Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Chenglei Si"'
Autor:
Chenglei Si, Zhengyan Zhang, Yingfa Chen, Fanchao Qi, Xiaozhi Wang, Zhiyuan Liu, Yasheng Wang, Qun Liu, Maosong Sun
Publikováno v:
Transactions of the Association for Computational Linguistics, Vol 11, Pp 469-487 (2023)
AbstractTokenization is fundamental to pretrained language models (PLMs). Existing tokenization methods for Chinese PLMs typically treat each character as an indivisible token. However, they ignore the unique feature of the Chinese writing system whe
Externí odkaz:
https://doaj.org/article/5e1c7178b0ed4851a6922b1218a03d89
Publikováno v:
ACL/IJCNLP (Findings)
Machine Reading Comprehension (MRC) is an important testbed for evaluating models' natural language understanding (NLU) ability. There has been rapid progress in this area, with new models achieving impressive performance on various benchmarks. Howev
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::438b087096412199bf8a0f572b272f72
https://doi.org/10.18653/v1/2021.findings-acl.56
https://doi.org/10.18653/v1/2021.findings-acl.56
Publikováno v:
ACL/IJCNLP (Findings)
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::81d9c75ac1d0bad0e2c161176e4f085e
https://doi.org/10.18653/v1/2021.findings-acl.137
https://doi.org/10.18653/v1/2021.findings-acl.137
Publikováno v:
SEM
Adversarial training (AT) as a regularization method has proved its effectiveness on various tasks. Though there are successful applications of AT on some NLP tasks, the distinguishing characteristics of NLP tasks have not been exploited. In this pap
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2c6b1d4c735299b7a4f5409562de7cf8
https://doi.org/10.18653/v1/2021.starsem-1.30
https://doi.org/10.18653/v1/2021.starsem-1.30
Publikováno v:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::139c4aa502b145a62cb24c94f7ecabae
https://doi.org/10.18653/v1/2021.emnlp-main.757
https://doi.org/10.18653/v1/2021.emnlp-main.757
Most pre-trained language models (PLMs) construct word representations at subword level with Byte-Pair Encoding (BPE) or its variations, by which OOV (out-of-vocab) words are almost avoidable. However, those methods split a word into subword units an
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ae49907ae6631806a28cd1e03f0a7937
Publikováno v:
WAT@EMNLP-IJCNLP
Sentiment ambiguous lexicons refer to words where their polarity depends strongly on con- text. As such, when the context is absent, their translations or their embedded sentence ends up (incorrectly) being dependent on the training data. While neura
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f91bbccdf5e5c67ef82f50d42bd0dfcd
https://doi.org/10.18653/v1/d19-5227
https://doi.org/10.18653/v1/d19-5227
Publikováno v:
Proceedings of the Workshop on Extracting Structured Knowledge from Scientific Publications.
Datasets are integral artifacts of empirical scientific research. However, due to natural language variation, their recognition can be difficult and even when identified, can often be inconsistently referred across and within publications. We report
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d0a6a17b66e9859bcd0d7a257cd93186
https://doi.org/10.18653/v1/w19-2604
https://doi.org/10.18653/v1/w19-2604