no code implementations • 13 Oct 2023 • Takuma Udagawa, Aashka Trivedi, Michele Merler, Bishwaranjan Bhattacharjee
Our target of study includes Output Distribution (OD) transfer, Hidden State (HS) transfer with various layer mapping strategies, and Multi-Head Attention (MHA) transfer based on MiniLMv2.
no code implementations • 7 Sep 2023 • Takuma Udagawa, Masayuki Suzuki, Gakuto Kurata, Masayasu Muraoka, George Saon
However, existing works only transfer a single representation of LLM (e. g. the last layer of pretrained BERT), while the representation of a text is inherently non-unique and can be obtained variously from different layers, contexts and models.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • 16 Mar 2023 • Aashka Trivedi, Takuma Udagawa, Michele Merler, Rameswar Panda, Yousef El-Kurdi, Bishwaranjan Bhattacharjee
In each episode of the search process, a NAS controller predicts a reward based on the distillation loss and latency of inference.
no code implementations • 31 Jan 2023 • Takuma Udagawa, Hiroshi Kanayama, Issei Yoshida
To tackle this issue, we formulate a novel task of sentence identification, where the goal is to identify SUs while excluding NSUs in a given text.
1 code implementation • 25 Nov 2022 • Takuma Udagawa, Haruka Kiyohara, Yusuke Narita, Yuta Saito, Kei Tateno
Although many estimators have been developed, there is no single estimator that dominates the others, because the estimators' accuracy can vary greatly depending on a given OPE task such as the evaluation policy, number of actions, and noise level.
no code implementations • 1 Apr 2022 • Takuma Udagawa, Masayuki Suzuki, Gakuto Kurata, Nobuyasu Itoh, George Saon
Large-scale language models (LLMs) such as GPT-2, BERT and RoBERTa have been successfully applied to ASR N-best rescoring.
no code implementations • 17 Sep 2021 • Yuta Saito, Takuma Udagawa, Kei Tateno
As proof of concept, we use our procedure to select the best estimator to evaluate coupon treatment policies on a real-world online content delivery service.
2 code implementations • 31 Aug 2021 • Yuta Saito, Takuma Udagawa, Haruka Kiyohara, Kazuki Mogi, Yusuke Narita, Kei Tateno
Unfortunately, identifying a reliable estimator from results reported in research papers is often difficult because the current experimental procedure evaluates and compares the estimators' performance on a narrow set of hyperparameters and evaluation policies.
1 code implementation • 29 May 2021 • Takuma Udagawa, Akiko Aizawa
Common grounding is the process of creating and maintaining mutual understandings, which is a critical aspect of sophisticated human communication.
End-To-End Dialogue Modelling Goal-Oriented Dialogue Systems +1
1 code implementation • Findings of the Association for Computational Linguistics 2020 • Takuma Udagawa, Takato Yamazaki, Akiko Aizawa
Recent models achieve promising results in visually grounded dialogues.
1 code implementation • 18 Nov 2019 • Takuma Udagawa, Akiko Aizawa
Common grounding is the process of creating, repairing and updating mutual understandings, which is a fundamental aspect of natural language conversation.
1 code implementation • 8 Jul 2019 • Takuma Udagawa, Akiko Aizawa
Finally, we evaluate and analyze baseline neural models on a simple subtask that requires recognition of the created common ground.