Zobrazeno 1 - 10
of 27
pro vyhledávání: '"Erik Velldal"'
Publikováno v:
Northern European Journal of Language Technology. 8
This paper presents a qualitative analysis of the outputs of contextualized embedding-based methods for detecting diachronic semantic change. We also introduce an ensemble-method outperforming previously described contextualized approaches. This meth
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::23f36f7e12ec33a6c243edcbbae7f605
https://doi.org/10.3384/nejlt.2000-1533.2022.3478
https://doi.org/10.3384/nejlt.2000-1533.2022.3478
This paper demonstrates how a graph-based semantic parser can be applied to the task of structured sentiment analysis, directly predicting sentiment graphs from text. We advance the state of the art on 4 out of 5 standard benchmark sets. We release t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::62c31b7ea7b36e3ff9d1a1aca6d8c296
Publikováno v:
Proceedings of the 4th Workshop on Gender Bias in Natural Language Processing (GeBNLP).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2d4c0e097593740ddf4bdf1cfe7a56fa
https://doi.org/10.18653/v1/2022.gebnlp-1.21
https://doi.org/10.18653/v1/2022.gebnlp-1.21
Publikováno v:
ACL/IJCNLP (1)
Structured sentiment analysis attempts to extract full opinion tuples from a text, but over time this task has been subdivided into smaller and smaller sub-tasks, e,g,, target extraction or targeted polarity classification. We argue that this divisio
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f8eda53e70d795c28e7766038246afa4
http://arxiv.org/abs/2105.14504
http://arxiv.org/abs/2105.14504
Publikováno v:
Proceedings of the 3rd Workshop on Gender Bias in Natural Language Processing.
In this work we explore the effect of incorporating demographic metadata in a text classifier trained on top of a pre-trained transformer language model. More specifically, we add information about the gender of critics and book authors when classify
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ec75585a47228463056e4131647dc487
https://doi.org/10.18653/v1/2021.gebnlp-1.8
https://doi.org/10.18653/v1/2021.gebnlp-1.8
Publikováno v:
CBMI
Understanding, detecting, moderating and in extreme cases deleting hateful comments in online discussions and social media are well-known challenges. In this paper we present a dataset consisting of a total of around 30 000 sentences from around 10 0
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e2b604bde9398eb040c45d90a7cbb70f
https://hdl.handle.net/10642/8506
https://hdl.handle.net/10642/8506
Publikováno v:
RepL4NLP@ACL
This paper extends the task of probing sentence representations for linguistic insight in a multilingual domain. In doing so, we make two contributions: first, we provide datasets for multilingual probing, derived from Wikipedia, in five languages, v
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::71aa8846e1ce67031c89f34c7ba645ac
https://doi.org/10.18653/v1/w19-4318
https://doi.org/10.18653/v1/w19-4318
Publikováno v:
BlackboxNLP@ACL
Neural methods for SA have led to quantitative improvements over previous approaches, but these advances are not always accompanied with a thorough analysis of the qualitative differences. Therefore, it is not clear what outstanding conceptual challe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::95db4df528fd7e958ef23c93552d7469
http://hdl.handle.net/10852/74129
http://hdl.handle.net/10852/74129
We measure the intensity of diachronic semantic shifts in adjectives in English, Norwegian and Russian across 5 decades. This is done in order to test the hypothesis that evaluative adjectives are more prone to temporal semantic change. To this end,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0891862c5a75f24a24741bd025449909
http://hdl.handle.net/10852/73976
http://hdl.handle.net/10852/73976
We extend the well-known word analogy task to a one-to-X formulation, including one-to-none cases, when no correct answer exists. The task is cast as a relation discovery problem and applied to historical armed conflicts datasets, attempting to predi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ed92c69e949e709ab6bd521113b2bc57