no code implementations • Findings (ACL) 2022 • Zihan Wang, Jiuxiang Gu, Jason Kuen, Handong Zhao, Vlad Morariu, Ruiyi Zhang, Ani Nenkova, Tong Sun, Jingbo Shang
We present a comprehensive study of sparse attention patterns in Transformer models.
no code implementations • 22 Apr 2022 • Jiuxiang Gu, Jason Kuen, Vlad I. Morariu, Handong Zhao, Nikolaos Barmpalios, Rajiv Jain, Ani Nenkova, Tong Sun
Document intelligence automates the extraction of information from documents and supports many business applications.
no code implementations • NeurIPS 2021 • Jiuxiang Gu, Jason Kuen, Vlad Morariu, Handong Zhao, Rajiv Jain, Nikolaos Barmpalios, Ani Nenkova, Tong Sun
Document intelligence automates the extraction of information from documents and supports many business applications.
no code implementations • 24 Nov 2021 • Oshin Agarwal, Ani Nenkova
We present a set of experiments with systems powered by large neural pretrained representations for English to demonstrate that {\em temporal model deterioration} is not as big a concern, with some models in fact improving when tested on data drawn from a later time period.
no code implementations • EACL 2021 • Anushree Hede, Oshin Agarwal, Linda Lu, Diana C. Mutz, Ani Nenkova
The ability to quantify incivility online, in news and in congressional debates, is of great interest to political scientists.
no code implementations • 7 Oct 2020 • Benjamin E. Nye, Jay DeYoung, Eric Lehman, Ani Nenkova, Iain J. Marshall, Byron C. Wallace
Here we consider the end-to-end task of both (a) extracting treatments and outcomes from full-text articles describing clinical trials (entity identification) and, (b) inferring the reported results for the former with respect to the latter (relation extraction).
1 code implementation • ACL 2020 • Benjamin E. Nye, Ani Nenkova, Iain J. Marshall, Byron C. Wallace
We apply the system at scale to all reports of randomized controlled trials indexed in MEDLINE, powering the automatic generation of evidence maps, which provide a global view of the efficacy of different interventions combining data from all relevant clinical trials on a topic.
no code implementations • CL (ACL) 2021 • Oshin Agarwal, Yinfei Yang, Byron C. Wallace, Ani Nenkova
We examine these questions by contrasting the performance of several variants of LSTM-CRF architectures for named entity recognition, with some provided only representations of the context as features.
1 code implementation • 8 Apr 2020 • Oshin Agarwal, Yinfei Yang, Byron C. Wallace, Ani Nenkova
We propose a method for auditing the in-domain robustness of systems, focusing specifically on differences in performance due to the national origin of entities.
no code implementations • IJCNLP 2019 • Simeng Sun, Ani Nenkova
ROUGE is widely used to automatically evaluate summarization systems.
no code implementations • NAACL 2019 • Rushab Munot, Ani Nenkova
It has been established that the performance of speech recognition systems depends on multiple factors including the lexical content, speaker identity and dialect.
no code implementations • WS 2019 • Oshin Agarwal, Sanjay Subramanian, Ani Nenkova, Dan Roth
It is therefore important that coreference resolution systems are able to link these different types of mentions to the correct entity name.
no code implementations • WS 2019 • Soham Parikh, Elizabeth Conrad, Oshin Agarwal, Iain Marshall, Byron Wallace, Ani Nenkova
Typical information needs, such as retrieving a full list of medical interventions for a given condition, or finding the reported efficacy of a particular treatment with respect to a specific outcome of interest cannot be straightforwardly posed in typical text-box search.
no code implementations • WS 2019 • Simeng Sun, Ori Shapira, Ido Dagan, Ani Nenkova
We show that plain ROUGE F1 scores are not ideal for comparing current neural systems which on average produce different lengths.
1 code implementation • SEMEVAL 2019 • Oshin Agarwal, Funda Durup{\i}nar, Norman I. Badler, Ani Nenkova
Word representations trained on text reproduce human implicit bias related to gender, race and age.
no code implementations • NAACL 2019 • Yinfei Yang, Oshin Agarwal, Chris Tar, Byron C. Wallace, Ani Nenkova
Experiments on a complex biomedical information extraction task using expert and lay annotators show that: (i) simply excluding from the training data instances predicted to be difficult yields a small boost in performance; (ii) using difficulty scores to weight instances during training provides further, consistent gains; (iii) assigning instances predicted to be difficult to domain experts is an effective strategy for task routing.
no code implementations • 26 Oct 2018 • Oshin Agarwal, Sanjay Subramanian, Ani Nenkova, Dan Roth
Here, we evaluate two state of the art coreference resolution systems on the subtask of Named Person Coreference, in which we are interested in identifying a person mentioned by name, along with all other mentions of the person, by pronoun or generic noun phrase.
no code implementations • EMNLP 2018 • Ori Shapira, David Gabay, Hadar Ronen, Judit Bar-Ilan, Yael Amsterdamer, Ani Nenkova, Ido Dagan
Practical summarization systems are expected to produce summaries of varying lengths, per user needs.
3 code implementations • ACL 2018 • Benjamin Nye, Junyi Jessy Li, Roma Patel, Yinfei Yang, Iain J. Marshall, Ani Nenkova, Byron C. Wallace
We present a corpus of 5, 000 richly annotated abstracts of medical articles describing clinical randomized controlled trials.
no code implementations • NAACL 2018 • Roma Patel, Yinfei Yang, Iain Marshall, Ani Nenkova, Byron Wallace
Medical professionals search the published literature by specifying the type of patients, the medical intervention(s) and the outcome measure(s) of interest.
1 code implementation • ACL 2017 • An Thanh Nguyen, Byron Wallace, Junyi Jessy Li, Ani Nenkova, Matthew Lease
Despite sequences being core to NLP, scant work has considered how to handle noisy sequence labels from multiple annotators for the same text.
no code implementations • 3 Apr 2017 • Yinfei Yang, Ani Nenkova
On manually annotated data, we compare the performance of domain-specific classifiers, trained on data only from a given news domain and a general classifier in which data from all four domains is pooled together.
no code implementations • EACL 2017 • Yinfei Yang, Forrest Sheng Bao, Ani Nenkova
We present a robust approach for detecting intrinsic sentence importance in news, by training on two corpora of document-summary pairs.
no code implementations • LREC 2016 • Junyi Jessy Li, Bridget O{'}Daniel, Yi Wu, Wenli Zhao, Ani Nenkova
We found that the lack of specificity distributes evenly among immediate prior context, long distance prior context and no prior context.
no code implementations • LREC 2014 • Kai Hong, John Conroy, Benoit Favre, Alex Kulesza, Hui Lin, Ani Nenkova
In the period since 2004, many novel sophisticated approaches for generic multi-document summarization have been developed.
no code implementations • TACL 2013 • Annie Louis, Ani Nenkova
We show that the distinction between great and typical articles can be detected fairly accurately, and that the entire spectrum of our features contribute to the distinction.
no code implementations • LREC 2012 • Annie Louis, Ani Nenkova
We present a corpus of sentences from news articles that are annotated as general or specific.