no code implementations • WNUT (ACL) 2021 • Shohei Higashiyama, Masao Utiyama, Taro Watanabe, Eiichiro Sumita
Lexical normalization, in addition to word segmentation and part-of-speech tagging, is a fundamental task for Japanese user-generated text processing.
no code implementations • Findings (ACL) 2022 • Zuchao Li, Yiran Wang, Masao Utiyama, Eiichiro Sumita, Hai Zhao, Taro Watanabe
Inspired by this discovery, we then propose approaches to improving it, with respect to model structure and model training, to make the deep decoder practical in NMT.
no code implementations • SpaNLP (ACL) 2022 • Van-Hien Tran, Hiroki Ouchi, Taro Watanabe, Yuji Matsumoto
Zero-shot relation extraction (ZSRE) aims to predict target relations that cannot be observed during training.
Ranked #3 on Zero-shot Relation Classification on FewRel
no code implementations • NAACL (CALCS) 2021 • Chihiro Taguchi, Yusuke Sakai, Taro Watanabe
Given this situation, we proposed a transliteration method based on subword-level language identification.
no code implementations • EURALI (LREC) 2022 • Chihiro Taguchi, Sei Iwata, Taro Watanabe
Experimenting on NMCTT and the Turkish-German CS treebank (SAGT), we demonstrate that the proposed annotation scheme introduced in NMCTT can improve the performance of the subword-level language identification.
1 code implementation • COLING (TextGraphs) 2022 • Xincan Feng, Zhi Qu, Yuchang Cheng, Taro Watanabe, Nobuhiro Yugami
A Knowledge Graph (KG) is the directed graphical representation of entities and relations in the real world.
no code implementations • 18 Apr 2024 • Yusuke Sakai, Mana Makinae, Hidetaka Kamigaito, Taro Watanabe
In Simultaneous Machine Translation (SiMT) systems, training with a simultaneous interpretation (SI) corpus is an effective method for achieving high-quality yet low-latency systems.
no code implementations • 28 Mar 2024 • Eri Onami, Shuhei Kurita, Taiki Miyanishi, Taro Watanabe
Document question answering is a task of question answering on given documents such as reports, slides, pamphlets, and websites, and it is a truly demanding task as paper and electronic forms of documents are so common in our society.
1 code implementation • 25 Mar 2024 • Huayang Li, Deng Cai, Zhi Qu, Qu Cui, Hidetaka Kamigaito, Lemao Liu, Taro Watanabe
In our work, we propose a new task formulation of dense retrieval, cross-lingual contextualized phrase retrieval, which aims to augment cross-lingual applications by addressing polysemy using context information.
no code implementations • 13 Mar 2024 • Jesse Atuhurra, Seiveright Cargill Dujohn, Hidetaka Kamigaito, Hiroyuki Shindo, Taro Watanabe
Natural language processing (NLP) practitioners are leveraging large language models (LLM) to create structured datasets from semi-structured and unstructured data sources such as patents, papers, and theses, without having domain-specific knowledge.
no code implementations • 29 Feb 2024 • Kazuki Hayashi, Yusuke Sakai, Hidetaka Kamigaito, Katsuhiko Hayashi, Taro Watanabe
To address this issue, we propose a new task: the artwork explanation generation task, along with its evaluation dataset and metric for quantitatively assessing the understanding and utilization of knowledge about artworks.
1 code implementation • 22 Feb 2024 • Seiji Gobara, Hidetaka Kamigaito, Taro Watanabe
Experimental results on the Stack-Overflow dataset and the TSCC dataset, including multi-turn conversation show that LLMs can implicitly handle text difficulty between user input and its generated response.
no code implementations • 19 Feb 2024 • Shigeki Saito, Kazuki Hayashi, Yusuke Ide, Yusuke Sakai, Kazuma Onishi, Toma Suzuki, Seiji Gobara, Hidetaka Kamigaito, Katsuhiko Hayashi, Taro Watanabe
Large-scale vision language models (LVLMs) are language models that are capable of processing images and text inputs by a single model.
no code implementations • 17 Feb 2024 • Hiroyuki Deguchi, Yusuke Sakai, Hidetaka Kamigaito, Taro Watanabe, Hideki Tanaka, Masao Utiyama
Minimum Bayes risk (MBR) decoding achieved state-of-the-art translation performance by using COMET, a neural metric that has a high correlation with human evaluation.
no code implementations • 14 Feb 2024 • Yuto Nishida, Makoto Morishita, Hidetaka Kamigaito, Taro Watanabe
Generating multiple translation candidates would enable users to choose the one that satisfies their needs.
no code implementations • 15 Nov 2023 • Yusuke Sakai, Hidetaka Kamigaito, Katsuhiko Hayashi, Taro Watanabe
Knowledge Graph Completion (KGC) is a task that infers unseen relationships between entities in a KG.
1 code implementation • 18 Oct 2023 • Hiroyuki Deguchi, Hayate Hirano, Tomoki Hoshino, Yuto Nishida, Justin Vasselli, Taro Watanabe
We publish our knn-seq as an MIT-licensed open-source project and the code is available on https://github. com/naist-nlp/knn-seq .
1 code implementation • 17 Sep 2023 • Xincan Feng, Hidetaka Kamigaito, Katsuhiko Hayashi, Taro Watanabe
Subsampling is effective in Knowledge Graph Embedding (KGE) for reducing overfitting caused by the sparsity in Knowledge Graph (KG) datasets.
1 code implementation • 14 Sep 2023 • Huayang Li, Siheng Li, Deng Cai, Longyue Wang, Lemao Liu, Taro Watanabe, Yujiu Yang, Shuming Shi
We release our dataset, model, and demo to foster future research in the area of multimodal instruction following.
Ranked #89 on Visual Question Answering on MM-Vet
2 code implementations • 30 Jun 2023 • Yusuke Ide, Masato Mita, Adam Nohejl, Hiroki Ouchi, Taro Watanabe
Lexical complexity prediction (LCP) is the task of predicting the complexity of words in a text on a continuous scale.
1 code implementation • Journal of Natural Language Processing 2023 • Van-Hien Tran, Hiroki Ouchi, Hiroyuki Shindo, Yuji Matsumoto, Taro Watanabe
This study argues that enhancing the semantic correlation between instances and relations is key to effectively solving the zero-shot relation extraction task.
Ranked #1 on Zero-shot Relation Classification on FewRel
1 code implementation • 5 Jun 2023 • Miyu Oba, Tatsuki Kuribayashi, Hiroki Ouchi, Taro Watanabe
With the success of neural language models (LMs), their language acquisition has gained much attention.
1 code implementation • 3 Jun 2023 • Hidetaka Kamigaito, Katsuhiko Hayashi, Taro Watanabe
This task consists of two parts: the first is to generate a table containing knowledge about an entity and its related image, and the second is to generate an image from an entity with a caption and a table containing related knowledge of the entity.
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 • 19 May 2023 • Hiroki Ouchi, Hiroyuki Shindo, Shoko Wakamiya, Yuki Matsuda, Naoya Inoue, Shohei Higashiyama, Satoshi Nakamura, Taro Watanabe
We have constructed Arukikata Travelogue Dataset and released it free of charge for academic research.
1 code implementation • 6 Dec 2022 • Ukyo Honda, Taro Watanabe, Yuji Matsumoto
Discriminativeness is a desirable feature of image captions: captions should describe the characteristic details of input images.
1 code implementation • 26 Oct 2022 • Huayang Li, Deng Cai, Jin Xu, Taro Watanabe
The combination of $n$-gram and neural LMs not only allows the neural part to focus on the deeper understanding of language but also provides a flexible way to customize an LM by switching the underlying $n$-gram model without changing the neural model.
1 code implementation • COLING 2022 • Zhi Qu, Taro Watanabe
Multilingual neural machine translation can translate unseen language pairs during training, i. e. zero-shot translation.
no code implementations • Findings (ACL) 2022 • Jiannan Xiang, Huayang Li, Defu Lian, Guoping Huang, Taro Watanabe, Lemao Liu
To this end, we study the dynamic relationship between the encoded linguistic information and task performance from the viewpoint of Pareto Optimality.
no code implementations • Journal of Natural Language Processing 2021 • Van-Hien Tran, Van-Thuy Phi, Akihiko Kato, Hiroyuki Shindo, Taro Watanabe, Yuji Matsumoto
A recent study (Yu et al. 2020) proposed a novel decomposition strategy that splits the task into two interrelated subtasks: detection of the head-entity (HE) and identification of the corresponding tail-entity and relation (TER) for each extracted head-entity.
no code implementations • 1 Nov 2021 • Yushi Hirose, Masashi Shimbo, Taro Watanabe
For knowledge graph completion, two major types of prediction models exist: one based on graph embeddings, and the other based on relation path rule induction.
no code implementations • Joint Conference on Lexical and Computational Semantics 2021 • Yuki Yamamoto, Yuji Matsumoto, Taro Watanabe
Abstract Meaning Representation (AMR) is a sentence-level meaning representation based on predicate argument structure.
no code implementations • ACL 2021 • Shintaro Harada, Taro Watanabe
It is reported that grammatical information is useful for machine translation (MT) task.
1 code implementation • ACL 2021 • Yiran Wang, Hiroyuki Shindo, Yuji Matsumoto, Taro Watanabe
This paper presents a novel method for nested named entity recognition.
Ranked #12 on Nested Named Entity Recognition on GENIA
no code implementations • ACL 2021 • Sei Iwata, Taro Watanabe, Masaaki Nagata
In the experiments, our model surpassed the sequence labeling baseline.
1 code implementation • EACL 2021 • Ukyo Honda, Yoshitaka Ushiku, Atsushi Hashimoto, Taro Watanabe, Yuji Matsumoto
Unsupervised image captioning is a challenging task that aims at generating captions without the supervision of image-sentence pairs, but only with images and sentences drawn from different sources and object labels detected from the images.
1 code implementation • NAACL 2021 • Shohei Higashiyama, Masao Utiyama, Taro Watanabe, Eiichiro Sumita
Morphological analysis (MA) and lexical normalization (LN) are both important tasks for Japanese user-generated text (UGT).
no code implementations • 1 Jan 2021 • Guanlin Li, Lemao Liu, Taro Watanabe, Conghui Zhu, Tiejun Zhao
Unsupervised Neural Machine Translation or UNMT has received great attention in recent years.
no code implementations • COLING 2020 • Yuya Sawada, Takashi Wada, Takayoshi Shibahara, Hiroki Teranishi, Shuhei Kondo, Hiroyuki Shindo, Taro Watanabe, Yuji Matsumoto
We propose a simple method for nominal coordination boundary identification.
no code implementations • WS 2018 • Wei Wang, Taro Watanabe, Macduff Hughes, Tetsuji Nakagawa, Ciprian Chelba
Measuring domain relevance of data and identifying or selecting well-fit domain data for machine translation (MT) is a well-studied topic, but denoising is not yet.
no code implementations • COLING 2016 • Yusuke Oda, Taku Kudo, Tetsuji Nakagawa, Taro Watanabe
In this paper, we propose a new decoding method for phrase-based statistical machine translation which directly uses multiple preordering candidates as a graph structure.