Word Embedding Causes Topic Shifting; Exploit Global Context!

By Navid Rekabsaz, Mihai Lupu, Allan Hanbury, Hamed Zamani. 2017

24 citations recorded by the source corpus.

How researchers see this paper

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

1. Hamed Zamani
2. Sebastian Hofstätter
3. Mostafa Dehghani
4. Allan Hanbury
5. Navid Rekabsaz
6. Jimmy J. Lin
7. W. Bruce Croft
8. Zhuyun Dai

Citations in the corpus

• Relevance-based Word Embedding (2017, background): “[30] proposed to exploit global context in word embeddings”
• 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 classi€cation [25, 44], etc.”
• 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].”
• On the Effect of Low-Frequency Terms on Neural-IR Models (2019, methodology): “Various studies apply neural methods by introducing pre-trained word embeddings into classical IR models [13, 14],”
• Convolutional Neural Networks for Soft-Matching N-Grams in Ad-hoc Search (2018, unknown): “word2vec [20] and GloVe [24], have been questioned about their suitability for ad hoc search [1, 25].”