Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Ziheng Zeng"'
Autor:
Ziheng Zeng, Suma Bhat
Publikováno v:
Transactions of the Association for Computational Linguistics, Vol 10, Pp 1120-1137 (2022)
AbstractIdiomatic expressions (IEs), characterized by their non-compositionality, are an important part of natural language. They have been a classical challenge to NLP, including pre-trained language models that drive today’s state-of-the-art. Pri
Externí odkaz:
https://doaj.org/article/ffd6eae464904473acc8abffc94c8b8c
Autor:
Ziheng Zeng, Suma Bhat
Publikováno v:
Transactions of the Association for Computational Linguistics, Vol 9, Pp 1546-1562 (2021)
AbstractIdiomatic expressions are an integral part of natural language and constantly being added to a language. Owing to their non-compositionality and their ability to take on a figurative or literal meaning depending on the sentential context, the
Externí odkaz:
https://doaj.org/article/94ca74f3e5d34a30baf4d15ff4210b33
Publikováno v:
Nano Research. 15:8524-8535
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6670ea1eaa685f91f124e47dbd32b350
https://doi.org/10.1007/s12274-022-4626-6
https://doi.org/10.1007/s12274-022-4626-6
Publikováno v:
Advanced Composites and Hybrid Materials. 6
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bd5022318a202cc09c8137f636daa6d1
https://doi.org/10.1007/s42114-023-00654-z
https://doi.org/10.1007/s42114-023-00654-z
Idiomatic expressions (IEs) play an essential role in natural language. In this paper, we study the task of idiomatic sentence paraphrasing (ISP), which aims to paraphrase a sentence with an IE by replacing the IE with its literal paraphrase. The lac
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9fb5d5c4b9a548125abd9c6f23353059
http://arxiv.org/abs/2112.08592
http://arxiv.org/abs/2112.08592
Publikováno v:
EMNLP (Findings)
In neural text editing, prevalent sequence-to-sequence based approaches directly map the unedited text either to the edited text or the editing operations, in which the performance is degraded by the limited source text encoding and long, varying dec
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7aa55c3ced20751261a9a216ff6ec6c2
https://doi.org/10.18653/v1/2020.findings-emnlp.159
https://doi.org/10.18653/v1/2020.findings-emnlp.159
Publikováno v:
LAK
Massive online courses occupy an important place in the educational landscape of today. We study an approach to scale predictive analytic models derived from online course discussion fora--specifically that of confusion detection--onto other courses.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::84eb8aa889efbdc1053d44684a840916
https://doi.org/10.1145/3303772.3303810
https://doi.org/10.1145/3303772.3303810
Publikováno v:
IEEE BigData
We present an effective machine learning method for malicious activity detection in enterprise security logs. Our method involves feature engineering, or generating new features by applying operators on features of the raw data. We generate DNF formu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a8b60342997560c75a8c18fe30eacc66
https://doi.org/10.1109/bigdata.2018.8621986
https://doi.org/10.1109/bigdata.2018.8621986