User Tools

Site Tools


nlp:information_retrieval

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
Next revision
Previous revision
nlp:information_retrieval [2022/10/11 21:22] – [Retrieval Methods used in NLP] jmflanignlp:information_retrieval [2025/07/07 06:00] (current) jmflanig
Line 9: Line 9:
   * [[https://arxiv.org/pdf/2103.05256.pdf|Naseri et al 2021 - CEQE: Contextualized Embeddings for Query Expansion]]   * [[https://arxiv.org/pdf/2103.05256.pdf|Naseri et al 2021 - CEQE: Contextualized Embeddings for Query Expansion]]
   * [[https://arxiv.org/pdf/2104.07186.pdf|Gao et al 2021 - COIL: Revisit Exact Lexical Match in Information Retrieval with Contextualized Inverted List]] There is really a lot that can be done in this area.  This is just the beginning   * [[https://arxiv.org/pdf/2104.07186.pdf|Gao et al 2021 - COIL: Revisit Exact Lexical Match in Information Retrieval with Contextualized Inverted List]] There is really a lot that can be done in this area.  This is just the beginning
 +
 +===== Conversational Search =====
 +See [[nlp:Dialog#Conversational Search]].
  
 ===== Retrieval Methods used in NLP ===== ===== Retrieval Methods used in NLP =====
Line 14: Line 17:
  
   * BM25   * BM25
-    * [[https://dl.acm.org/doi/pdf/10.1145/2682862.2682863|Trotman et al 2014 - Improvements to BM25 and Language Models Examined]] [[https://github.com/dorianbrown/rank_bm25|Github implementation of various variations]]+    * [[https://dl.acm.org/doi/pdf/10.1145/2682862.2682863|Trotman et al 2014 - Improvements to BM25 and Language Models Examined]] [[https://github.com/dorianbrown/rank_bm25|Github implementation]] of various variations 
 +  * Generating Titles 
 +    * [[https://arxiv.org/pdf/2204.05511.pdf|Chen et al 2023 - GERE: Generative Evidence Retrieval for Fact Verification]] 
 + 
 +===== Dense Document Retrieval with LLMs ==== 
 +  * **Overviews** 
 +    * [[https://arxiv.org/pdf/2211.14876.pdf|Zhao et al 2023 - Dense Text Retrieval based on Pretrained 
 +Language Models: A Survey]] 
 +  * [[https://dl.acm.org/doi/pdf/10.1145/3511808.3557527|Ma et al 2023 - A Contrastive Pre-training Approach to Learn Discriminative Autoencoder for Dense Retrieval]] 
 + 
 +===== Generative IR ===== 
 +  * **Overviews** 
 +    * [[https://arxiv.org/pdf/2404.14851|Li et al 2024 - From Matching to Generation: A Survey on Generative Information Retrieval]]
  
 ===== Datasets ===== ===== Datasets =====
Line 25: Line 40:
   * [[https://www.lemurproject.org/|Lemur]] Open-source research search engine   * [[https://www.lemurproject.org/|Lemur]] Open-source research search engine
   * [[https://aurelieherbelot.net/pears/|PeARS]] Local browser-based search engine (seems to be a research system)   * [[https://aurelieherbelot.net/pears/|PeARS]] Local browser-based search engine (seems to be a research system)
 +  * [[https://github.com/dorianbrown/rank_bm25|Rank-BM25]] A two line search engine
  
 ===== Conferences ===== ===== Conferences =====
Line 34: Line 50:
   * [[https://scholar.google.com/citations?user=ArV74ZMAAAAJ&hl=en|Bruce Croft]]   * [[https://scholar.google.com/citations?user=ArV74ZMAAAAJ&hl=en|Bruce Croft]]
   * [[https://scholar.google.com/citations?user=IIXpJ8oAAAAJ&hl=en&oi=ao|Laura Dietz]]   * [[https://scholar.google.com/citations?user=IIXpJ8oAAAAJ&hl=en&oi=ao|Laura Dietz]]
 +  * [[https://scholar.google.com/citations?user=tbxCHJgAAAAJ&hl=en|Ji-Rong Wen]]
  
 ===== Related Pages ===== ===== Related Pages =====
 +  * [[nlp:Dialog#Conversational Search]]
   * [[ml:Learning to Rank]]   * [[ml:Learning to Rank]]
 +
  
nlp/information_retrieval.1665523341.txt.gz · Last modified: 2023/06/15 07:36 (external edit)

Donate Powered by PHP Valid HTML5 Valid CSS Driven by DokuWiki