Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Berfin Aktaş"'
Autor:
Berfin Aktaş, Manfred Stede
Publikováno v:
Discours, Vol 31 (2022)
We investigate the variation in oral and written language in terms of anaphoric distance (i.e., the textual distance between anaphors and their antecedents), expanding corpus-based research with experimental evidence. Contrastive corpus studies demon
Externí odkaz:
https://doaj.org/article/31d8a4e53d7b403bbace5edfc44bdb15
Publikováno v:
EMNLP (Findings)
The performance of standard coreference resolution is known to drop significantly on Twitter texts. We improve the performance of the (Lee et al., 2018) system, which is originally trained on OntoNotes, by retraining on manually-annotated Twitter con
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::87e078293ab16af9884ad19eb7a86455
https://doi.org/10.18653/v1/2020.findings-emnlp.222
https://doi.org/10.18653/v1/2020.findings-emnlp.222
Autor:
Manfred Stede, Berfin Aktaş
Publikováno v:
COLING
In response to (i) inconclusive results in the literature as to the properties of coreference chains in written versus spoken language, and (ii) a general lack of work on automatic coreference resolution on both spoken language and social media, we u
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f0b83eedb63039d6c0b6ac08154ba84a
https://doi.org/10.18653/v1/2020.coling-main.508
https://doi.org/10.18653/v1/2020.coling-main.508
Publikováno v:
Proceedings of the Workshop on Discourse Relation Parsing and Treebanking 2019.
We introduce our pilot study applying PDTB-style annotation to Twitter conversations. Lexically grounded coherence annotation for Twitter threads will enable detailed investigations of the discourse structure of conversations on social media. Here, w
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::650b4ef523c8f06b3756531dafbf5de1
https://doi.org/10.18653/v1/w19-2707
https://doi.org/10.18653/v1/w19-2707
Publikováno v:
Text, Speech, and Dialogue ISBN: 9783030279462
TSD
TSD
The OntoNotes corpus is widely used for training and testing coreference resolution systems, but only little attention has so far been given to the differences between the different genres of language that the corpus is composed of. We are primarily
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::25958f221f9774743d3fae80a484c106
https://doi.org/10.1007/978-3-030-27947-9_15
https://doi.org/10.1007/978-3-030-27947-9_15
Publikováno v:
Proceedings of the First Workshop on Computational Models of Reference, Anaphora and Coreference.
We present a corpus study of pronominal anaphora on Twitter conversations. After outlining the specific features of this genre, with respect to reference resolution, we explain the construction of our corpus and the annotation steps. From this we der
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::df9c146542015c38568e3bc3233c9c13
https://doi.org/10.18653/v1/w18-0701
https://doi.org/10.18653/v1/w18-0701