Abstract
In this talk I present Generationary, an approach that goes beyond the mainstream assumption that word senses can be represented as discrete items of a predefined inventory, and put forward a unified model which produces contextualized definitions for arbitrary lexical items, from words to phrases and even sentences. Generationary employs a novel span-based encoding scheme to fine-tune an English pre-trained Encoder-Decoder system and generate new definitions. Our model outperforms previous approaches in the generative task of Definition Modeling in many settings, but it also matches or surpasses the state of the art in discriminative tasks such as Word Sense Disambiguation and Word-in-Context. I also show that Generationary benefits from training on definitions from multiple inventories, with strong gains across benchmarks, including a novel dataset of definitions for free adjective-noun phrases, and discuss interesting examples of generated definitions. Joint work with Michele Bevilacqua and Marco Maru.- Anthology ID:
- 2020.mwe-1.9
- Volume:
- Proceedings of the Joint Workshop on Multiword Expressions and Electronic Lexicons
- Month:
- December
- Year:
- 2020
- Address:
- online
- Editors:
- Stella Markantonatou, John McCrae, Jelena Mitrović, Carole Tiberius, Carlos Ramisch, Ashwini Vaidya, Petya Osenova, Agata Savary
- Venue:
- MWE
- SIG:
- SIGLEX
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 73
- Language:
- URL:
- https://aclanthology.org/2020.mwe-1.9
- DOI:
- Cite (ACL):
- Roberto Navigli. 2020. Invited Talk: Generationary or: “How We Went beyond Sense Inventories and Learned to Gloss”. In Proceedings of the Joint Workshop on Multiword Expressions and Electronic Lexicons, page 73, online. Association for Computational Linguistics.
- Cite (Informal):
- Invited Talk: Generationary or: “How We Went beyond Sense Inventories and Learned to Gloss” (Navigli, MWE 2020)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2020.mwe-1.9.pdf