no code implementations • NAACL (ACL) 2022 • Tatsuya Aoyama, Nathan Schneider
The current study quantitatively (and qualitatively for an illustrative purpose) analyzes BERT’s layer-wise masked word prediction on an English corpus, and finds that (1) the layerwise localization of linguistic knowledge primarily shown in probing studies is replicated in a behavior-based design and (2) that syntactic and semantic information is encoded at different layers for words of different syntactic categories.
no code implementations • 25 Apr 2024 • Hiroyuki Hanada, Satoshi Akahane, Tatsuya Aoyama, Tomonari Tanaka, Yoshito Okura, Yu Inatsu, Noriaki Hashimoto, Taro Murayama, Lee Hanju, Shinya Kojima, Ichiro Takeuchi
In this study, we propose a method Distributionally Robust Safe Screening (DRSS), for identifying unnecessary samples and features within a DR covariate shift setting.
no code implementations • 23 Apr 2024 • Kevin Stowe, Benny Longwill, Alyssa Francis, Tatsuya Aoyama, Debanjan Ghosh, Swapna Somasundaran
Natural language generation tools are powerful and effective for generating content.
no code implementations • 20 Mar 2024 • Amir Zeldes, Tatsuya Aoyama, Yang Janet Liu, Siyao Peng, Debopam Das, Luke Gessler
In this article we present Enhanced Rhetorical Structure Theory (eRST), a new theoretical framework for computational discourse analysis, based on an expansion of Rhetorical Structure Theory (RST).
1 code implementation • 10 Sep 2023 • Yang Janet Liu, Tatsuya Aoyama, Amir Zeldes
Despite recent advances in Natural Language Processing (NLP), hierarchical discourse parsing in the framework of Rhetorical Structure Theory remains challenging, and our understanding of the reasons for this are as yet limited.
1 code implementation • 3 Jun 2023 • Tatsuya Aoyama, Shabnam Behzad, Luke Gessler, Lauren Levine, Jessica Lin, Yang Janet Liu, Siyao Peng, YIlun Zhu, Amir Zeldes
We evaluate state-of-the-art NLP systems on GENTLE and find severe degradation for at least some genres in their performance on all tasks, which indicates GENTLE's utility as an evaluation dataset for NLP systems.