NLQuAD: A Non-Factoid Long Question Answering Data Set

Autor: Soleimani, A., Monz, C., Worring, M., Merlo, P., Tiedemann, J., Tsarfaty, R.

Publikováno v: The 16th Conference of the European Chapter of the Association for Computational Linguistics: EACL 2021 : proceedings of the conference : April 19-23, 2021, 1245-1255
STARTPAGE=1245;ENDPAGE=1255;TITLE=The 16th Conference of the European Chapter of the Association for Computational Linguistics
EACL

We introduce NLQuAD, the first data set with baseline methods for non-factoid long question answering, a task requiring document-level language understanding. In contrast to existing span detection question answering data sets, NLQuAD has non-factoid

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d490360e8081ef1b42be63cf542d42ae
https://dare.uva.nl/personal/pure/en/publications/nlquad-a-nonfactoid-long-question-answering-data-set(47e0fbdb-d2ef-431f-9c7b-99a61594ef35).html

Language Modelling as a Multi-Task Problem

Autor: Weber, L., Jumelet, J., Bruni, E., Hupkes, D., Merlo, P., Tiedemann, J., Tsarfaty, R.

Publikováno v: The 16th Conference of the European Chapter of the Association for Computational Linguistics: EACL 2021 : proceedings of the conference : April 19-23, 2021
The 16th Conference of the European Chapter of the Association for Computational Linguistics
EACL

In this paper, we propose to study language modelling as a multi-task problem, bringing together three strands of research: multi-task learning, linguistics, and interpretability. Based on hypotheses derived from linguistic theory, we investigate whe

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e28c3db30b3ccbb73b71054011955087
https://dare.uva.nl/personal/pure/en/publications/language-modelling-as-a-multitask-problem(d8da817d-e365-464d-831f-cf637e7d282a).html

CoNLL-UL: Universal Morphological Lattices for Universal Dependency Parsing

Autor: More, A., Çetinoglu, Ö, Çöltekin, Ç, Habash, N., Sagot, B., Seddah, D., Dima Taji, Tsarfaty, R.

Publikováno v: 11th Language Resources and Evaluation Conference
11th Language Resources and Evaluation Conference, May 2018, Miyazaki, Japan
11th Language Resources and Evaluation Conference, May 2018, Miyazaki, Japan. 2018, 〈http://lrec2018.lrec-conf.org〉
Scopus-Elsevier

International audience; Following the development of the universal dependencies (UD) framework and the CoNLL 2017 Shared Task on end-to-end UD parsing, we address the need for a universal representation of morphological analysis which on the one hand

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::83a5b1a8469f8aec1118ff6a2f5d56f6
https://inria.hal.science/hal-01786125

Data-driven broad-coverage grammars for opinionated natural language generation (ONLG)

Autor: Cagan, T., Frank, S.L., Tsarfaty, R., Barzilay, R., Kan, M.-Y.

Publikováno v: Barzilay, R.; Kan, M.-Y. (ed.), Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Vol. 1: Long Papers), pp. 1331-1341
Barzilay, R.; Kan, M.-Y. (ed.), Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Vol. 1: Long Papers), 1331-1341. Vancouver, Canada : Association for Computational Linguistics
STARTPAGE=1331;ENDPAGE=1341;TITLE=Barzilay, R.; Kan, M.-Y. (ed.), Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Vol. 1: Long Papers)
ACL (1)

Opinionated Natural Language Generation (ONLG) is a new, challenging, task that aims to automatically generate human-like, subjective, responses to opinionated articles online. We present a data-driven architecture for ONLG that generates subjective

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7c3b9f23f39ff2fba0251ac29e42513e
https://hdl.handle.net/2066/179462

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.