Back to the Future: Sequential Alignment of Text Representations

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Documents

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.
Original languageEnglish
Title of host publicationProceedings of the 34th AAAI Conference on Artificial Intelligence
Number of pages8
PublisherAAAI Press
Publication date2020
Publication statusPublished - 2020
Event34th AAAI Conference on Artificial Intelligence - New York, United States
Duration: 7 Feb 202012 Jan 2021

Conference

Conference34th AAAI Conference on Artificial Intelligence
LandUnited States
ByNew York
Periode07/02/202012/01/2021

ID: 255053434