Learning to Reweight Terms with Distributed Representations

By Guoqing Zheng, Jamie Callan. 2015

133 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Retrieval & Search

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 Retrieval & Search

Citations in the corpus

A Deep Relevance Matching Model for Ad-hoc Retrieval (2016, methodology): “Term Vector (TV): Inspired by the work [32] where term embeddings can be leveraged to learn the term weights in queries, we use query term vectors as the input of the”
Relevance-based Word Embedding (2017, neutral): “n retrieval in the context of community question answering. Vuli´c and Moens [37] proposed a model to learn bilingual word embedding vectors from document-aligned comparable corpora. Zheng and Callan [46] presented a supervised embedding-based technique to re-weight terms in the existing IR models, ”
Context-Aware Sentence/Passage Term Importance Estimation For First Stage Retrieval (2019, methodology): “InspiredbyZheng and Callan [36], DeepCT-Query uses term recall [35]: D q is the set of documents that are relevant to the query.”
Learning to Match using Local and Distributed Representations of Text for Web Search (2016, background): “In IR, a significant number of these works have focused on word embeddings [6, 8, 10, 11, 27, 28, 34, 41] and modelling short-text similarities [15, 16, 29, 35–37].”
Neural Ranking Models with Weak Supervision (2017, methodology): “Word embedding vectors have been applied to term re-weighting in IR models [32, 47], query expansion [10, 33, 43], query classification [25, 44], etc.”
Generalizing Translation Models in the Probabilistic Relevance Framework (2016, background): “For instance, Zheng and Callan [40] address query term weighting by exploiting word embedding as a feature vector to train a model for the optimal term weights.”
Embedding-based Query Language Models (2016, methodology): “[30] G. Zheng and J. Callan.”
Convolutional Neural Networks for Soft-Matching N-Grams in Ad-hoc Search (2018, unknown): “ere is also much work about how to beer weight n-grams in SDM, for example, by emphasizing frequent and meaningful concepts [3, 32].”
Neural information retrieval: at the end of the early years (2017, methodology): “For ad-hoc retrieval, embeddings learned from Wikipedia (general purpose embeddings) and embeddings learned from the retrieval corpus itself (corpus-specific word embeddings) are compared in Zheng and Callan (2015), Zuccon et al. (2015).”
Estimating Embedding Vectors for Queries (2016, methodology): “While query embedding vectors play a key role in a number of the aforementioned methods, such as [35, 39], they only considered the average or sum of word embedding vectors of all query terms as the query vector.”
An Introduction to Neural Information Retrieval (2018, unknown): “Term embeddings have also been explored for re-weighting query terms [Zheng and Callan, 2015] and finding relevant query re-writes [Grbovic et al.”
Query Expansion Using Word Embeddings (2016, methodology): “Word embeddings were used to re-weight the query terms [20] and to compare a query directly with a document [16, 12].”
A Modern Perspective on Query Likelihood with Deep Generative Retrieval Models (2021, unknown): “This is done for instance by generalizing term salience with translation models [38, 40], and re-weighting terms [57], or through adapting word embeddings for document retrieval by post-filtering [39], retrofitting [16], or re-training on local documents [9].”
A Dual Embedding Space Model for Document Ranking (2016, background): “embeddings have also been studied in other IR contexts such as term reweighting [50], cross-lingual retrieval [14, 46, 52] and shorttext similarity [20].”
Learning Semantic Similarity for Very Short Texts (2015, background): “Also recently, Zheng and Callan created a simple algorithm based on linear regression to find relevant terms in a query [15].”
Topic Modeling for Short Texts with Auxiliary Word Embeddings (2016, unknown): “Effective learning of general word semantic relatedness is now feasible and practical with the recent development in neural network techniques, which have contributed improvements in many tasks in Information Retrieval (IR) and Natural Language Processing (NLP) [9,10,16,17, 43].”
To Clean or Not to Clean (2018, methodology): “The filtered version was created by eliminating all documents with a spam score of less than 70% (as suggested in https://plg.uwaterloo.ca/ ∼ gvcormac/clueweb09spam/ and used in References [28, 54, 71, 78]).”