A Deep Relevance Matching Model for Ad-hoc Retrieval

Abstract

In recent years, deep neural networks have led to exciting breakthroughs in speech recognition, computer vision, and natural language processing (NLP) tasks. However, there have been few positive results of deep models on ad-hoc retrieval tasks. This is partially due to the fact that many important characteristics of the ad-hoc retrieval task have not been well addressed in deep models yet. Typically, the ad-hoc retrieval task is formalized as a matching problem between two pieces of text in existing work using deep models, and treated equivalent to many NLP tasks such as paraphrase identification, question answering and automatic conversation. However, we argue that the ad-hoc retrieval task is mainly about relevance matching while most NLP matching tasks concern semantic matching, and there are some fundamental differences between these two matching tasks. Successful relevance matching requires proper handling of the exact matching signals, query term importance, and diverse matching requirements. In this paper, we propose a novel deep relevance matching model (DRMM) for ad-hoc retrieval. Specifically, our model employs a joint deep architecture at the query term level for relevance matching. By using matching histogram mapping, a feed forward matching network, and a term gating network, we can effectively deal with the three relevance matching factors mentioned above. Experimental results on two representative benchmark collections show that our model can significantly outperform some well-known retrieval models as well as state-of-the-art deep matching models.

CIKM 2016, long paper

References in corpus (3)

• Convolutional Neural Network Architectures for Matching Natural Language Sentences
• A Convolutional Neural Network for Modelling Sentences
• Syntax-based Deep Matching of Short Texts

Cited by in corpus (68)

• End-to-End Neural Ad-hoc Ranking with Kernel Pooling
• Deeper Text Understanding for IR with Contextual Neural Language Modeling
• Multi-Stage Document Ranking with BERT
• Understanding the Behaviors of BERT in Ranking
• Simple Applications of BERT for Ad Hoc Document Retrieval
• Word-Entity Duet Representations for Document Ranking
• A study on the Interpretability of Neural Retrieval Models using DeepSHAP
• Unseen Class Discovery in Open-world Classification
• Neural Information Retrieval: A Literature Review
• MatchZoo: A Learning, Practicing, and Developing System for Neural Text Matching
• Multiresolution Graph Attention Networks for Relevance Matching
• MatchZoo: A Toolkit for Deep Text Matching
• A Study of Neural Matching Models for Cross-lingual IR
• Novel Entity Discovery from Web Tables
• Learning to Selectively Transfer: Reinforced Transfer Learning for Deep Text Matching
• Neural Matching Models for Question Retrieval and Next Question Prediction in Conversation
• Preliminary Exploration of Formula Embedding for Mathematical Information Retrieval: can mathematical formulae be embedded like a natural language?
• Incorporating Query Term Independence Assumption for Efficient Retrieval and Ranking using Deep Neural Networks
• Selective Weak Supervision for Neural Information Retrieval
• Passage Ranking with Weak Supervision
• Leveraging Semantic and Lexical Matching to Improve the Recall of Document Retrieval Systems: A Hybrid Approach
• Match-Tensor: a Deep Relevance Model for Search
• A Deep Look into Neural Ranking Models for Information Retrieval
• Learning to Match Using Local and Distributed Representations of Text for Web Search
• Semantic Product Search
• Learning Contextualized Document Representations for Healthcare Answer Retrieval
• GRAPHENE: A Precise Biomedical Literature Retrieval Engine with Graph Augmented Deep Learning and External Knowledge Empowerment
• A Deep Investigation of Deep IR Models
• Domain Adaptation for Enterprise Email Search
• Neural IR Meets Graph Embedding: A Ranking Model for Product Search
• Co-PACRR: A Context-Aware Neural IR Model for Ad-hoc Retrieval
• Guided Transformer: Leveraging Multiple External Sources for Representation Learning in Conversational Search
• Improving Low-Resource Cross-lingual Document Retrieval by Reranking with Deep Bilingual Representations
• One word at a time: adversarial attacks on retrieval models
• Variational Deep Semantic Hashing for Text Documents
• Integrating Lexical and Temporal Signals in Neural Ranking Models for Searching Social Media Streams
• Longformer for MS MARCO Document Re-ranking Task
• Neural Ranking Models with Weak Supervision
• LATTE: Latent Type Modeling for Biomedical Entity Linking
• SPARTA: Efficient Open-Domain Question Answering via Sparse Transformer Matching Retrieval
• A Comparison of Supervised Learning to Match Methods for Product Search
• Towards Personalized and Semantic Retrieval: An End-to-End Solution for E-commerce Search via Embedding Learning
• Modeling Document Interactions for Learning to Rank with Regularized Self-Attention
• ICS-Assist: Intelligent Customer Inquiry Resolution Recommendation in Online Customer Service for Large E-Commerce Businesses
• BanditRank: Learning to Rank Using Contextual Bandits
• Context Attentive Document Ranking and Query Suggestion
• Getting Started with Neural Models for Semantic Matching in Web Search
• IART: Intent-aware Response Ranking with Transformers in Information-seeking Conversation Systems
• Biomedical Evidence Generation Engine
• Luandri: a Clean Lua Interface to the Indri Search Engine
• Neural Ranking Models with Multiple Document Fields
• Curriculum Learning Strategies for IR: An Empirical Study on Conversation Response Ranking
• MRNN: A Multi-Resolution Neural Network with Duplex Attention for Document Retrieval in the Context of Question Answering
• Separate and Attend in Personal Email Search
• Impact of Training Dataset Size on Neural Answer Selection Models
• Patient Cohort Retrieval using Transformer Language Models
• Optimize What You Evaluate With: A Simple Yet Effective Framework For Direct Optimization Of IR Metrics
• Fine-tune BERT for E-commerce Non-Default Search Ranking
• DeText: A Deep Text Ranking Framework with BERT
• Learning Fast Matching Models from Weak Annotations
• AutoSUM: Automating Feature Extraction and Multi-user Preference Simulation for Entity Summarization
• MIRA: Leveraging Multi-Intention Co-click Information in Web-scale Document Retrieval using Deep Neural Networks
• PT-Ranking: A Benchmarking Platform for Neural Learning-to-Rank
• Gender Stereotype Reinforcement: Measuring the Gender Bias Conveyed by Ranking Algorithms
• Cross-language Citation Recommendation via Hierarchical Representation Learning on Heterogeneous Graph
• Practical User Feedback-driven Internal Search Using Online Learning to Rank
• Place Deduplication with Embeddings
• Cross-Modality Relevance for Reasoning on Language and Vision