Search Results for author: Takuma Udagawa

Found 12 papers, 6 papers with code

A Comparative Analysis of Task-Agnostic Distillation Methods for Compressing Transformer Language Models

no code implementations13 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.

Knowledge Distillation

Multiple Representation Transfer from Large Language Models to End-to-End ASR Systems

no code implementations7 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

Sentence Identification with BOS and EOS Label Combinations

no code implementations31 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.

Sentence Sentence segmentation

Policy-Adaptive Estimator Selection for Off-Policy Evaluation

1 code implementation25 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.

counterfactual Off-policy evaluation

Data-Driven Off-Policy Estimator Selection: An Application in User Marketing on An Online Content Delivery Service

no code implementations17 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.

Decision Making Marketing +2

Evaluating the Robustness of Off-Policy Evaluation

2 code implementations31 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.

Off-policy evaluation Recommendation Systems

Maintaining Common Ground in Dynamic Environments

1 code implementation29 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

An Annotated Corpus of Reference Resolution for Interpreting Common Grounding

1 code implementation18 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.

Coreference Resolution Goal-Oriented Dialog +2

A Natural Language Corpus of Common Grounding under Continuous and Partially-Observable Context

1 code implementation8 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.

Dialogue Understanding Goal-Oriented Dialog +1

Cannot find the paper you are looking for? You can Submit a new open access paper.