Zobrazeno 1 - 10
of 22
pro vyhledávání: '"Agarwal, Oshin"'
Autor:
Demeter, David, Agarwal, Oshin, Igeri, Simon Ben, Sterbentz, Marko, Molino, Neil, Conroy, John M., Nenkova, Ani
Academic literature does not give much guidance on how to build the best possible customer-facing summarization system from existing research components. Here we present analyses to inform the selection of a system backbone from popular models; we fi
Externí odkaz:
http://arxiv.org/abs/2306.10555
Autor:
Agarwal, Oshin, Nenkova, Ani
Keeping the performance of language technologies optimal as time passes is of great practical interest. We study temporal effects on model performance on downstream language tasks, establishing a nuanced terminology for such discussion and identifyin
Externí odkaz:
http://arxiv.org/abs/2111.12790
The ability to quantify incivility online, in news and in congressional debates, is of great interest to political scientists. Computational tools for detecting online incivility for English are now fairly accessible and potentially could be applied
Externí odkaz:
http://arxiv.org/abs/2102.03671
Knowledge Graph Based Synthetic Corpus Generation for Knowledge-Enhanced Language Model Pre-training
Prior work on Data-To-Text Generation, the task of converting knowledge graph (KG) triples into natural text, focused on domain-specific benchmark datasets. In this paper, however, we verbalize the entire English Wikidata KG, and discuss the unique c
Externí odkaz:
http://arxiv.org/abs/2010.12688
Named Entity Recognition systems achieve remarkable performance on domains such as English news. It is natural to ask: What are these models actually learning to achieve this? Are they merely memorizing the names themselves? Or are they capable of in
Externí odkaz:
http://arxiv.org/abs/2004.04564
Named entity recognition systems perform well on standard datasets comprising English news. But given the paucity of data, it is difficult to draw conclusions about the robustness of systems with respect to recognizing a diverse set of entities. We p
Externí odkaz:
http://arxiv.org/abs/2004.04123
Autor:
Agarwal, Oshin, Bikel, Daniel M.
Entity Linking has two main open areas of research: 1) generate candidate entities without using alias tables and 2) generate more contextual representations for both mentions and entities. Recently, a solution has been proposed for the former as a d
Externí odkaz:
http://arxiv.org/abs/2004.03555
Modern NLP systems require high-quality annotated data. In specialized domains, expert annotations may be prohibitively expensive. An alternative is to rely on crowdsourcing to reduce costs at the risk of introducing noise. In this paper we demonstra
Externí odkaz:
http://arxiv.org/abs/1905.07791
People are often entities of interest in tasks such as search and information extraction. In these tasks, the goal is to find as much information as possible about people specified by their name. However in text, some of the references to people are
Externí odkaz:
http://arxiv.org/abs/1810.11476
Autor:
Agarwal, Oshin1 (AUTHOR) oagarwal@seas.upenn.edu, Yang, Yinfei2 (AUTHOR) yinfeiy@google.com, Wallace, Byron C.3 (AUTHOR) b.wallace@northeastern.edu, Nenkova, Ani1 (AUTHOR) nenkova@seas.upenn.edu
Publikováno v:
Computational Linguistics. Mar2021, Vol. 47 Issue 1, p117-140. 24p.
