Papers with information retrieval models
BERT meets Cranfield: Uncovering the Properties of Full Ranking on Fully Labeled Data (2021.eacl-srw)
Copied to clipboard
| Challenge: | Existing information retrieval models based on pre-trained BERT models have been tested on data collections with partial relevance labels, where a relevant document has not been exposed to the annotators. |
| Approach: | They propose to use BERT-based rankers to evaluate documents with partial relevance labels on a Cranfield collection, which comes with full relevance judgment on all documents in the collection. |
| Outcome: | The proposed model performs better than the initial ranker and re-ranker on the Cranfield dataset. |
NevIR: Negation in Neural Information Retrieval (2024.eacl-long)
Copied to clipboard
| Challenge: | Negation is a common everyday phenomenon and has been a consistent area of weakness for language models. |
| Approach: | They ask IR models to rank two documents that differ only by negation . they find that most current information retrieval models do not consider negation. |
| Outcome: | The proposed benchmarks show that most current models do not consider negation . the results are similar to those found in the literature, but are poorer than random ranking . |
The Million Authors Corpus: A Cross-Lingual and Cross-Domain Wikipedia Dataset for Authorship Verification (2025.findings-acl)
Copied to clipboard
| Challenge: | Authorship verification (AV) is a crucial task for identity verification, accountlinking, historical linguistics, and AI-generated text identification. |
| Approach: | They propose to use Wikipedia's Million Authors Corpus to examine authorship verification models on a broad scale. |
| Outcome: | The proposed dataset includes 60.08M textual chunks, contributed by 1.29M Wikipedia authors. |