DartmouthCS at SemEval-2022 Task 8: Predicting Multilingual News Article Similarity with Meta-Information and Translation
25020Authors
nan
Abstract
AbstractThis paper presents our approach for tackling SemEval-2022 Task 8: Multilingual News Article Similarity. Our experiments show that even by using multi-lingual pre-trained language models (LMs), translating the text into the same language yields the best evaluation performance. We also find that stylometric features of the text and meta-information of the news articles can be predicted based on the text with low error rates, and these predictions could be used to improve the predictions of the overall similarity scores. These findings suggest substantial correlations between authorship information and topical similarity estimation, which sheds light on future stylometric and topic modeling research.
Keywords
Full Content
Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022), pages 1157 - 1162 July 14-15, 2022 ©2022 Association for Computational Linguistics 1157 1158 1159 1160 1161 1162
Labeled Text
AbstractThis paper presents our approach for tackling SemEval-2022 Task 8: Multilingual News Article Similarity. Our experiments show that even by using multi-lingual pre-trained language models (LMs), translating the text into the same language yields the best evaluation performance. We also find that stylometric features of the text and meta-information of the news articles can be predicted based on the text with low error rates, and these predictions could be used to improve the predictions of the overall similarity scores. These findings suggest substantial correlations between authorship information and topical similarity estimation, which sheds light on future stylometric and topic modeling research.
Publication Details
- Paper ID:
- 25020
- Year:
- 2022
- Publication:
- TIPSTER
- Publication Type:
- conf
- DOI:
- nan