![]() ![]() Anthology ID: ling-1.238 Volume: Proceedings of the 29th International Conference on Computational Linguistics Month: October Year: 2022 Address: Gyeongju, Republic of Korea Venue: COLING SIG: Publisher: International Committee on Computational Linguistics Note: Pages: 2692–2710 Language: URL: DOI: Bibkey: frisoni-etal-2022-text Cite (ACL): Giacomo Frisoni, Gianluca Moro, and Lorenzo Balzani. Our extractive models achieve greater state-of-the-art performance than single-task competitors and show promising capabilities for the controlled generation of coherent natural language utterances from structured data. By streamlining parsing and generation to translations, we propose baseline transformer model results according to multiple biomedical text mining benchmarks and NLG metrics. To this end, we present a new event graph linearization technique and release highly comprehensive event-text paired datasets, covering more than 150 event types from multiple biology subareas (English language). ![]() We present the first lightweight framework to solve both event extraction and event verbalization with a unified text-to-text approach, allowing us to fuse all the resources so far designed for different tasks. Almost all contributions in the event realm orbit around semantic parsing, usually employing discriminative architectures and cumbersome multi-step pipelines limited to a small number of target interaction types. Abstract Biomedical events represent complex, graphical, and semantically rich interactions expressed in the scientific literature. ![]()
0 Comments
Leave a Reply. |