Next big challenges in core AI technology

Autor: Dengel, A., Etzioni, O., DeCario, N., Hoos, H.H., Li, F.F., Tsujii, J., Traverso, P., Braunschweig, B., Ghallab, M.

Publikováno v: Lecture Notes in Computer Science, 90-115. Cham: Springer
STARTPAGE=90;ENDPAGE=115;TITLE=Lecture Notes in Computer Science
Reflections on Artificial Intelligence for Humanity ISBN: 9783030691271
Reflections on Artificial Intelligence for Humanity

The field of AI is rich in scientific and technical challenges. Progress needs to be made in machine learning paradigms to make them more efficient and less data intensive. Bridges between data-based and model-based AI are needed in order to benefit

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bcefcb7b4727da87b2397f1096e5f5e3
https://hdl.handle.net/1887/3277262

The Importance of Being Recurrent for Modeling Hierarchical Structure

Autor: Tran, K., Bisazza, A., Monz, C., Riloff, E., Chiang, D., Hockenmaier, J., Tsujii, J.

Publikováno v: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing : EMNLP 2018: Brussels, Belgium, Oct. 31-Nov. 4
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing : EMNLP 2018
EMNLP

Recent work has shown that recurrent neural networks (RNNs) can implicitly capture and exploit hierarchical information when trained to solve common natural language processing tasks such as language modeling (Linzen et al., 2016) and neural machine

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c89018babd3caa9bd8bdbb7e385d8f6c
https://doi.org/10.18653/v1/D18-1503

BanditSum: Extractive Summarization as a Contextual Bandit

Autor: Dong, Y., Shen, Y., Crawford, E., van Hoof, H., Cheung, J.C.K., Riloff, E., Chiang, D., Hockenmaier, J., Tsujii, J.

Publikováno v: EMNLP
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing : EMNLP 2018: Brussels, Belgium, Oct. 31-Nov. 4, 3739-3748
STARTPAGE=3739;ENDPAGE=3748;TITLE=Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing : EMNLP 2018

In this work, we propose a novel method for training neural networks to perform single-document extractive summarization without heuristically-generated extractive labels. We call our approach BanditSum as it treats extractive summarization as a cont

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e2f5809ad603014a2715bea2a6939fea
https://hdl.handle.net/11245.1/a11de747-8c4c-442d-a268-d2d1dd43b396

Class-Based Language Modeling for Translating into Morphologically Rich Languages

Autor: Bisazza, A., Monz, C., Tsujii, J., Hajic, J.

Publikováno v: COLING 2014: the 25th International Conference on Computational Linguistics: proceedings of COLING 2014 : technical papers: August 23-29, 2014, Dublin, Ireland, 1918-1927
STARTPAGE=1918;ENDPAGE=1927;TITLE=COLING 2014: the 25th International Conference on Computational Linguistics

Class-based language modeling (LM) is a long-studied and effective approach to overcome data sparsity in the context of n-gram model training. In statistical machine translation (SMT), differ- ent forms of class-based LMs have been shown to improve b

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=narcis______::24d8ff829ba1cd71e610db85eb6900ff
https://dare.uva.nl/personal/pure/en/publications/classbased-language-modeling-for-translating-into-morphologically-rich-languages(77089f79-07ee-4c1e-a7c4-97b37d03a56b).html

Applying automatically parsed corpora to the study of language variation

Autor: Bloem, J., Versloot, A., Weerman, F., Tsujii, J., Hajic, J.

Publikováno v: COLING 2014: the 25th International Conference on Computational Linguistics: proceedings of COLING 2014 : technical papers: August 23-29, 2014, Dublin, Ireland, 1974-1984
STARTPAGE=1974;ENDPAGE=1984;TITLE=COLING 2014: the 25th International Conference on Computational Linguistics

In this work, we discuss the benefits of using automatically parsed corpora to study language variation. The study of language variation is an area of linguistics in which quantitative methods have been particularly successful. We argue that the larg

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=narcis______::1f286d4f2c386a95b45225219e7adc11
https://dare.uva.nl/personal/pure/en/publications/applying-automatically-parsed-corpora-to-the-study-of-language-variation(731e3bcb-f098-4305-b500-3513372eefd6).html