Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Anthony Ferritto"'
Publikováno v:
ACL/IJCNLP (2)
Existing models on Machine Reading Comprehension (MRC) require complex model architecture for effectively modeling long texts with paragraph representation and classification, thereby making inference computationally inefficient for production use. I
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::782281516ca6aeba54b5069fbe16ed1d
http://arxiv.org/abs/2105.03229
http://arxiv.org/abs/2105.03229
Autor:
Revanth Gangi Reddy, Radu Florian, Rong Zhang, Salim Roukos, Efsun Sarioglu Kayi, Vittorio Castelli, Todd Ward, Anthony Ferritto, Arafat Sultan, Avirup Sil
Publikováno v:
EMNLP (1)
Transfer learning techniques are particularly useful in NLP tasks where a sizable amount of high-quality annotated data is difficult to obtain. Current approaches directly adapt a pre-trained language model (LM) on in-domain text before fine-tuning t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6bf6235c5789b7932b5c6951a120710c
http://arxiv.org/abs/2010.05904
http://arxiv.org/abs/2010.05904
Autor:
Radu Florian, Sara Rosenthal, Rishav Chakravarti, Avi Sil, Mihaela A. Bornea, Anthony Ferritto, Kazi Saidul Hasan, Salim Roukos
Publikováno v:
COLING (Demonstrations)
This paper presents M-GAAMA, a Multilingual Question Answering architecture and demo system. This is the first multilingual machine reading comprehension (MRC) demo which is able to answer questions in over 100 languages. M-GAAMA answers questions fr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::eca1803ee8062dc086335e6fd80472d8
https://doi.org/10.18653/v1/2020.coling-demos.8
https://doi.org/10.18653/v1/2020.coling-demos.8
Autor:
Lin Pan, Avi Sil, Bhavani S. Iyer, Anthony Ferritto, Radu Florian, Rishav Chakravarti, Salim Roukos
Publikováno v:
COLING (Industry)
Industry-scale NLP systems necessitate two features. 1. Robustness: “zero-shot transfer learning” (ZSTL) performance has to be commendable and 2. Efficiency: systems have to train efficiently and respond instantaneously. In this paper, we introdu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a3096aa17370bd1e5a2b4ea1e9de47af
https://doi.org/10.18653/v1/2020.coling-industry.9
https://doi.org/10.18653/v1/2020.coling-industry.9
Autor:
Saswati Dana, Saurabh Pujar, Radu Florian, Dinesh Khandelwal, Todd Ward, Rong Zhang, Rishav Chakravarti, Lin Pan, Rosario A. Uceda-Sosa, John F. Pitrelli, Salim Roukos, Martin Franz, Anthony Ferritto, Cezar Pendus, Avirup Sil, Mohamed Nasr, J. Scott McCarley, Dinesh Garg, Vittorio Castelli, Mike McCawley, Andrzej Sakrajda
Publikováno v:
ACL
We introduce TechQA, a domain-adaptation question answering dataset for the technical support domain. The TechQA corpus highlights two real-world issues from the automated customer support domain. First, it contains actual questions posed by users on
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8da2b299f91f5ddc8c3eeb48fc926b06
https://doi.org/10.18653/v1/2020.acl-main.117
https://doi.org/10.18653/v1/2020.acl-main.117
Autor:
J. William Murdock, Lin Pan, Anthony Ferritto, Avirup Sil, Salim Roukos, Radu Florian, Rishav Chakravarti
Publikováno v:
EMNLP (Demos)
We introduce ARES (A Reading Comprehension Ensembling Service): a novel Machine Reading Comprehension (MRC) demonstration system which utilizes an ensemble of models to increase F1 by 2.3 points. While many of the top leaderboard submissions in popul
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b69427fe6f8853849e5f4778c47129b4
https://doi.org/10.18653/v1/2020.emnlp-demos.5
https://doi.org/10.18653/v1/2020.emnlp-demos.5
Autor:
Salim Roukos, Vittorio Castelli, Andrzej Sakrajda, Cezar Pendus, Lin Pan, J. William Murdock, Radu Florian, Rishav Chakravarti, Anthony Ferritto, Avirup Sil, Michael R. Glass
Publikováno v:
EMNLP/IJCNLP (3)
This paper introduces a novel orchestration framework, called CFO (COMPUTATION FLOW ORCHESTRATOR), for building, experimenting with, and deploying interactive NLP (Natural Language Processing) and IR (Information Retrieval) systems to production envi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::66f0492a5fe215404f198acce9944aed
http://arxiv.org/abs/1908.06121
http://arxiv.org/abs/1908.06121