1 code implementation • 22 Apr 2024 • Jue Hou, Anisia Katinskaia, Lari Kotilainen, Sathianpong Trangcasanchai, Anh-Duc Vu, Roman Yangarber
This paper investigates what insights about linguistic features and what knowledge about the structure of natural language can be obtained from the encodings in transformer language models. In particular, we explore how BERT encodes the government relation between constituents in a sentence.
no code implementations • 9 May 2023 • Jue Hou, Anisia Katinskaia, Anh-Duc Vu, Roman Yangarber
Lastly, we show 4. that LMs of smaller size using morphological segmentation can perform comparably to models of larger size trained with BPE -- both in terms of (1) perplexity and (3) scores on downstream tasks.
no code implementations • 3 Dec 2022 • Anisia Katinskaia, Jue Hou, Anh-Duc Vu, Roman Yangarber
This paper presents the development of an AI-based language learning platform Revita.