (2)
Cited by in corpus (34)
- A Deep Relevance Matching Model for Ad-hoc Retrieval
- Information Retrieval: Recent Advances and Beyond
- Semantic Models for the First-stage Retrieval: A Comprehensive Review
- Modeling Diverse Relevance Patterns in Ad-hoc Retrieval
- Neural Models for Information Retrieval
- Neural ranking models for document retrieval
- MatchZoo: A Toolkit for Deep Text Matching
- Learning a Product Relevance Model from Click-Through Data in E-Commerce
- Sequential Attention-based Network for Noetic End-to-End Response Selection
- Enhance word representation for out-of-vocabulary on Ubuntu dialogue corpus
- Multi-Cast Attention Networks for Retrieval-based Question Answering and Response Prediction
- Match-Ignition: Plugging PageRank into Transformer for Long-form Text Matching
- Speaker-Aware BERT for Multi-Turn Response Selection in Retrieval-Based Chatbots
- The Power of Selecting Key Blocks with Local Pre-ranking for Long Document Information Retrieval
- Match-Prompt: Improving Multi-task Generalization Ability for Neural Text Matching via Prompt Learning
- Semantic Product Search
- Expert Finding in Community Question Answering: A Review
- Legal Element-oriented Modeling with Multi-view Contrastive Learning for Legal Case Retrieval
- Sequential Matching Network: A New Architecture for Multi-turn Response Selection in Retrieval-based Chatbots
- A Sequential Matching Framework for Multi-turn Response Selection in Retrieval-based Chatbots
- RLTM: An Efficient Neural IR Framework for Long Documents
- BanditRank: Learning to Rank Using Contextual Bandits
- Toward the Understanding of Deep Text Matching Models for Information Retrieval
- A Social Search Model for Large Scale Social Networks
- Embedding-based Product Retrieval in Taobao Search
- Learning From Weights: A Cost-Sensitive Approach For Ad Retrieval
- Utterance-to-Utterance Interactive Matching Network for Multi-Turn Response Selection in Retrieval-Based Chatbots
- CONNA: Addressing Name Disambiguation on The Fly
- A multi-perspective combined recall and rank framework for Chinese procedure terminology normalization
- Improving Multi-Turn Response Selection Models with Complementary Last-Utterance Selection by Instance Weighting
- FILM: A Fast, Interpretable, and Low-rank Metric Learning Approach for Sentence Matching
- Embracing Structure in Data for Billion-Scale Semantic Product Search
- YES SIR!Optimizing Semantic Space of Negatives with Self-Involvement Ranker
- Attentive Long Short-Term Preference Modeling for Personalized Product Search