Výsledky vyhledávání

Rethinking Supervised Learning and Reinforcement Learning in Task-Oriented Dialogue Systems

Autor: Li, Z., Kiseleva, J., de Rijke, M., Cohn, T., He, Y., Liu, Y.

Publikováno v: EMNLP (Findings)
Findings of the Association for Computational Linguistics. Findings of ACL: EMNLP 2020: 16-20 November, 2020
Findings of the Association for Computational Linguistics. Findings of ACL: EMNLP 2020

Dialogue policy learning for task-oriented dialogue systems has enjoyed great progress recently mostly through employing reinforcement learning methods. However, these approaches have become very sophisticated. It is time to re-evaluate it. Are we re

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e8b7042a7d5c695e243b4174c22c9a9d
https://doi.org/10.18653/v1/2020.findings-emnlp.316

Zobrazit plný text záznamu

Guided Dialogue Policy Learning without Adversarial Learning in the Loop

Autor: Li, Z., Lee, S., Peng, B., Li, J., Kiseleva, J., de Rijke, M., Shayandeh, S., Gao, J., Cohn, T., He, Y., Liu, Y.

Publikováno v: Findings of the Association for Computational Linguistics. Findings of ACL: EMNLP 2020: 16-20 November, 2020
Findings of the Association for Computational Linguistics. Findings of ACL: EMNLP 2020
EMNLP (Findings)

Reinforcement learning methods have emerged as a popular choice for training an efficient and effective dialogue policy. However, these methods suffer from sparse and unstable reward signals returned by a user simulator only when a dialogue finishes.

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::557a8ee72818aab19d2ba827522e8382
https://doi.org/10.18653/v1/2020.findings-emnlp.209

Zobrazit plný text záznamu

Generating Image Descriptions via Sequential Cross-Modal Alignment Guided by Human Gaze

Autor: Takmaz, E., Pezzelle, S., Beinborn, L., Fernández, R., Webber, B., Cohn, T., He, Y., Liu, Y.

Publikováno v: Takmaz, E, Pezzelle, S, Beinborn, L & Fernández, R 2020, Generating Image Descriptions via Sequential Cross-Modal Alignment Guided by Human Gaze . in Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) . Association for Computational Linguistics, pp. 4664-4677 . https://doi.org/10.18653/v1/2020.emnlp-main.377
EMNLP (1)
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
2020 Conference on Empirical Methods in Natural Language Processing: EMNLP 2020 : proceedings of the conference : November 16-20, 2020
2020 Conference on Empirical Methods in Natural Language Processing
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), 4664-4677
STARTPAGE=4664;ENDPAGE=4677;TITLE=Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

When speakers describe an image, they tend to look at objects before mentioning them. In this paper, we investigate such sequential cross-modal alignment by modelling the image description generation process computationally. We take as our starting p

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0de5296d4ab58b0425a667f2c4e05b8f
https://doi.org/10.18653/v1/2020.emnlp-main.377

Zobrazit plný text záznamu

Understanding the Mechanics of SPIGOT: Surrogate Gradients for Latent Structure Learning

Autor: Mihaylova, T., Niculae, V., Martins, A.F.T., Webber, B., Cohn, T., He, Y., Liu, Y.

Publikováno v: 2020 Conference on Empirical Methods in Natural Language Processing: EMNLP 2020 : proceedings of the conference : November 16-20, 2020
2020 Conference on Empirical Methods in Natural Language Processing

Latent structure models are a powerful tool for modeling language data: they can mitigate the error propagation and annotation bottleneck in pipeline systems, while simultaneously uncovering linguistic insights about the data. One challenge with end-

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=narcis______::b638a7c1eb6edad054b1b152e2f271ec
https://dare.uva.nl/personal/pure/en/publications/understanding-the-mechanics-of-spigot-surrogate-gradients-for-latent-structure-learning(49c73d18-27f0-41d6-bac5-668d02ad7910).html

Zobrazit plný text záznamu

Learning to Learn to Disambiguate: Meta-Learning for Few-Shot Word Sense Disambiguation

Autor: Holla, N., Mishra, P., Yannakoudakis, H., Shutova, E., Cohn, T., He, Y., Liu, Y.

Publikováno v: Findings of the Association for Computational Linguistics : Findings of ACL: EMNLP 2020: 16-20 November, 2020, 4517-4533
STARTPAGE=4517;ENDPAGE=4533;TITLE=Findings of the Association for Computational Linguistics : Findings of ACL: EMNLP 2020
EMNLP (Findings)

The success of deep learning methods hinges on the availability of large training datasets annotated for the task of interest. In contrast to human intelligence, these methods lack versatility and struggle to learn and adapt quickly to new tasks, whe

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5ef80ee19b065b5dcd692e8d3e64b31f
https://hdl.handle.net/11245.1/f76f0533-0131-48b7-9e0a-b92655fc1c4c

Zobrazit plný text záznamu

Be Different to Be Better!

Autor: Pezzelle, S., Greco, C., Gandolfi, G., Gualdoni, E., Bernardi, R., Cohn, T., He, Y., Liu, Y.

Publikováno v: Findings of the Association for Computational Linguistics : Findings of ACL: EMNLP 2020: 16-20 November, 2020, 2751-2767
STARTPAGE=2751;ENDPAGE=2767;TITLE=Findings of the Association for Computational Linguistics : Findings of ACL: EMNLP 2020
Findings of the Association for Computational Linguistics: EMNLP 2020
EMNLP (Findings)

This paper introduces BD2BB, a novel language and vision benchmark that requires multimodal models combine complementary information from the two modalities. Recently, impressive progress has been made to develop universal multimodal encoders suitabl

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::849395fbcc81a7abaaa24425f2265fea
https://doi.org/10.18653/v1/2020.findings-emnlp.248

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání