Search Results for author: Yasuhiro Sogawa

Found 11 papers, 7 papers with code

Unsupervised Domain Adaptation on Question-Answering System with Conversation Data

no code implementations SIGDIAL (ACL) 2022 Amalia Adiba, Takeshi Homma, Yasuhiro Sogawa

Therefore, unlike previous studies, we propose a domain-adaptation framework of MRC under the assumption that the only available data in the target domain are human conversations between a user asking questions and an expert answering the questions.

Machine Reading Comprehension Question Answering +1

Text Retrieval with Multi-Stage Re-Ranking Models

1 code implementation14 Nov 2023 Yuichi Sasazawa, Kenichi Yokote, Osamu Imaichi, Yasuhiro Sogawa

We ranked the documents by BM25 and language models, and then re-ranks by a model ensemble or a larger language model for documents with high similarity to the query.

Language Modelling Re-Ranking +2

Learning Deductive Reasoning from Synthetic Corpus based on Formal Logic

1 code implementation11 Aug 2023 Terufumi Morishita, Gaku Morio, Atsuki Yamaguchi, Yasuhiro Sogawa

We rethink this and adopt a well-grounded set of deduction rules based on formal logic theory, which can derive any other deduction rules when combined in a multistep way.

Formal Logic Logical Reasoning

LARCH: Large Language Model-based Automatic Readme Creation with Heuristics

1 code implementation6 Aug 2023 Yuta Koreeda, Terufumi Morishita, Osamu Imaichi, Yasuhiro Sogawa

Writing a readme is a crucial aspect of software development as it plays a vital role in managing and reusing program code.

Language Modelling Large Language Model

How do different tokenizers perform on downstream tasks in scriptio continua languages?: A case study in Japanese

1 code implementation16 Jun 2023 Takuro Fujii, Koki Shibata, Atsuki Yamaguchi, Terufumi Morishita, Yasuhiro Sogawa

This paper investigates the effect of tokenizers on the downstream performance of pretrained language models (PLMs) in scriptio continua languages where no explicit spaces exist between words, using Japanese as a case study.

How does the task complexity of masked pretraining objectives affect downstream performance?

1 code implementation18 May 2023 Atsuki Yamaguchi, Hiroaki Ozaki, Terufumi Morishita, Gaku Morio, Yasuhiro Sogawa

Masked language modeling (MLM) is a widely used self-supervised pretraining objective, where a model needs to predict an original token that is replaced with a mask given contexts.

Language Modelling Masked Language Modeling

Controlling keywords and their positions in text generation

1 code implementation19 Apr 2023 Yuichi Sasazawa, Terufumi Morishita, Hiroaki Ozaki, Osamu Imaichi, Yasuhiro Sogawa

In this paper, we tackle a novel task of controlling not only keywords but also the position of each keyword in the text generation.

Story Generation

Hitachi at SemEval-2023 Task 3: Exploring Cross-lingual Multi-task Strategies for Genre and Framing Detection in Online News

no code implementations3 Mar 2023 Yuta Koreeda, Ken-ichi Yokote, Hiroaki Ozaki, Atsuki Yamaguchi, Masaya Tsunokake, Yasuhiro Sogawa

Based on the multilingual, multi-task nature of the task and the low-resource setting, we investigated different cross-lingual and multi-task strategies for training the pretrained language models.

An Interactive Greedy Approach to Group Sparsity in High Dimensions

1 code implementation10 Jul 2017 Wei Qian, Wending Li, Yasuhiro Sogawa, Ryohei Fujimaki, Xitong Yang, Ji Liu

Sparsity learning with known grouping structure has received considerable attention due to wide modern applications in high-dimensional data analysis.

Human Activity Recognition Vocal Bursts Intensity Prediction

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