Word Embedding based Generalized Language Model for Information Retrieval

By Debasis Ganguly, Dwaipayan Roy, Mandar Mitra, Gareth J.F. Jones. 2015

268 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems, 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 Systems

In Information Retrieval & Search

Citations in the corpus

Pretrained Transformers for Text Ranking: BERT and Beyond (2020, methodology): “pre-trained word2vec embeddings [Le and Mikolov, 2014] and computes relevance scores by aggregating cosine similarities across all query–document term pairs. Language models based on word embeddings [Ganguly et al., 2015] can be thought of as conceptually belonging to the class of representation-bas”
Learning to Match using Local and Distributed Representations of Text for Web Search (2016, methodology): “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].”
Query Expansion with Locally-Trained Word Embeddings (2016, methodology): “(Ganguly et al., 2015) used the word similarity in the word2vec embedding space as a way to estimate term transformation probabilities in a language modelling setting for retrieval.”
COIL: Revisit Exact Lexical Match in Information Retrieval with Contextualized Inverted List (2021, methodology): “Early attempts compute similarity between pre-trained word embedding such as word2vec (Mikolov et al., 2013) and GLoVe (Pennington et al., 2014) to produce matching score (Ganguly et al., 2015; Diaz et al., 2016).”
Cross-Domain Sentence Modeling for Relevance Transfer with BERT (2019, background): “There has also been some effort in learning word embeddings to directly capture relevance matching [74, 21] rather than linguistic features as in word2vec [43] or GloVe [49].”
Estimating Embedding Vectors for Queries (2016, background): “Ganguly et al. [15] considered the semantic similarities between vocabulary terms to smooth document language models.”
A Dual Embedding Space Model for Document Ranking (2016, background): “[9] recently proposed a generalized language model for IR that incorporates IN-IN similarities.”
Neural information retrieval: at the end of the early years (2017, methodology): “…et al. 2015; Grbovic et al. 2015b; Mitra 2015; Severyn and Moschitti 2015; Vulic and Moens 2015; Zheng and Callan 2015), spanning ad-hoc search (Ganguly et al. 2015; Vulic and Moens 2015; Zheng and Callan 2015; Zuccon et al. 2015), QA sentence selection and Twitter reranking (Kenter and de…”
Query Expansion Using Word Embeddings (2016, methodology): “Document embeddings [5, 2] and word-embeddings-based translation models [8, 21] were also used for retrieval.”
A Comparison of Word Embeddings for the Biomedical Natural Language Processing (2018, background): “There has been an increasing number of studies applying word embeddings in common NLP tasks, such as information extraction (IE) [4], [5], [6], information retrieval (IR) [7], sentiment analysis [8], [9], question answering [10], [11], and text summarization [12], [13].”
Embedding-based Query Language Models (2016, methodology): “The main difference between this paper and the existing work is that we focus on estimating accurate query language models which efficiently outperforms the embedding-based document language models [10].”
Generalizing Translation Models in the Probabilistic Relevance Framework (2016, methodology): “Other recent studies have combined language modelling and distributional semantics: Ganguly et al. [8] expand the classic language models through word embedding-based noisy channels which aim to discover the hidden dependencies between terms.”
Critically Examining the "Neural Hype": Weak Baselines and the Additivity of Effectiveness Gains from Neural Ranking Models (2019, background): “While there are much more sophisticated approaches to integrating multiple relevance signals, this approach is commonly used [6, 16, 19, 24, 26].”
BioWordVec, improving biomedical word embeddings with subword information and MeSH (2019, methodology): “Based on word embeddings, the recent deep learning methods have been successfully applied to various natural language processing (NLP) tasks 4–6 .”
Analysis of the Paragraph Vector Model for Information Retrieval (2016, background): “Ganguly et al. [7] and Zuccon et al. [27] applied word embeddings in the translation language model framework.”
Provably Confidential Language Modelling (2022, background): “Language models (LM) have rich real-world applications in, among others, machine translation (Bahdanau et al., 2015), AI chatbots (Hosseini-Asl et al., 2020), question answering (Kwiatkowski et al., 2019), and information retrieval (Ganguly et al., 2015).”
Incorporating Query Term Independence Assumption for Efficient Retrieval and Ranking using Deep Neural Networks (2019, methodology): “Several neural IR methods—e.g., [Ganguly et al., 2015, Kenter and De Rijke, 2015, Nalisnick et al., 2016, Guo et al., 2016]—already operate under query term independence assumption.”
Semantic Matching by Non-Linear Word Transportation for Information Retrieval (2016, methodology): “for IR was proposed in [12], where query words are assumed to be generated in three ways, i.”