Monolingual and Cross-Lingual Information Retrieval Models Based on (Bilingual) Word Embeddings

By Ivan Vulic, Marie-Francine Moens. 2015

300 citations recorded by the source corpus.

Subfields: Artificial Intelligence, 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 Retrieval & Search

In Natural Language Processing

Citations in the corpus

Pretrained Transformers for Text Ranking: BERT and Beyond (2020, background): “Although some of the early neural ranking approaches did explore cross-lingual retrieval [Vulić and Moens, 2015] and new research on this topic continues to emerge in the neural context [Yu and Allan, 2020], we have not found enough references in the context of transformers to provide a detailed tre”
Relevance-based Word Embedding (2017, methodology): “tors of individual words in one document to the other one. Zhou et al. [47] introduced an embeddingbased method for question 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 cor”
A Survey of Cross-lingual Word Embedding Models (2017, methodology): “A shared cross-lingual embedding space provides means to more general cross-lingual and multilingual IR models without any substantial change in the algorithmic design of the retrieval process (Vulić & Moens, 2015).”
An Introduction to Neural Information Retrieval (2018, unknown): “, 2015b], as well as in the context of other IR tasks such as cross-lingual retrieval [Vulić and Moens, 2015] and entity retrieval [Van Gysel et al.”
Explicit Semantic Ranking for Academic Search via Knowledge Graph Embedding (2017, background): “This research was supported by National Science Foundation (NSF) grant IIS-1422676 and a gift from the Allen Institute for Artificial Intelligence.”
Generalizing Translation Models in the Probabilistic Relevance Framework (2016, background): “…[2] also allows a relatively straight-forward inclusion of feedback information: Amati et al. [1] study the robustness of QE by two factors: divergence of the distribution of the query term in the retrieved documents from a random distribution and the frequency of the term in the whole document.”
Semantic Specialisation of Distributional Word Vector Spaces using Monolingual and Cross-Lingual Constraints (2017, background): “, 2016), cross-lingual information retrieval (Vulić and Moens, 2015; Mitra et al., 2016), and transfer learning for resource-lean languages (Søgaard et al.”
Explainable Product Search with a Dynamic Relation Embedding Model (2019, methodology): “ of w q, andW ∈R α×, b ∈Rα are parameters to be learned in the training process. In this work, we employ this non-linear projection function to compute f (q). We tried other query embedding functions [45, 59] as well, but observed no significant performance improvement in our retrieval experiments. ”
Retrieving Textual Evidence for Knowledge Graph Facts (2019, methodology): “A basic method to build document vectors from word embeddings is to aggregate the word vectors by summation or averaging [24].”
Semantic Matching by Non-Linear Word Transportation for Information Retrieval (2016, methodology): “We note that the improvements of RM3 and NWT over simple exact matching based models are much more significant on the Robust04 collection than the other two collections.”
Neural information retrieval: at the end of the early years (2017, methodology): “Ad-Hoc retrieval: Ad-hoc retrieval refers to a single search performed by a user: a single query, with no further interaction or feedback, on the basis of which an IR system strives to return an accurate document ranking.”
Seeping Semantics: Linking Datasets Using Word Embeddings for Data Discovery (2018, background): “Of those, averaging word embeddings (AWE) is quite popular [13], [14], [15].”
Unsupervised Cross-Lingual Representation Learning (2019, background): “…us to reason about word meaning in multilingual contexts and serve as an integral source of knowledge for multilingual applications such as machine translation (Artetxe et al., 2018d; Qi et al., 2018; Lample et al., 2018b) or multilingual search and question answering (Vulić and Moens, 2015).”
Teaching a New Dog Old Tricks: Resurrecting Multilingual Retrieval Using Zero-Shot Learning (2019, background): “For example, Vulic and Moens [34] proposed BWESG, an algorithm to learn word embeddings on aligned documents that can be used to calculate document-query similarity.”
Estimating Embedding Vectors for Queries (2016, methodology): “Following the impressive results achieved by word embedding techniques in NLP tasks, these techniques have begun to be studied in IR tasks [28, 35, 39, 40].”
Embedding-based Query Language Models (2016, methodology): “BWESG [27], a bilingual word embedding method, has recently been developed and applied to information retrieval.”
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].”