Search Results for author: Takenobu Tokunaga

Found 35 papers, 2 papers with code

Parsing Argumentative Structure in English-as-Foreign-Language Essays

1 code implementation EACL (BEA) 2021 Jan Wira Gotama Putra, Simone Teufel, Takenobu Tokunaga

Two sentence encoders are employed, and we observed that non-fine-tuning models generally performed better when using Sentence-BERT as opposed to BERT encoder.

Argument Mining Sentence

Annotation Study of Japanese Judgments on Tort for Legal Judgment Prediction with Rationales

no code implementations LREC 2022 Hiroaki Yamada, Takenobu Tokunaga, Ryutaro Ohara, Keisuke Takeshita, Mihoko Sumida

Moreover, the scheme can capture the explicit causal relation between judge’s decisions and their corresponding rationales, allowing multiple decisions in a document.

NHK’s Lexically-Constrained Neural Machine Translation at WAT 2021

no code implementations ACL (WAT) 2021 Hideya Mino, Kazutaka Kinugawa, Hitoshi Ito, Isao Goto, Ichiro Yamada, Takenobu Tokunaga

In this paper, we use a lexically-constrained neural machine translation (NMT), which concatenates the source sentence and constrained words with a special token to input them into the encoder of NMT.

Machine Translation NMT +3

Japanese Tort-case Dataset for Rationale-supported Legal Judgment Prediction

no code implementations1 Dec 2023 Hiroaki Yamada, Takenobu Tokunaga, Ryutaro Ohara, Akira Tokutsu, Keisuke Takeshita, Mihoko Sumida

This paper presents the first dataset for Japanese Legal Judgment Prediction (LJP), the Japanese Tort-case Dataset (JTD), which features two tasks: tort prediction and its rationale extraction.

Multi-Task and Multi-Corpora Training Strategies to Enhance Argumentative Sentence Linking Performance

1 code implementation EMNLP (ArgMining) 2021 Jan Wira Gotama Putra, Simone Teufel, Takenobu Tokunaga

Argumentative structure prediction aims to establish links between textual units and label the relationship between them, forming a structured representation for a given input text.


Gamification Platform for Collecting Task-oriented Dialogue Data

no code implementations LREC 2020 Haruna Ogawa, Hitoshi Nishikawa, Takenobu Tokunaga, Hikaru Yokono

Our platform enables data collectors to create their original video game in which they can collect dialogue data of various types of tasks by using the logging function of the platform.

Neural Machine Translation System using a Content-equivalently Translated Parallel Corpus for the Newswire Translation Tasks at WAT 2019

no code implementations WS 2019 Hideya Mino, Hitoshi Ito, Isao Goto, Ichiro Yamada, Hideki Tanaka, Takenobu Tokunaga

The content-equivalent corpus was effective for improving translation quality, and our systems achieved the best human evaluation scores in the newswire translation tasks at WAT 2019.

Machine Translation Sentence +1

Supporting content evaluation of student summaries by Idea Unit embedding

no code implementations WS 2019 Marcello Gecchele, Hiroaki Yamada, Takenobu Tokunaga, Yasuyo Sawaki

We im-plemented the proposed method in a GUI tool{``}Segment Matcher{''} that aids teachers to estab-lish a link between corresponding IUs acrossthe summary and source text.

Key-value Attention Mechanism for Neural Machine Translation

no code implementations IJCNLP 2017 Hideya Mino, Masao Utiyama, Eiichiro Sumita, Takenobu Tokunaga

In this paper, we propose a neural machine translation (NMT) with a key-value attention mechanism on the source-side encoder.

Machine Translation NMT +1

An Eye-tracking Study of Named Entity Annotation

no code implementations RANLP 2017 Takenobu Tokunaga, Hitoshi Nishikawa, Tomoya Iwakura

Utilising effective features in machine learning-based natural language processing (NLP) is crucial in achieving good performance for a given NLP task.

Active Learning Coreference Resolution +4

Evaluation of Automatically Generated Pronoun Reference Questions

no code implementations WS 2017 Arief Yudha Satria, Takenobu Tokunaga

This study provides a detailed analysis of evaluation of English pronoun reference questions which are created automatically by machine.

Multiple-choice Reading Comprehension

Evaluating text coherence based on semantic similarity graph

no code implementations WS 2017 Jan Wira Gotama Putra, Takenobu Tokunaga

Coherence is a crucial feature of text because it is indispensable for conveying its communication purpose and meaning to its readers.

graph construction Semantic Similarity +3

Parameter estimation of Japanese predicate argument structure analysis model using eye gaze information

no code implementations COLING 2016 Ryosuke Maki, Hitoshi Nishikawa, Takenobu Tokunaga

In this paper, we propose utilising eye gaze information for estimating parameters of a Japanese predicate argument structure (PAS) analysis model.

An extension of ISO-Space for annotating object direction

no code implementations WS 2016 Daiki Gotou, Hitoshi Nishikawa, Takenobu Tokunaga

In this paper, we extend an existing annotation scheme ISO-Space for annotating necessary spatial information for the task placing an specified object at a specified location with a specified direction according to a natural language instruction.

Object TAG

Building a Corpus of Manually Revised Texts from Discourse Perspective

no code implementations LREC 2014 Ryu Iida, Takenobu Tokunaga

This paper presents building a corpus of manually revised texts which includes both before and after-revision information.

The REX corpora: A collection of multimodal corpora of referring expressions in collaborative problem solving dialogues

no code implementations LREC 2012 Takenobu Tokunaga, Ryu Iida, Asuka Terai, Naoko Kuriyama

In this respect, we succeeded in constructing a collection of corpora that included a variety of characteristics by changing the configurations for each set of dialogues, as originally planned.

Effects of Document Clustering in Modeling Wikipedia-style Term Descriptions

no code implementations LREC 2012 Atsushi Fujii, Yuya Fujii, Takenobu Tokunaga

Because viewpoints required for explanation are different depending on the type of a term, such as animal and disease, we model articles in Wikipedia to extract a viewpoint structure for each term type.

Clustering Cultural Vocal Bursts Intensity Prediction

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