Clickthrough-based translation models for web search: from word models to phrase models

By Jianfeng Gao, Xiaodong He, Jian-Yun Nie. 2010

103 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems, Information Retrieval & Search, Machine Translation

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems

In Information Retrieval & Search

In Machine Translation

Citations in the corpus

Representation Learning Using Multi-Task Deep Neural Networks for Semantic Classification and Information Retrieval (2015, neutral): “…Allocation (Topic=100) (Blei et al., 2003) 0.308 0.339 0.403 Latent Dirichlet Allocation (Topic=500) (Blei et al., 2003) 0.310 0.339 0.405 Bilingual Topic Model (Gao et al., 2011) 0.316 0.344 0.410 Word based Machine Translation model (Gao et al., 2010) 0.315 0.342 0.411 DSSM, J=50 (Figure 2, .”
Deep Learning: Methods and Applications (2014, methodology): “In the second line of research, click-through data, which consists of a list of queries and the corresponding clicked documents, is exploited for semantic modeling so as to bridge the language discrepancy between search queries and Web documents in recent studies [120, 124].”
Learning Concept Embeddings for Query Expansion by Quantum Entropy Minimization (2014, methodology): “Recently, Gao et al. (Gao and Nie 2012; Gao, He, and Nie 2010) successfully performed QE by training a statistical translation model on clickthrough data and showed that it performed better than a standard correlation model (Cui et al. 2002).”
Deep stacking networks for information retrieval (2013, methodology): “The second type of click features used in our experiments is a set of translation probabilities between query and ad based on the translation models learned on the query-ad pairs extracted from clickthrough logs [6].”
Clickthrough-based latent semantic models for web search (2011, methodology): “The first is a set of clickthrough-based translation models for Web search presented and evaluated in [14], which is a significant extension of the original approach [2], motivated by the increasingly large amount of clickthrough data.”
Neural information retrieval: at the end of the early years (2017, methodology): “Learn to match Gao et al. (2014) propose using DSSM for both automatic highlighting of relevant keywords in documents and recommendation of alternative relevant documents based upon these keywords.”
A Latent Semantic Model with Convolutional-Pooling Structure for Information Retrieval (2014, methodology): “PTM (Row 11) is the phrase-based translation model proposed in [12].”
Identifying Web Search Query Reformulation using Concept based Matching (2013, methodology): “It has been also used in different IR applications to estimate the probability of translating from one sequence of words to another sequence in the same language (e.g. (Gao et al., 2012), (Gao et al., 2010) and (White et al., 2013)).”
Learning semantic representations using convolutional neural networks for web search (2014, methodology): “Following [5], we only used the title field of a Web document for ranking.”
Learning deep structured semantic models for web search using clickthrough data (2013, methodology): “First, clickthrough data, which consists of a list of queries and their clicked documents, is exploited for semantic modeling so as to bridge the language discrepancy between search q ueries and Web documents [9][10].”