Abstract
This paper describes our submission to SemEval-2022 Multilingual News Article Similarity task. We experiment with different approaches that utilize a pre-trained language model fitted with a regression head to predict similarity scores for a given pair of news articles. Our best performing systems include 2 key steps: 1) pre-training with in-domain data 2) training data enrichment through machine translation. Our final submission is an ensemble of predictions from our top systems. While we show the significance of pre-training and augmentation, we believe the issue of language coverage calls for more attention.- Anthology ID:
- 2022.semeval-1.162
- Volume:
- Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)
- Month:
- July
- Year:
- 2022
- Address:
- Seattle, United States
- Editors:
- Guy Emerson, Natalie Schluter, Gabriel Stanovsky, Ritesh Kumar, Alexis Palmer, Nathan Schneider, Siddharth Singh, Shyam Ratan
- Venue:
- SemEval
- SIG:
- SIGLEX
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1151–1156
- Language:
- URL:
- https://aclanthology.org/2022.semeval-1.162
- DOI:
- 10.18653/v1/2022.semeval-1.162
- Cite (ACL):
- Sai Sandeep Sharma Chittilla and Talaat Khalil. 2022. HuaAMS at SemEval-2022 Task 8: Combining Translation and Domain Pre-training for Cross-lingual News Article Similarity. In Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022), pages 1151–1156, Seattle, United States. Association for Computational Linguistics.
- Cite (Informal):
- HuaAMS at SemEval-2022 Task 8: Combining Translation and Domain Pre-training for Cross-lingual News Article Similarity (Chittilla & Khalil, SemEval 2022)
- PDF:
- https://preview.aclanthology.org/naacl24-info/2022.semeval-1.162.pdf