Zobrazeno 1 - 10
of 20
pro vyhledávání: '"Sandipan Dandapat"'
Autor:
Anirudh Srinivasan, Gauri Kholkar, Rahul Kejriwal, Tanuja Ganu, Sandipan Dandapat, Sunayana Sitaram, Balakrishnan Santhanam, Somak Aditya, Kalika Bali, Monojit Choudhury
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 36:13227-13229
Pre-trained multilingual language models are gaining popularity due to their cross-lingual zero-shot transfer ability, but these models do not perform equally well in all languages. Evaluating task-specific performance of a model in a large number of
Borrowing ideas from {\em Production functions} in micro-economics, in this paper we introduce a framework to systematically evaluate the performance and cost trade-offs between machine-translated and manually-created labelled data for task-specific
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::38cc51d358d2c8b1bb71783ebfb19657
http://arxiv.org/abs/2205.06350
http://arxiv.org/abs/2205.06350
Massively Multilingual Transformer based Language Models have been observed to be surprisingly effective on zero-shot transfer across languages, though the performance varies from language to language depending on the pivot language(s) used for fine-
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a120cc3d46f47827cfbb8b16786755c2
http://arxiv.org/abs/2205.06130
http://arxiv.org/abs/2205.06130
Few-shot transfer often shows substantial gain over zero-shot transfer~\cite{lauscher2020zero}, which is a practically useful trade-off between fully supervised and unsupervised learning approaches for multilingual pretrained model-based systems. Thi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2f467bd5e5fb8cdc96c5184d8f9b5b47
Autor:
Tanuja Ganu, Jahanvi Shah, Monojit Choudhury, Anurag Shukla, Kalika Bali, Sandipan Dandapat, Sebastin Santy, Vivek Seshadri
Publikováno v:
COMPASS
Seamless access to information in a rapidly globalizing world demands for availability of information across, ideally all but at the least a large number of, languages. Machine translation has been proposed as a technological solution to this complex
Publikováno v:
ACL
Code-switching is the use of more than one language in the same conversation or utterance. Recently, multilingual contextual embedding models, trained on multiple monolingual corpora, have shown promising results on cross-lingual and multilingual tas
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::de1e82356acfa3558f6494ce3471c8fc
Publikováno v:
EMNLP/IJCNLP (3)
In this paper, we demonstrate an Interactive Machine Translation interface, that assists human translators with on-the-fly hints and suggestions. This makes the end-to-end translation process faster, more efficient and creates high-quality translatio
Publikováno v:
ACL (1)
Getting manually labeled data in each domain is always an expensive and a time consuming task. Cross-domain sentiment analysis has emerged as a demanding concept where a labeled source domain facilitates a sentiment classifier for an unlabeled target
Autor:
Gayatri Bhat, Adithya Pratapa, Kalika Bali, Sunayana Sitaram, Sandipan Dandapat, Monojit Choudhury
Publikováno v:
ACL (1)
Training language models for Code-mixed (CM) language is known to be a difficult problem because of lack of data compounded by the increased confusability due to the presence of more than one language. We present a computational technique for creatio
Autor:
Sandipan Dandapat, Shreshtha Mundra, Shourya Roy, Manjira Sinha, Anirban Sen, Sandya Mannarswamy
Publikováno v:
Advances in Knowledge Discovery and Data Mining ISBN: 9783319575285
PAKDD (2)
PAKDD (2)
Contact center chats are textual conversations involving customers and agents on queries, issues, grievances etc. about products and services. Contact centers conduct periodic analysis of these chats to measure customer satisfaction, of which the cha
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c9c12e9f8138d06bc4f3e8c405819642
https://doi.org/10.1007/978-3-319-57529-2_27
https://doi.org/10.1007/978-3-319-57529-2_27