1 code implementation • 1 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.
1 code implementation • 27 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.
1 code implementation • 14 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.
no code implementations • 5 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.
8 code implementations • EMNLP 2020 • Ikuya Yamada, Akari Asai, Hiroyuki Shindo, Hideaki Takeda, Yuji Matsumoto
In this paper, we propose new pretrained contextualized representations of words and entities based on the bidirectional transformer.
Ranked #1 on Entity Typing on Open Entity
2 code implementations • 1 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).
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.
no code implementations • 26 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.
1 code implementation • TACL 2017 • Ikuya Yamada, Hiroyuki Shindo, Hideaki Takeda, Yoshiyasu Takefuji
Given a text in the KB, we train our proposed model to predict entities that are relevant to the text.
Ranked #2 on Entity Disambiguation on TAC2010
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.
Ranked #4 on Entity Disambiguation on TAC2010