Search Results for author: Yoshihiko Hayashi

Found 18 papers, 0 papers with code

Evaluating the Effects of Embedding with Speaker Identity Information in Dialogue Summarization

no code implementations LREC 2022 Yuji Naraki, Tetsuya Sakai, Yoshihiko Hayashi

Automatic dialogue summarization is a task used to succinctly summarize a dialogue transcript while correctly linking the speakers and their speech, which distinguishes this task from a conventional document summarization.

Document Summarization Informativeness +1

Towards the Detection of a Semantic Gap in the Chain of Commonsense Knowledge Triples

no code implementations LREC 2022 Yoshihiko Hayashi

A commonsense knowledge resource organizes common sense that is not necessarily correct all the time, but most people are expected to know or believe.

Common Sense Reasoning Language Modelling

Phrase-Level Localization of Inconsistency Errors in Summarization by Weak Supervision

no code implementations COLING 2022 Masato Takatsuka, Tetsunori Kobayashi, Yoshihiko Hayashi

Although the fluency of automatically generated abstractive summaries has improved significantly with advanced methods, the inconsistency that remains in summarization is recognized as an issue to be addressed.

Sentence Sentence Fusion

Learning Bidirectional Translation between Descriptions and Actions with Small Paired Data

no code implementations8 Mar 2022 Minori Toyoda, Kanata Suzuki, Yoshihiko Hayashi, Tetsuya OGATA

We experimentally evaluated our method using a paired dataset consisting of motion-captured actions and descriptions.

Translation

Embodying Pre-Trained Word Embeddings Through Robot Actions

no code implementations17 Apr 2021 Minori Toyoda, Kanata Suzuki, Hiroki Mori, Yoshihiko Hayashi, Tetsuya OGATA

These embeddings allow the robot to properly generate actions from unseen words that are not paired with actions in a dataset.

Translation Word Embeddings

Word Attribute Prediction Enhanced by Lexical Entailment Tasks

no code implementations LREC 2020 Mika Hasegawa, Tetsunori Kobayashi, Yoshihiko Hayashi

Human semantic knowledge about concepts acquired through perceptual inputs and daily experiences can be expressed as a bundle of attributes.

Attribute Lexical Entailment +1

Answerable or Not: Devising a Dataset for Extending Machine Reading Comprehension

no code implementations COLING 2018 Mao Nakanishi, Tetsunori Kobayashi, Yoshihiko Hayashi

However, to realize human-like language comprehension ability, a machine should also be able to distinguish not-answerable questions (NAQs) from answerable questions.

Machine Reading Comprehension Question Answering +1

Predicting the Evocation Relation between Lexicalized Concepts

no code implementations COLING 2016 Yoshihiko Hayashi

Evocation is a directed yet weighted semantic relationship between lexicalized concepts.

Relation

A Framework for Cross-lingual/Node-wise Alignment of Lexical-Semantic Resources

no code implementations LREC 2016 Yoshihiko Hayashi

Given lexical-semantic resources in different languages, it is useful to establish cross-lingual correspondences, preferably with semantic relation labels, between the concept nodes in these resources.

Relation

Extending Monolingual Semantic Textual Similarity Task to Multiple Cross-lingual Settings

no code implementations LREC 2016 Yoshihiko Hayashi, Wentao Luo

This paper describes our independent effort for extending the monolingual semantic textual similarity (STS) task setting to multiple cross-lingual settings involving English, Japanese, and Chinese.

Semantic Similarity Semantic Textual Similarity +2

Web-imageability of the Behavioral Features of Basic-level Concepts

no code implementations LREC 2014 Yoshihiko Hayashi

The recent research direction toward multimodal semantic representation would be further advanced, if we could have a machinery to collect adequate images from the Web, given a target concept.

Information Retrieval

Classifying Standard Linguistic Processing Functionalities based on Fundamental Data Operation Types

no code implementations LREC 2012 Yoshihiko Hayashi, Chiharu Narawa

iIt is often argued that a set of standard linguistic processing functionalities should be identified, with each of them given a formal specification.

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