Papers with neural ranker
Improving Large-Scale Fact-Checking using Decomposable Attention Models and Lexical Tagging (D18-1)
Copied to clipboard
| Challenge: | Existing pipelines for fact-checking of textual sources are limited . fact- checking of text sources requires a large knowledge base to extract relevant information . |
| Approach: | They propose a neural ranker that dynamically selects sentences to improve evidence retrieval . they incorporate lexical tagging methods into the pipeline framework to simplify the tasks . |
| Outcome: | The proposed model outperforms the existing TF-IDF method on a large-scale fact extraction and verification dataset with speedup. |
Towards Robust Ranker for Text Retrieval (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for text retrieval are based on a 'retrieval & rerank' pipeline, which uses a fast retriever to fetch a set of top document candidates, while a robust ranker is based upon a weak negative mining during contrastive learning. |
| Approach: | They propose a multi-adversarial training strategy that leverages multiple retrievers as generators to challenge a ranker. |
| Outcome: | The proposed model outperforms the existing de facto ranker training paradigms on the passage retrieval benchmarks using BM25-reranking, full-ranking and retriever distillation. |
DUQGen: Effective Unsupervised Domain Adaptation of Neural Rankers by Diversifying Synthetic Query Generation (2024.naacl-long)
Copied to clipboard
| Challenge: | State-of-the-art rankers pre-trained on large task-specific training data such as MS-MARCO exhibit strong performance on various ranking tasks without domain adaptation, also called zero-shot. |
| Approach: | They propose a method to generate unsupervised domain adaptation for ranking using large-scale task-specific training data such as MS-MARCO and Wikipedia retrieval. |
| Outcome: | The proposed method outperforms all zero-shot baselines and significantly outperfies the SOTA baselines on 16 out of 18 datasets, for an average of 4% relative improvement across all datasets. |