Text Matching as Image Recognition
arXiv:1602.06359
Abstract
Matching two texts is a fundamental problem in many natural language processing tasks. An effective way is to extract meaningful matching patterns from words, phrases, and sentences to produce the matching score. Inspired by the success of convolutional neural network in image recognition, where neurons can capture many complicated patterns based on the extracted elementary visual patterns such as oriented edges and corners, we propose to model text matching as the problem of image recognition. Firstly, a matching matrix whose entries represent the similarities between words is constructed and viewed as an image. Then a convolutional neural network is utilized to capture rich matching patterns in a layer-by-layer way. We show that by resembling the compositional hierarchies of patterns in image recognition, our model can successfully identify salient signals such as n-gram and n-term matchings. Experimental results demonstrate its superiority against the baselines.
Accepted by AAAI-2016
References in corpus (5)
- Efficient Estimation of Word Representations in Vector Space
- Improving neural networks by preventing co-adaptation of feature detectors
- Caffe: Convolutional Architecture for Fast Feature Embedding
- Convolutional Neural Network Architectures for Matching Natural Language Sentences
- A Convolutional Neural Network for Modelling Sentences
Cited by in corpus (36)
- A Deep Relevance Matching Model for Ad-hoc Retrieval
- End-to-End Neural Ad-hoc Ranking with Kernel Pooling
- Beyond 512 Tokens: Siamese Multi-depth Transformer-based Hierarchical Encoder for Long-Form Document Matching
- Neural Models for Information Retrieval
- A Study of MatchPyramid Models on Ad-hoc Retrieval
- Diverse Weighted Bipartite b-Matching
- Neural Information Retrieval: A Literature Review
- Multiresolution Graph Attention Networks for Relevance Matching
- MatchZoo: A Toolkit for Deep Text Matching
- A Study of Neural Matching Models for Cross-lingual IR
- EENMF: An End-to-End Neural Matching Framework for E-Commerce Sponsored Search
- Multi-Cast Attention Networks for Retrieval-based Question Answering and Response Prediction
- Ranking Distillation: Learning Compact Ranking Models With High Performance for Recommender System
- Match-Tensor: a Deep Relevance Model for Search
- DeepTileBars: Visualizing Term Distribution for Neural Information Retrieval
- Learning to Match Using Local and Distributed Representations of Text for Web Search
- A Deep Investigation of Deep IR Models
- Transfer Learning for Context-Aware Question Matching in Information-seeking Conversations in E-commerce
- A Fast Deep Learning Model for Textual Relevance in Biomedical Information Retrieval
- Co-PACRR: A Context-Aware Neural IR Model for Ad-hoc Retrieval
- Improving Multilingual Semantic Textual Similarity with Shared Sentence Encoder for Low-resource Languages
- An Auto-Encoder Matching Model for Learning Utterance-Level Semantic Dependency in Dialogue Generation
- Lattice CNNs for Matching Based Chinese Question Answering
- Multi-Perspective Relevance Matching with Hierarchical ConvNets for Social Media Search
- A Comparison of Supervised Learning to Match Methods for Product Search
- Learning Fine-grained Fact-Article Correspondence in Legal Cases
- Modelling Domain Relationships for Transfer Learning on Retrieval-based Question Answering Systems in E-commerce
- Interaction Matching for Long-Tail Multi-Label Classification
- RLTM: An Efficient Neural IR Framework for Long Documents
- Word Embedding based Edit Distance
- Identifying High-Quality Chinese News Comments Based on Multi-Target Text Matching Model
- Luandri: a Clean Lua Interface to the Indri Search Engine
- Match: A Matching over Matching Model for Similar Question Identification
- Impact of Training Dataset Size on Neural Answer Selection Models
- GiBERT: Introducing Linguistic Knowledge into BERT through a Lightweight Gated Injection Method
- GTM: A Generative Triple-Wise Model for Conversational Question Generation