Back to the Future: Sequential Alignment of Text Representations
Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Dokumenter
- Back to the Future
Accepteret manuskript, 682 KB, PDF-dokument
Language evolves over time in many ways relevant to natural language processing tasks. For example, recent occurrences of tokens 'BERT' and 'ELMO' in publications refer to neural network architectures rather than persons. This type of temporal signal is typically overlooked, but is important if one aims to deploy a machine learning model over an extended period of time. In particular, language evolution causes data drift between time-steps in sequential decision-making tasks. Examples of such tasks include prediction of paper acceptance for yearly conferences (regular intervals) or author stance prediction for rumours on Twitter (irregular intervals). Inspired by successes in computer vision, we tackle data drift by sequentially aligning learned representations. We evaluate on three challenging tasks varying in terms of time-scales, linguistic units, and domains. These tasks show our method outperforming several strong baselines, including using all available data. We argue that, due to its low computational expense, sequential alignment is a practical solution to dealing with language evolution.
Originalsprog | Engelsk |
---|---|
Titel | Proceedings of the 34th AAAI Conference on Artificial Intelligence |
Antal sider | 8 |
Forlag | AAAI Press |
Publikationsdato | 2020 |
Status | Udgivet - 2020 |
Begivenhed | 34th AAAI Conference on Artificial Intelligence - New York, USA Varighed: 7 feb. 2020 → 12 jan. 2021 |
Konference
Konference | 34th AAAI Conference on Artificial Intelligence |
---|---|
Land | USA |
By | New York |
Periode | 07/02/2020 → 12/01/2021 |
Antal downloads er baseret på statistik fra Google Scholar og www.ku.dk
Ingen data tilgængelig
ID: 255053434