Zobrazeno 1 - 10
of 11
pro vyhledávání: '"Ana Valeria Gonzalez"'
Publikováno v:
ACL/IJCNLP (Findings)
Publikováno v:
ACL/IJCNLP (Findings)
A myriad of explainability methods have been proposed in recent years, but there is little consensus on how to evaluate them. While automatic metrics allow for quick benchmarking, it isn't clear how such metrics reflect human interaction with explana
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::24e48fe8af6692b0fa5cc2e35c61e325
Publikováno v:
EMNLP (1)
Gonzalez, A V, Barrett, M J, Hvingelby, R, Søgaard, A & Webster, K 2020, Type B Reflexivization as an Unambiguous Testbed for Multilingual Multi-Task Gender Bias . in Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) . Association for Computational Linguistics, pp. 2637–2648, The 2020 Conference on Empirical Methods in Natural Language Processing, 16/11/2020 . https://doi.org/10.18653/v1/2020.emnlp-main.209
Gonzalez, A V, Barrett, M J, Hvingelby, R, Søgaard, A & Webster, K 2020, Type B Reflexivization as an Unambiguous Testbed for Multilingual Multi-Task Gender Bias . in Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) . Association for Computational Linguistics, pp. 2637–2648, The 2020 Conference on Empirical Methods in Natural Language Processing, 16/11/2020 . https://doi.org/10.18653/v1/2020.emnlp-main.209
The one-sided focus on English in previous studies of gender bias in NLP misses out on opportunities in other languages: English challenge datasets such as GAP and WinoGender highlight model preferences that are "hallucinatory", e.g., disambiguating
Publikováno v:
RANLP
Neural machine translation models have little inductive bias, which can be a disadvantage in low-resource scenarios. Neural models have to be trained on large amounts of data and have been shown to perform poorly when only limited data is available.
Publikováno v:
Gonzalez, A V, Augenstein, I & Søgaard, A 2020, ' Retrieval-based Goal-Oriented Dialogue Generation ', Paper presented at The 3rd NeurIPS workshop on Conversational AI, Vancouver, Canada, 14/12/2019 .
University of Copenhagen
University of Copenhagen
Most research on dialogue has focused either on dialogue generation for openended chit chat or on state tracking for goal-directed dialogue. In this work, we explore a hybrid approach to goal-oriented dialogue generation that combines retrieval from
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::12c67d051048651068f9c654a08409d7
http://arxiv.org/abs/1909.13717
http://arxiv.org/abs/1909.13717
Autor:
Joachim Bingel, Victor Petrén Bach Hansen, Ana Valeria Gonzalez, Pavel Budzianowski, Isabelle Augenstein, Anders Søgaard
Publikováno v:
University of Copenhagen
Task oriented dialogue systems rely heavily on specialized dialogue state tracking (DST) modules for dynamically predicting user intent throughout the conversation. State-of-the-art DST models are typically trained in a supervised manner from manual
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::79b09d2abe0f5dcc639ae1704946fee3
Autor:
Rahul Aralikatte, Chen Qiu, Ana Valeria Gonzalez, Anders B. Sandholm, Heather C. Lent, Daniel Herschcovich, Anders Søgaard, Michael Ringaard
Publikováno v:
Aralikatte, R, Lent, H, Gonzalez, A V, Herschcovich, D, Qiu, C, Sandholm, A, Ringaard, M & Søgaard, A 2019, Rewarding Coreference Resolvers for Being Consistent with World Knowledge . in Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) . Association for Computational Linguistics, pp. 1229-1235, Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), 01/11/2019 . https://doi.org/10.18653/v1/D19-1118
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
EMNLP/IJCNLP (1)
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
EMNLP/IJCNLP (1)
Unresolved coreference is a bottleneck for relation extraction, and high-quality coreference resolvers may produce an output that makes it a lot easier to extract knowledge triples. We show how to improve coreference resolvers by forwarding their inp
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1710950f3ecfbb39d53f8abea92b7767
https://curis.ku.dk/ws/files/239862441/OA_Rewarding_Coreference_Resolvers_for_Being_Consistent.pdf
https://curis.ku.dk/ws/files/239862441/OA_Rewarding_Coreference_Resolvers_for_Being_Consistent.pdf
Publikováno v:
González, A V, Petrén Bach Hansen, V, Bingel, J & Søgaard, A 2019, CoAStaL at SemEval-2019 Task 3 : Affect Classification in Dialogue using Attentive BiLSTMs . in Proceedings of the 13th International Workshop on Semantic Evaluation . Association for Computational Linguistics, pp. 169-174, 13th International Workshop on Semantic Evaluation (SemEval-2019), Minneapolis, United States, 06/06/2019 . https://doi.org/10.18653/v1/S19-2026
SemEval@NAACL-HLT
SemEval@NAACL-HLT
This work describes the system presented by the CoAStaL Natural Language Processing group at University of Copenhagen. The main system we present uses the same attention mechanism presented in (Yang et al., 2016). Our overall model architecture is al
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::dfd76c02edf5aead2f1cf882a5ff55d7
https://curis.ku.dk/portal/da/publications/coastal-at-semeval2019-task-3(62d88b81-1d3c-4194-8b07-bdf6e1911eb9).html
https://curis.ku.dk/portal/da/publications/coastal-at-semeval2019-task-3(62d88b81-1d3c-4194-8b07-bdf6e1911eb9).html
Autor:
Mariana Mazzini, Carlos Guillermo Catracchia, Ana Valeria Gonzalez Pereyra, M. A. Herrero, Verónica Maldonado May, M. Flores
Publikováno v:
Chilean journal of agricultural research v.70 n.2 2010
SciELO Chile
CONICYT Chile
instacron:CONICYT
SciELO Chile
CONICYT Chile
instacron:CONICYT
Grazing animals are exposed to heat stress and there should be conditions to facilitate water intake. Three experiments were carried out to determine the relationship between water intake, water temperature, and heat stress for Holstein pastured dair
Autor:
Gustavo Repetto, Luis A. Quesada-Allué, Alejandro Rabossi, Alicia Basso, Ana Valeria Gonzalez Pereyra, Natalia S. Forneris, Gabriel Otero
Publikováno v:
Comparative Cytogenetics
Vol.9, no.1
FAUBA Digital (UBA-FAUBA)
Universidad de Buenos Aires. Facultad de Agronomía
instacron:UBA-FAUBA
CONICET Digital (CONICET)
Consejo Nacional de Investigaciones Científicas y Técnicas
instacron:CONICET
Comparative Cytogenetics 9(1): 31-50
Vol. 9, no. 1
Comparative Cytogenetics, Vol 9, Iss 1, Pp 31-50 (2015)
Vol.9, no.1
FAUBA Digital (UBA-FAUBA)
Universidad de Buenos Aires. Facultad de Agronomía
instacron:UBA-FAUBA
CONICET Digital (CONICET)
Consejo Nacional de Investigaciones Científicas y Técnicas
instacron:CONICET
Comparative Cytogenetics 9(1): 31-50
Vol. 9, no. 1
Comparative Cytogenetics, Vol 9, Iss 1, Pp 31-50 (2015)
The horn fly, Haematobiairritans is an obligate haematophagous cosmopolitan insect pest. The first reports of attacks on livestock by Haematobiairritans in Argentina and Uruguay occurred in 1991, and since 1993 it is considered an economically import
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f5a9f2715d9473bf549a5e02650ef9aa
http://ri.agro.uba.ar/greenstone3/library/collection/arti/document/2015forneris
http://ri.agro.uba.ar/greenstone3/library/collection/arti/document/2015forneris