Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2305.16128 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929225661939712 |
|---|---|
| author | Hu, Xuming Chen, Junzhe Guo, Zhijiang Yu, Philip S. |
| author_facet | Hu, Xuming Chen, Junzhe Guo, Zhijiang Yu, Philip S. |
| contents | Evidence plays a crucial role in automated fact-checking. When verifying real-world claims, existing fact-checking systems either assume the evidence sentences are given or use the search snippets returned by the search engine. Such methods ignore the challenges of collecting evidence and may not provide sufficient information to verify real-world claims. Aiming at building a better fact-checking system, we propose to incorporate full text from source documents as evidence and introduce two enriched datasets. The first one is a multilingual dataset, while the second one is monolingual (English). We further develop a latent variable model to jointly extract evidence sentences from documents and perform claim verification. Experiments indicate that including source documents can provide sufficient contextual clues even when gold evidence sentences are not annotated. The proposed system is able to achieve significant improvements upon best-reported models under different settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2305_16128 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Give Me More Details: Improving Fact-Checking with Latent Retrieval Hu, Xuming Chen, Junzhe Guo, Zhijiang Yu, Philip S. Computation and Language Evidence plays a crucial role in automated fact-checking. When verifying real-world claims, existing fact-checking systems either assume the evidence sentences are given or use the search snippets returned by the search engine. Such methods ignore the challenges of collecting evidence and may not provide sufficient information to verify real-world claims. Aiming at building a better fact-checking system, we propose to incorporate full text from source documents as evidence and introduce two enriched datasets. The first one is a multilingual dataset, while the second one is monolingual (English). We further develop a latent variable model to jointly extract evidence sentences from documents and perform claim verification. Experiments indicate that including source documents can provide sufficient contextual clues even when gold evidence sentences are not annotated. The proposed system is able to achieve significant improvements upon best-reported models under different settings. |
| title | Give Me More Details: Improving Fact-Checking with Latent Retrieval |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2305.16128 |