Zobrazeno 1 - 10
of 17
pro vyhledávání: '"Abhilasha Ravichander"'
Autor:
Yanai Elazar, Nora Kassner, Shauli Ravfogel, Abhilasha Ravichander, Eduard Hovy, Hinrich Schütze, Yoav Goldberg
Publikováno v:
Transactions of the Association for Computational Linguistics, Vol 9, Pp 1012-1031 (2021)
AbstractConsistency of a model—that is, the invariance of its behavior under meaning-preserving alternations in its input—is a highly desirable property in natural language processing. In this paper we study the question: Are Pretrained Language
Externí odkaz:
https://doaj.org/article/c20cd42e8e454ec39e1cb1d0b076a64a
Autor:
Ziqi Wang, Joel R. Reidenberg, Daniel Smullen, Abhilasha Ravichander, Peter Story, N. Cameron Russell, Sebastian Zimmeck, Norman Sadeh
Publikováno v:
Proceedings on Privacy Enhancing Technologies, Vol 2019, Iss 3, Pp 66-86 (2019)
The app economy is largely reliant on data collection as its primary revenue model. To comply with legal requirements, app developers are often obligated to notify users of their privacy practices in privacy policies. However, prior research has sugg
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0f7c71dc512440d160848eb3098923f3
https://doaj.org/article/7afb6a1d4c7c4f229f4abef16aa694b2
https://doaj.org/article/7afb6a1d4c7c4f229f4abef16aa694b2
Autor:
Dheeraj Rajagopal, Aman Madaan, Niket Tandon, Yiming Yang, Shrimai Prabhumoye, Abhilasha Ravichander, Peter Clark, Eduard H Hovy
Recently, models have been shown to predict the effects of unexpected situations, e.g., would cloudy skies help or hinder plant growth? Given a context, the goal of such situational reasoning is to elicit the consequences of a new situation (st) that
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5223a358d0ce8e09978dff242b3746c6
http://arxiv.org/abs/2104.00814
http://arxiv.org/abs/2104.00814
Publikováno v:
ACL/IJCNLP (1)
Privacy plays a crucial role in preserving democratic ideals and personal autonomy. The dominant legal approach to privacy in many jurisdictions is the “Notice and Choice” paradigm, where privacy policies are the primary instrument used to convey
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ef8993c00e1154cfe6c8f646bb054bbc
https://doi.org/10.18653/v1/2021.acl-long.319
https://doi.org/10.18653/v1/2021.acl-long.319
Autor:
Eduard Hovy, Yoav Goldberg, Yanai Elazar, Hinrich Schütze, Abhilasha Ravichander, Nora Kassner, Shauli Ravfogel
Publikováno v:
Transactions of the Association for Computational Linguistics
Consistency of a model -- that is, the invariance of its behavior under meaning-preserving alternations in its input -- is a highly desirable property in natural language processing. In this paper we study the question: Are Pretrained Language Models
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::be6863397a5a1d930de4d137ea335c62
Autor:
Alan W. Black, Siddharth Dalmia, Eduard Hovy, Florian Metze, Abhilasha Ravichander, Maria Ryskina
Publikováno v:
EACL
When Question-Answering (QA) systems are deployed in the real world, users query them through a variety of interfaces, such as speaking to voice assistants, typing questions into a search engine, or even translating questions to languages supported b
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::111fd7131612730326b02349fcabe08b
https://doi.org/10.18653/v1/2021.eacl-main.259
https://doi.org/10.18653/v1/2021.eacl-main.259
Publikováno v:
EACL
Although neural models have achieved impressive results on several NLP benchmarks, little is understood about the mechanisms they use to perform language tasks. Thus, much recent attention has been devoted to analyzing the sentence representations le
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8c7d192e6f02a9d2ff8c4002f0fde739
http://arxiv.org/abs/2005.00719
http://arxiv.org/abs/2005.00719
Autor:
Abhilasha Ravichander, Muthu Kumar Chandrasekaran, Anita de Waard, Michal Shmueli-Scheuer, Guy Feigenblat, Eduard Hovy
Publikováno v:
SDP@EMNLP
We present the results of three Shared Tasks held at the Scholarly Document Processing Workshop at EMNLP2020: CL-SciSumm, LaySumm and LongSumm. We report on each of the tasks, which received 18 submissions in total, with some submissions addressing t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::56ad396b904c4cf8ce94bdbaaa36dc69
https://doi.org/10.18653/v1/2020.sdp-1.24
https://doi.org/10.18653/v1/2020.sdp-1.24
Publikováno v:
EMNLP/IJCNLP (1)
Privacy policies are long and complex documents that are difficult for users to read and understand, and yet, they have legal effects on how user data is collected, managed and used. Ideally, we would like to empower users to inform themselves about
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2c5df793387498c67a03c113269ce663
https://doi.org/10.18653/v1/d19-1500
https://doi.org/10.18653/v1/d19-1500
Publikováno v:
ACL (1)
Word embeddings are now pervasive across NLP subfields as the de-facto method of forming text representataions. In this work, we show that existing embedding models are inadequate at constructing representations that capture salient aspects of mathem
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::40445cab6c74d5643a710a98bc8dcf4f
https://doi.org/10.18653/v1/p19-1329
https://doi.org/10.18653/v1/p19-1329