Integrating and Evaluating Neural Word Embeddings in Information Retrieval

By Guido Zuccon, Bevan Koopman, Peter D. Bruza, Leif Azzopardi. 2015

137 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems, Information Retrieval & Search, Natural Language Processing

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 Natural Language Processing

Citations in the corpus

End-to-End Neural Ad-hoc Ranking with Kernel Pooling (2017, background): “Compared to word pair similarities which are hard to learn, word embeddings provide a smooth low-level approximation of word similarities that may improve translation models [8, 24].”
Query Expansion Using Word Embeddings (2016, methodology): “We focused on query expansion and showed that our meth-ods outperform an embedding-based translation model [21].”
Semantic Matching by Non-Linear Word Transportation for Information Retrieval (2016, methodology): “A similar idea was proposed in [33] where word embeddings were explored in a translation language model framework.”
Neural information retrieval: at the end of the early years (2017, methodology): “note that no significant effect of this choice is observed for query-reweighting (Zheng and Callan 2015) or in a translation language model for computing term similarities (Zuccon et al. 2015).”
Word Embedding Causes Topic Shifting; Exploit Global Context! (2017, methodology): “Zuccon et al. [18] integrate word embedding with the translation language modeling by using the set of extended terms from word embedding: Rekabsaz et al. [12] extend the idea into four probabilistic relevance frameworks.”
Embedding-based Query Language Models (2016, methodology): “also similar to [32]), (3) a heuristic-based query expansion method based on word embeddings (VEXP) [2], and (4) a query expansion method based on the similarity of vocabulary term vectors and the average embedding vector of all query terms (AWE).”
An Introduction to Neural Information Retrieval (2018, unknown): “, 1990, 1993]—but other approaches for estimation have also been explored [Zuccon et al., 2015].”
Generalizing Translation Models in the Probabilistic Relevance Framework (2016, methodology): “Our own experiments (not reported here) as well as those reported by Zuccon et al. [41], indicate these parameters as reasonable as a general baseline.”
Estimating Embedding Vectors for Queries (2016, background): “[40] proposed to employ word embeddings within the well-known translation model for IR.”
Analysis of the Paragraph Vector Model for Information Retrieval (2016, methodology): “[27] applied word embeddings in the translation language model framework.”
Easy over hard: a case study on deep learning (2017, background): “[80] found that embedding dimensionality and context window size have no consistent impact on retrieval model performance.”