Zobrazeno 1 - 10
of 46
pro vyhledávání: '"Ekaterina Shutova"'
Autor:
Rochelle Choenni, Ekaterina Shutova
Publikováno v:
Computational Linguistics, Vol 48, Iss 3 (2022)
Multilingual sentence encoders have seen much success in cross-lingual model transfer for downstream NLP tasks. The success of this transfer is, however, dependent on the model’s ability to encode the patterns of cross-lingual similarity and variat
Externí odkaz:
https://doaj.org/article/2b8cb6e381104f02940f817654711dae
Publikováno v:
Computational Linguistics, Vol 43, Iss 1 (2016)
Highly frequent in language and communication, metaphor represents a significant challenge for Natural Language Processing (NLP) applications. Computational work on metaphor has traditionally evolved around the use of hand-coded knowledge, making the
Externí odkaz:
https://doaj.org/article/f851d1ded5cd47c69348a61e12ed5bcd
Autor:
Danushka Bollegala, Ekaterina Shutova
Publikováno v:
PLoS ONE, Vol 8, Iss 9, p e74304 (2013)
Interpreting metaphor is a hard but important problem in natural language processing that has numerous applications. One way to address this task is by finding a paraphrase that can replace the metaphorically used word in a given context. This approa
Externí odkaz:
https://doaj.org/article/66d2f59100af42f6a42d0a593545913c
Publikováno v:
Computational Linguistics. :1-29
Large multilingual language models typically share their parameters across all languages, which enables cross-lingual task transfer, but learning can also be hindered when training updates from different languages are in conflict. In this article, we
Publikováno v:
AAAI
AAAI-20, IAAI-20, EAAI-20 proceedings: Thirty-Fourth AAAI Conference on Artificial Intelligence, Thirty-Second Conference on Innovative Applications of Artificial Intelligence, The Tenth Symposium on Educational Advances in Artificial Intelligence : February 7–12th, 2020, New York Hilton Midtown, New York, New York, USA, 5, 9090-9097
AAAI-20, IAAI-20, EAAI-20 proceedings: Thirty-Fourth AAAI Conference on Artificial Intelligence, Thirty-Second Conference on Innovative Applications of Artificial Intelligence, The Tenth Symposium on Educational Advances in Artificial Intelligence : February 7–12th, 2020, New York Hilton Midtown, New York, New York, USA, 5, 9090-9097
The lack of annotated data in many languages is a well-known challenge within the field of multilingual natural language processing (NLP). Therefore, many recent studies focus on zero-shot transfer learning and joint training across languages to over
Publikováno v:
Transactions of the Association of Computational Linguistics, 8, 231-246. MIT Press Journals
Transactions of the Association for Computational Linguistics, Vol 8, Pp 231-246 (2020)
Transactions of the Association for Computational Linguistics, Vol 8, Pp 231-246 (2020)
Recent years have seen a growing interest within the natural language processing (NLP) community in evaluating the ability of semantic models to capture human meaning representation in the brain. Existing research has mainly focused on applying seman
Publikováno v:
CHI Extended Abstracts
Metaphorical thinking acts as a bridge between embodiment and abstraction and helps to flexibly organize human knowledge and behavior. Yet its role in embodied human-computer interface de- sign, and its potential for supporting goals such as self-awa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::17eaf8a7b5c392589904a263e1befa04
https://research.gold.ac.uk/id/eprint/29800/1/DjokicShutovaFiebrink_CHI2021Interactivity.pdf
https://research.gold.ac.uk/id/eprint/29800/1/DjokicShutovaFiebrink_CHI2021Interactivity.pdf
Autor:
Anna Langedijk, Verna Dankers, Phillip Lippe, Sander Bos, Bryan Cardenas Guevara, Helen Yannakoudakis, Ekaterina Shutova
Meta-learning, or learning to learn, is a technique that can help to overcome resource scarcity in cross-lingual NLP problems, by enabling fast adaptation to new tasks. We apply model-agnostic meta-learning (MAML) to the task of cross-lingual depende
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6185a079390dfaae0b607c5625306563
http://arxiv.org/abs/2104.04736
http://arxiv.org/abs/2104.04736
Publikováno v:
EACL
The great majority of languages in the world are considered under-resourced for the successful application of deep learning methods. In this work, we propose a meta-learning approach to document classification in limited-resource setting and demonstr
Metaphors are widely used in political rhetoric as an effective framing device. While the efficacy of specific metaphors such as the war metaphor in political discourse has been documented before, those studies often rely on small number of hand-code
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f347fab11a4a718137655f6b215f6799