1 code implementation • 18 Feb 2024 • Ikuya Yamada, Ryokan Ri
In this study, we introduce LEIA, a language adaptation tuning method that utilizes Wikipedia entity names aligned across languages.
1 code implementation • 23 May 2023 • Shohei Higashiyama, Hiroki Ouchi, Hiroki Teranishi, Hiroyuki Otomo, Yusuke Ide, Aitaro Yamamoto, Hiroyuki Shindo, Yuki Matsuda, Shoko Wakamiya, Naoya Inoue, Ikuya Yamada, Taro Watanabe
Geoparsing is a fundamental technique for analyzing geo-entity information in text.
no code implementations • NAACL (MIA) 2022 • Akari Asai, Shayne Longpre, Jungo Kasai, Chia-Hsuan Lee, Rui Zhang, Junjie Hu, Ikuya Yamada, Jonathan H. Clark, Eunsol Choi
We present the results of the Workshop on Multilingual Information Access (MIA) 2022 Shared Task, evaluating cross-lingual open-retrieval question answering (QA) systems in 16 typologically diverse languages.
1 code implementation • NAACL 2022 • Sosuke Nishikawa, Ryokan Ri, Ikuya Yamada, Yoshimasa Tsuruoka, Isao Echizen
We present EASE, a novel method for learning sentence embeddings via contrastive learning between sentences and their related entities.
2 code implementations • ACL 2022 • Ryokan Ri, Ikuya Yamada, Yoshimasa Tsuruoka
We train a multilingual language model with 24 languages with entity representations and show the model consistently outperforms word-based pretrained models in various cross-lingual transfer tasks.
Ranked #1 on Cross-Lingual Question Answering on XQuAD (Average F1 metric, using extra training data)
no code implementations • 15 Oct 2021 • Sosuke Nishikawa, Ikuya Yamada, Yoshimasa Tsuruoka, Isao Echizen
We present a multilingual bag-of-entities model that effectively boosts the performance of zero-shot cross-lingual text classification by extending a multilingual pre-trained language model (e. g., M-BERT).
1 code implementation • ACL 2021 • Ikuya Yamada, Akari Asai, Hannaneh Hajishirzi
Most state-of-the-art open-domain question answering systems use a neural retrieval model to encode passages into continuous vectors and extract them from a knowledge source.
Ranked #2 on Open-Domain Question Answering on TQA
no code implementations • 1 Jan 2021 • Sewon Min, Jordan Boyd-Graber, Chris Alberti, Danqi Chen, Eunsol Choi, Michael Collins, Kelvin Guu, Hannaneh Hajishirzi, Kenton Lee, Jennimaria Palomaki, Colin Raffel, Adam Roberts, Tom Kwiatkowski, Patrick Lewis, Yuxiang Wu, Heinrich Küttler, Linqing Liu, Pasquale Minervini, Pontus Stenetorp, Sebastian Riedel, Sohee Yang, Minjoon Seo, Gautier Izacard, Fabio Petroni, Lucas Hosseini, Nicola De Cao, Edouard Grave, Ikuya Yamada, Sonse Shimaoka, Masatoshi Suzuki, Shumpei Miyawaki, Shun Sato, Ryo Takahashi, Jun Suzuki, Martin Fajcik, Martin Docekal, Karel Ondrej, Pavel Smrz, Hao Cheng, Yelong Shen, Xiaodong Liu, Pengcheng He, Weizhu Chen, Jianfeng Gao, Barlas Oguz, Xilun Chen, Vladimir Karpukhin, Stan Peshterliev, Dmytro Okhonko, Michael Schlichtkrull, Sonal Gupta, Yashar Mehdad, Wen-tau Yih
We review the EfficientQA competition from NeurIPS 2020.
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
3 code implementations • CONLL 2019 • Ikuya Yamada, Hiroyuki Shindo
This study proposes a Neural Attentive Bag-of-Entities model, which is a neural network model that performs text classification using entities in a knowledge base.
Ranked #9 on Text Classification on 20NEWS
1 code implementation • NAACL 2022 • Ikuya Yamada, Koki Washio, Hiroyuki Shindo, Yuji Matsumoto
We propose a global entity disambiguation (ED) model based on BERT.
Ranked #1 on Entity Disambiguation on MSNBC
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.
1 code implementation • TACL 2019 • Eric Wallace, Pedro Rodriguez, Shi Feng, Ikuya Yamada, Jordan Boyd-Graber
We propose human-in-the-loop adversarial generation, where human authors are guided to break models.
2 code implementations • COLING 2018 • Ikuya Yamada, Hiroyuki Shindo, Yoshiyasu Takefuji
In this paper, we describe TextEnt, a neural network model that learns distributed representations of entities and documents directly from a knowledge base (KB).
Ranked #1 on Entity Typing on Freebase FIGER
no code implementations • 23 Mar 2018 • Ikuya Yamada, Ryuji Tamaki, Hiroyuki Shindo, Yoshiyasu Takefuji
In this chapter, we describe our question answering system, which was the winning system at the Human-Computer Question Answering (HCQA) Competition at the Thirty-first Annual Conference on Neural Information Processing Systems (NIPS).
no code implementations • IJCNLP 2017 • Motoki Sato, Hiroyuki Shindo, Ikuya Yamada, Yuji Matsumoto
We present Segment-level Neural CRF, which combines neural networks with a linear chain CRF for segment-level sequence modeling tasks such as named entity recognition (NER) and syntactic chunking.
1 code implementation • CONLL 2017 • Yotam Eshel, Noam Cohen, Kira Radinsky, Shaul Markovitch, Ikuya Yamada, Omer Levy
We address the task of Named Entity Disambiguation (NED) for noisy text.
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 • 15 Mar 2017 • Ikuya Yamada, Motoki Sato, Hiroyuki Shindo
This paper describes our approach for the triple scoring task at the WSDM Cup 2017.
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