Zobrazeno 1 - 10 of 26 pro vyhledávání: '"Hiroki Ouchi"'
1
Akademický článek
Instance-Based Neural Dependency Parsing
Autor: Hiroki Ouchi, Jun Suzuki, Sosuke Kobayashi, Sho Yokoi, Tatsuki Kuribayashi, Masashi Yoshikawa, Kentaro Inui
Publikováno v: Transactions of the Association for Computational Linguistics, Vol 9, Pp 1493-1507 (2021)
AbstractInterpretable rationales for model predictions are crucial in practical applications. We develop neural models that possess an interpretable inference process for dependency parsing. Our models adopt instance-based inference, where dependency
Externí odkaz: https://doaj.org/article/53a8dde4eecf4b1e97ab48158f11ca50
Zobrazit plný text záznamu
7
An Empirical Study of Contextual Data Augmentation for Japanese Zero Anaphora Resolution
Autor: Hiroki Ouchi, Ryo Takahashi, Kentaro Inui, Yuichiroh Matsubayashi, Shun Kiyono, Ryuto Konno
Publikováno v: COLING
One critical issue of zero anaphora resolution (ZAR) is the scarcity of labeled data. This study explores how effectively this problem can be alleviated by data augmentation. We adopt a state-of-the-art data augmentation method, called the contextual
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::780c0b373a92cb171e50b1d12cf92ff8
http://arxiv.org/abs/2011.00948
Zobrazit plný text záznamu
8
Corruption Is Not All Bad: Incorporating Discourse Structure into Pre-training via Corruption for Essay Scoring
Autor: Naoya Inoue, Farjana Sultana Mim, Paul Reisert, Hiroki Ouchi, Kentaro Inui
Existing approaches for automated essay scoring and document representation learning typically rely on discourse parsers to incorporate discourse structure into text representation. However, the performance of parsers is not always adequate, especial
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b3e5f7171c33246ad2691169c2600801
http://arxiv.org/abs/2010.06137
Zobrazit plný text záznamu
9
Embeddings of Label Components for Sequence Labeling: A Case Study of Fine-grained Named Entity Recognition
Autor: Shumpei Miyawaki, Takuma Kato, Kaori Abe, Jun Suzuki, Kentaro Inui, Hiroki Ouchi
Publikováno v: ACL (student)
In general, the labels used in sequence labeling consist of different types of elements. For example, IOB-format entity labels, such as B-Person and I-Person, can be decomposed into span (B and I) and type information (Person). However, while most se
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f8753cb2542525bbeb6579025aa1a0ec
http://arxiv.org/abs/2006.01372
Zobrazit plný text záznamu
10
Instance-Based Learning of Span Representations: A Case Study through Named Entity Recognition
Autor: Sho Yokoi, Ryuto Konno, Sosuke Kobayashi, Hiroki Ouchi, Jun Suzuki, Tatsuki Kuribayashi, Kentaro Inui
Publikováno v: ACL
Interpretable rationales for model predictions play a critical role in practical applications. In this study, we develop models possessing interpretable inference process for structured prediction. Specifically, we present a method of instance-based
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a909f6bd658064ea24fd9faf8fa70862
Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání

Omezení vyhledávání
Plný text Recenzováno Digitální knihovna AV ČR
Zdroje