mlsanityData to 7 Oct 2026

FecTek: Enhancing Term Weight in Lexicon-Based Retrieval with Feature Context and Term-level Knowledge

arXiv 2404.12152 ↗First posted 18 Apr 2024cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Lexicon-based retrieval has gained siginificant popularity in text retrieval due to its efficient and robust performance. To further enhance performance of lexicon-based retrieval, researchers have been diligently incorporating state-of-the-art methodologies like Neural retrieval and text-level contrastive learning approaches. Nonetheless, despite the promising outcomes, current lexicon-based retrieval methods have received limited attention in exploring the potential benefits of feature context representations and term-level knowledge guidance. In this paper, we introduce an innovative method by introducing FEature Context and TErm-level Knowledge modules(FecTek). To effectively enrich the feature context representations of term weight, the Feature Context Module (FCM) is introduced, which leverages the power of BERT's representation to determine dynamic weights for each element in the embedding. Additionally, we develop a term-level knowledge guidance module (TKGM) for effectively utilizing term-level knowledge to intelligently guide the modeling process of term weight. Evaluation of the proposed method on MS Marco benchmark demonstrates its superiority over the previous state-of-the-art approaches.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 26 of its 31 references that are in the map. First posted on arXiv 18 Apr 2024.

Builds on

26 of 31 references.

References · 26

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2017Squeeze-and-Excitation Networkscited by 4,763
  3. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,591
  4. 2020ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTcited by 1,160
  5. 2020Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrievalcited by 846
  6. 2021ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interactioncited by 464
  7. 2020RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answeringcited by 410
  8. 2021Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Samplingcited by 238
  9. 2021Unsupervised Corpus Aware Language Model Pre-training for Dense Passage Retrievalcited by 203
  10. 2021RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-rankingcited by 175
  11. 2021Condenser: a Pre-training Architecture for Dense Retrievalcited by 162
  12. 2021Optimizing Dense Retrieval Model Training with Hard Negativescited by 154
14 more
  1. 2021SPLADE v2: Sparse Lexical and Expansion Model for Information Retrievalcited by 126
  2. 2021COIL: Revisit Exact Lexical Match in Information Retrieval with Contextualized Inverted Listcited by 113
  3. 2022From Distillation to Hard Negative Sampling: Making Sparse Neural IR Models More Effectivecited by 98
  4. 2021Adversarial Retriever-Ranker for dense text retrievalcited by 82
  5. 2021A Few Brief Notes on DeepImpact, COIL, and a Conceptual Framework for Information Retrieval Techniquescited by 69
  6. 2021Learning Passage Impacts for Inverted Indexescited by 68
  7. 2019Context-Aware Sentence/Passage Term Importance Estimation For First Stage Retrievalcited by 65
  8. 2021PAIR: Leveraging Passage-Centric Similarity Relation for Improving Dense Passage Retrievalcited by 50
  9. 2020SparTerm: Learning Term-based Sparse Representation for Fast Text Retrievalcited by 45
  10. 2021Learning Discrete Representations via Constrained Clustering for Effective and Efficient Dense Retrievalcited by 27
  11. 2021Fast Passage Re-ranking with Contextualized Exact Term Matching and Efficient Passage Expansioncited by 20
  12. 2022LED: Lexicon-Enlightened Dense Retriever for Large-Scale Retrievalcited by 15
  13. 2020Biased TextRank: Unsupervised Graph-Based Content Extractioncited by 14
  14. 2022SpaDE: Improving Sparse Representations using a Dual Document Encoder for First-stage Retrievalcited by 6

Built on by

Not cited yet.