Search Results for author: Hideaki Takeda

Found 13 papers, 7 papers with code

SPARQL Generation with Entity Pre-trained GPT for KG Question Answering

1 code implementation1 Feb 2024 Diego Bustamante, Hideaki Takeda

We obtained a 62. 703% accuracy of exact SPARQL matches on testing at 3-shots, a F1 of 0. 809 on the entity linking challenge and a F1 of 0. 009 on the question answering challenge.

Entity Linking Knowledge Graphs +1

TabIQA: Table Questions Answering on Business Document Images

1 code implementation27 Mar 2023 Phuc Nguyen, Nam Tuan Ly, Hideaki Takeda, Atsuhiro Takasu

Table answering questions from business documents has many challenges that require understanding tabular structures, cross-document referencing, and additional numeric computations beyond simple search queries.

Rethinking Image-based Table Recognition Using Weakly Supervised Methods

1 code implementation14 Mar 2023 Nam Tuan Ly, Atsuhiro Takasu, Phuc Nguyen, Hideaki Takeda

In this paper, we propose a weakly supervised model named WSTabNet for table recognition that relies only on HTML (or LaTeX) code-level annotations of table images.

Table Recognition

TabEAno: Table to Knowledge Graph Entity Annotation

no code implementations5 Oct 2020 Phuc Nguyen, Natthawut Kertkeidkachorn, Ryutaro Ichise, Hideaki Takeda

In the Open Data era, a large number of table resources have been made available on the Web and data portals.

MTab: Matching Tabular Data to Knowledge Graph using Probability Models

2 code implementations1 Oct 2019 Phuc Nguyen, Natthawut Kertkeidkachorn, Ryutaro Ichise, Hideaki Takeda

This paper presents the design of our system, namely MTab, for Semantic Web Challenge on Tabular Data to Knowledge Graph Matching (SemTab 2019).

Entity Typing Graph Matching +3

Wikipedia2Vec: An Efficient Toolkit for Learning and Visualizing the Embeddings of Words and Entities from Wikipedia

no code implementations EMNLP 2020 Ikuya Yamada, Akari Asai, Jin Sakuma, Hiroyuki Shindo, Hideaki Takeda, Yoshiyasu Takefuji, Yuji Matsumoto

The embeddings of entities in a large knowledge base (e. g., Wikipedia) are highly beneficial for solving various natural language tasks that involve real world knowledge.

World Knowledge

EmbNum: Semantic labeling for numerical values with deep metric learning

no code implementations26 Jun 2018 Phuc Nguyen, Khai Nguyen, Ryutaro Ichise, Hideaki Takeda

Semantic labeling for numerical values is a task of assigning semantic labels to unknown numerical attributes.

Attribute Metric Learning +1

Joint Learning of the Embedding of Words and Entities for Named Entity Disambiguation

1 code implementation CONLL 2016 Ikuya Yamada, Hiroyuki Shindo, Hideaki Takeda, Yoshiyasu Takefuji

The KB graph model learns the relatedness of entities using the link structure of the KB, whereas the anchor context model aims to align vectors such that similar words and entities occur close to one another in the vector space by leveraging KB anchors and their context words.

Entity Disambiguation Entity Linking

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