QLUT at SemEval-2017 Task 1: Semantic Textual Similarity Based on Word Embeddings
Fanqing Meng, Wenpeng Lu, Yuteng Zhang, Jinyong Cheng, Yuehan Du, Shuwang Han
Abstract
This paper reports the details of our submissions in the task 1 of SemEval 2017. This task aims at assessing the semantic textual similarity of two sentences or texts. We submit three unsupervised systems based on word embeddings. The differences between these runs are the various preprocessing on evaluation data. The best performance of these systems on the evaluation of Pearson correlation is 0.6887. Unsurprisingly, results of our runs demonstrate that data preprocessing, such as tokenization, lemmatization, extraction of content words and removing stop words, is helpful and plays a significant role in improving the performance of models.- Anthology ID:
- S17-2020
- Volume:
- Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017)
- Month:
- August
- Year:
- 2017
- Address:
- Vancouver, Canada
- Editors:
- Steven Bethard, Marine Carpuat, Marianna Apidianaki, Saif M. Mohammad, Daniel Cer, David Jurgens
- Venue:
- SemEval
- SIG:
- SIGLEX
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 150–153
- Language:
- URL:
- https://preview.aclanthology.org/add_missing_videos/S17-2020/
- DOI:
- 10.18653/v1/S17-2020
- Cite (ACL):
- Fanqing Meng, Wenpeng Lu, Yuteng Zhang, Jinyong Cheng, Yuehan Du, and Shuwang Han. 2017. QLUT at SemEval-2017 Task 1: Semantic Textual Similarity Based on Word Embeddings. In Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017), pages 150–153, Vancouver, Canada. Association for Computational Linguistics.
- Cite (Informal):
- QLUT at SemEval-2017 Task 1: Semantic Textual Similarity Based on Word Embeddings (Meng et al., SemEval 2017)
- PDF:
- https://preview.aclanthology.org/add_missing_videos/S17-2020.pdf