Abstract
Shared Task 1 at SemEval-2017 deals with assessing the semantic similarity between sentences, either in the same or in different languages. In our system submission, we employ multilingual word representations, in which similar words in different languages are close to one another. Using such representations is advantageous, since the increasing amount of available parallel data allows for the application of such methods to many of the languages in the world. Hence, semantic similarity can be inferred even for languages for which no annotated data exists. Our system is trained and evaluated on all language pairs included in the shared task (English, Spanish, Arabic, and Turkish). Although development results are promising, our system does not yield high performance on the shared task test sets.- Anthology ID:
- S17-2021
- 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:
- 154–158
- Language:
- URL:
- https://aclanthology.org/S17-2021
- DOI:
- 10.18653/v1/S17-2021
- Cite (ACL):
- Johannes Bjerva and Robert Östling. 2017. ResSim at SemEval-2017 Task 1: Multilingual Word Representations for Semantic Textual Similarity. In Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017), pages 154–158, Vancouver, Canada. Association for Computational Linguistics.
- Cite (Informal):
- ResSim at SemEval-2017 Task 1: Multilingual Word Representations for Semantic Textual Similarity (Bjerva & Östling, SemEval 2017)
- PDF:
- https://preview.aclanthology.org/emnlp-22-attachments/S17-2021.pdf