Zobrazeno 1 - 10
of 32
pro vyhledávání: '"Konstantine Arkoudas"'
Autor:
Melanie A. Rubino, Nicolas Guenon des mesnards, Uday Shah, Nanjiang Jiang, Weiqi Sun and Konstantine Arkoudas
Publikováno v:
Proceedings of the Third Workshop on Deep Learning for Low-Resource Natural Language Processing.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::069e5f574bd0f06eaa133969a65d6b11
https://doi.org/10.18653/v1/2022.deeplo-1.6
https://doi.org/10.18653/v1/2022.deeplo-1.6
Task-oriented parsing (TOP) aims to convert natural language into machine-readable representations of specific tasks, such as setting an alarm. A popular approach to TOP is to apply seq2seq models to generate linearized parse trees. A more recent lin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::732bca8fe00c00947d9d8c2f0ce6acc9
Autor:
Victor Soto, Konstantine Arkoudas
Publikováno v:
NAACL-HLT (Industry Papers)
Recent advances in transfer learning have improved the performance of virtual assistants considerably. Nevertheless, creating sophisticated voice-enabled applications for new domains remains a challenge, and meager training data is often a key bottle
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::16cb8830a6b6d794e8c06040c93cba01
https://doi.org/10.18653/v1/2021.naacl-industry.36
https://doi.org/10.18653/v1/2021.naacl-industry.36
Publikováno v:
Machine Ethics and Robot Ethics ISBN: 9781003074991
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0b5a6b1a677c692711476ee5770e320d
https://doi.org/10.4324/9781003074991-27
https://doi.org/10.4324/9781003074991-27
Publikováno v:
COLING (Industry)
We present a neural model for paraphrasing and train it to generate delexicalized sentences. We achieve this by creating training data in which each input is paired with a number of reference paraphrases. These sets of reference paraphrases represent
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3c11ac2ff6e46d55825e387faa10c976
Autor:
Konstantine Arkoudas, Mohamed Yahya
Publikováno v:
CIKM
The Bloomberg Terminal has been a leading source of financial data and analytics for over 30 years. Through its thousands of functions, the Terminal allows its users to query and run analytics over a large array of data sources, including structured,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::24b1b7b4cd258df2d7c9f6cd0c4cb5c6
http://arxiv.org/abs/1906.09450
http://arxiv.org/abs/1906.09450
While sequence-to-sequence (seq2seq) models achieve state-of-the-art performance in many natural language processing tasks, they can be too slow for real-time applications. One performance bottleneck is predicting the most likely next token over a la
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::76480cda46ac23d898a903a013a807b3
Autor:
Konstantine Arkoudas, Mohamed Yahya
Publikováno v:
SIGIR
The Bloomberg Terminal is the leading source of information and news in the finance industry. Through hundreds of functions that provide access to a vast wealth of structured and semi-structured data, the terminal is able to satisfy a wide range of i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::515ac8a67a0f885c5637a7d0b6d165a0
https://doi.org/10.1145/3209978.3210204
https://doi.org/10.1145/3209978.3210204
Autor:
Keith Whittaker, Ritu Chadha, C. Jason Chiang, Daniel Apgar, Jason Perry, Konstantine Arkoudas
Publikováno v:
Computer Standards & Interfaces. 35:417-427
We have developed a translation system that maps sentences of Attempto Controlled English to predicates of many-sorted first-order logic, which can be directly imported into a logic-based policy management framework. Our translation achieves broader
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a7b14f2a7988f9a7781a900a625884ab
https://doi.org/10.1016/j.csi.2013.02.002
https://doi.org/10.1016/j.csi.2013.02.002
Publikováno v:
Artificial Intelligence. 173(15):1367-1405
We introduce Vivid, a domain-independent framework for mechanized heterogeneous reasoning that combines diagrammatic and symbolic representation and inference. The framework is presented in the form of a family of denotational proof languages (DPLs).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1c2030719c3b5911425d122de2b3f794