Zobrazeno 1 - 10
of 25
pro vyhledávání: '"Dumitru-Clementin Cercel"'
Autor:
Andrei-Marius Avram, Verginica Barbu Mititelu, Vasile Păiș, Dumitru-Clementin Cercel, Ștefan Trăușan-Matu
Publikováno v:
Mathematics, Vol 11, Iss 11, p 2548 (2023)
Correctly identifying multiword expressions (MWEs) is an important task for most natural language processing systems since their misidentification can result in ambiguity and misunderstanding of the underlying text. In this work, we evaluate the perf
Externí odkaz:
https://doaj.org/article/8d5645591a954ca0af5b7a30c0842878
Autor:
Trăușan-Matu, Andrei-Marius Avram, Verginica Barbu Mititelu, Vasile Păiș, Dumitru-Clementin Cercel, Ștefan
Publikováno v:
Mathematics; Volume 11; Issue 11; Pages: 2548
Correctly identifying multiword expressions (MWEs) is an important task for most natural language processing systems since their misidentification can result in ambiguity and misunderstanding of the underlying text. In this work, we evaluate the perf
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=multidiscipl::be93245c19bdd247aea6e5a83cb4cb3e
Publikováno v:
2022 International Joint Conference on Neural Networks (IJCNN).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6fd9aa6637e2882eb927ab71efd6472d
https://doi.org/10.1109/ijcnn55064.2022.9892876
https://doi.org/10.1109/ijcnn55064.2022.9892876
In recent times, the detection of hate-speech, offensive, or abusive language in online media has become an important topic in NLP research due to the exponential growth of social media and the propagation of such messages, as well as their impact. M
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7d0cf8e2ef6deeeefa8f44c386767808
http://arxiv.org/abs/2205.14769
http://arxiv.org/abs/2205.14769
Publikováno v:
SemEval@ACL/IJCNLP
Reading is a complex process which requires proper understanding of texts in order to create coherent mental representations. However, comprehension problems may arise due to hard-to-understand sections, which can prove troublesome for readers, while
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0cd4ec158e7ae9afe5524439e2ea17a5
http://arxiv.org/abs/2104.06983
http://arxiv.org/abs/2104.06983
Publikováno v:
SemEval@ACL/IJCNLP
Detecting humor is a challenging task since words might share multiple valences and, depending on the context, the same words can be even used in offensive expressions. Neural network architectures based on Transformer obtain state-of-the-art results
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3fd30fbccb6e7daf530348ddff03f9d2
http://arxiv.org/abs/2104.06063
http://arxiv.org/abs/2104.06063
Publikováno v:
SemEval@ACL/IJCNLP
Extracting semantic information on measurements and counts is an important topic in terms of analyzing scientific discourses. The 8th task of SemEval-2021: Counts and Measurements (MeasEval) aimed to boost research in this direction by providing a ne
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::49b63e3bd8d365197c725f80fee40fae
http://arxiv.org/abs/2104.04549
http://arxiv.org/abs/2104.04549
Publikováno v:
SemEval@ACL/IJCNLP
The real-world impact of polarization and toxicity in the online sphere marked the end of 2020 and the beginning of this year in a negative way. Semeval-2021, Task 5 - Toxic Spans Detection is based on a novel annotation of a subset of the Jigsaw Uni
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::164892c9a765ee6651b189cac6944505
https://doi.org/10.18653/v1/2021.semeval-1.26
https://doi.org/10.18653/v1/2021.semeval-1.26
Publikováno v:
Proceedings of the Sixth Social Media Mining for Health (#SMM4H) Workshop and Shared Task.
This paper presents our contribution to the Social Media Mining for Health Applications Shared Task 2021. We addressed all the three subtasks of Task 1: Subtask A (classification of tweets containing adverse effects), Subtask B (extraction of text sp
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8774b9b0c49cc1d3377e28659768ddee
https://doi.org/10.18653/v1/2021.smm4h-1.7
https://doi.org/10.18653/v1/2021.smm4h-1.7
Publikováno v:
ICTAI
Complex Word Identification (CWI) is a task centered on detecting hard-to-understand words, or groups of words, in texts from different areas of expertise. The purpose of CWI is to highlight problematic structures that non-native speakers would usual
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::016bdc7b72084b56e38415159c2eb988
https://doi.org/10.1109/ictai50040.2020.00067
https://doi.org/10.1109/ictai50040.2020.00067