Getting Started with Neural Models for Semantic Matching in Web Search
arXiv:1611.03305
Abstract
The vocabulary mismatch problem is a long-standing problem in information retrieval. Semantic matching holds the promise of solving the problem. Recent advances in language technology have given rise to unsupervised neural models for learning representations of words as well as bigger textual units. Such representations enable powerful semantic matching methods. This survey is meant as an introduction to the use of neural models for semantic matching. To remain focused we limit ourselves to web search. We detail the required background and terminology, a taxonomy grouping the rapidly growing body of work in the area, and then survey work on neural models for semantic matching in the context of three tasks: query suggestion, ad retrieval, and document retrieval. We include a section on resources and best practices that we believe will help readers who are new to the area. We conclude with an assessment of the state-of-the-art and suggestions for future work.
under review for the Information Retrieval Journal
References in corpus (9)
- Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
- From Frequency to Meaning: Vector Space Models of Semantics
- A Deep Relevance Matching Model for Ad-hoc Retrieval
- Hierarchical Neural Language Models for Joint Representation of Streaming Documents and their Content
- Semantic Modelling with Long-Short-Term Memory for Information Retrieval
- Query Expansion with Locally-Trained Word Embeddings
- Deep Learning Relevance: Creating Relevant Information (as Opposed to Retrieving it)
- Learning Dynamic Classes of Events using Stacked Multilayer Perceptron Networks
- Selective Term Proximity Scoring Via BP-ANN