Abstract
The Princeton WordNet is a powerful tool for studying language and developing natural language processing algorithms. With significant work developing it further, one line considers its extension through aligning its expert-annotated structure with other lexical resources. In contrast, this work explores a completely data-driven approach to network construction, forming a wordnet using the entirety of the open-source, noisy, user-annotated dictionary, Wiktionary. Comparing baselines to WordNet, we find compelling evidence that our network induction process constructs a network with useful semantic structure. With thousands of semantically-linked examples that demonstrate sense usage from basic lemmas to multiword expressions (MWEs), we believe this work motivates future research.- Anthology ID:
- D19-5523
- Volume:
- Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019)
- Month:
- November
- Year:
- 2019
- Address:
- Hong Kong, China
- Editors:
- Wei Xu, Alan Ritter, Tim Baldwin, Afshin Rahimi
- Venue:
- WNUT
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 170–180
- Language:
- URL:
- https://aclanthology.org/D19-5523
- DOI:
- 10.18653/v1/D19-5523
- Cite (ACL):
- Hunter Heidenreich and Jake Williams. 2019. Latent semantic network induction in the context of linked example senses. In Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019), pages 170–180, Hong Kong, China. Association for Computational Linguistics.
- Cite (Informal):
- Latent semantic network induction in the context of linked example senses (Heidenreich & Williams, WNUT 2019)
- PDF:
- https://preview.aclanthology.org/naacl24-info/D19-5523.pdf