no code implementations • 24 May 2023 • Erica Cai, Brendan O'Connor
We consider dyadic zero-shot event extraction (EE) to identify actions between pairs of actors.
no code implementations • 27 Feb 2023 • Brendan O'Connor, Simon Dixon
We propose an alternative loss component in a loss function that is otherwise well-established among VC tasks, which has been shown to improve our model's SVC performance.
1 code implementation • 29 Dec 2022 • Ankita Gupta, Su Lin Blodgett, Justin H Gross, Brendan O'Connor
Participants in political discourse employ rhetorical strategies -- such as hedging, attributions, or denials -- to display varying degrees of belief commitments to claims proposed by themselves or others.
1 code implementation • 13 Oct 2022 • Ankita Gupta, Marzena Karpinska, Wenlong Zhao, Kalpesh Krishna, Jack Merullo, Luke Yeh, Mohit Iyyer, Brendan O'Connor
Large-scale, high-quality corpora are critical for advancing research in coreference resolution.
1 code implementation • FieldMatters (COLING) 2022 • Tessa Masis, Anissa Neal, Lisa Green, Brendan O'Connor
The study of language variation examines how language varies between and within different groups of speakers, shedding light on how we use language to construct identities and how social contexts affect language use.
no code implementations • EMNLP (CINLP) 2021 • Katherine A. Keith, Douglas Rice, Brendan O'Connor
Using observed language to understand interpersonal interactions is important in high-stakes decision making.
1 code implementation • Findings (ACL) 2021 • Andrew Halterman, Katherine A. Keith, Sheikh Muhammad Sarwar, Brendan O'Connor
Automated event extraction in social science applications often requires corpus-level evaluations: for example, aggregating text predictions across metadata and unbiased estimates of recall.
1 code implementation • EMNLP (NLP+CSS) 2020 • Dhruvil Gala, Mohammad Omar Khursheed, Hannah Lerner, Brendan O'Connor, Mohit Iyyer
Popular media reflects and reinforces societal biases through the use of tropes, which are narrative elements, such as archetypal characters and plot arcs, that occur frequently across media.
no code implementations • EMNLP (NLP+CSS) 2020 • Katherine A. Keith, Christoph Teichmann, Brendan O'Connor, Edgar Meij
We find for this application (1) some annotator disagreements of economic policy uncertainty can be attributed to ambiguity in language, and (2) switching measurements from keyword-matching to supervised machine learning classifiers results in low correlation, a concerning implication for the validity of the index.
no code implementations • ACL 2020 • Katherine A. Keith, David Jensen, Brendan O'Connor
For example, an individual's entire history of social media posts or the content of a news article could provide a rich measurement of multiple confounders.
1 code implementation • IJCNLP 2019 • Jack Merullo, Luke Yeh, Abram Handler, Alvin Grissom II, Brendan O'Connor, Mohit Iyyer
Sports broadcasters inject drama into play-by-play commentary by building team and player narratives through subjective analyses and anecdotes.
no code implementations • 19 Apr 2019 • Abram Handler, Brendan O'Connor
Search applications often display shortened sentences which must contain certain query terms and must fit within the space constraints of a user interface.
no code implementations • 1 Feb 2019 • Abram Handler, Brian Dillon, Brendan O'Connor
Recent approaches to English-language sentence compression rely on parallel corpora consisting of sentence-compression pairs.
no code implementations • 6 Sep 2018 • Johnny Tian-Zheng Wei, Khiem Pham, Brian Dillon, Brendan O'Connor
We explore whether such output belongs to a formal and realistic grammar, by employing the English Resource Grammar (ERG), a broad coverage, linguistically precise HPSG-based grammar of English.
1 code implementation • NAACL 2018 • Katherine A. Keith, Su Lin Blodgett, Brendan O'Connor
Dependency parsing research, which has made significant gains in recent years, typically focuses on improving the accuracy of single-tree predictions.
no code implementations • 6 Aug 2017 • Abram Handler, Brendan O'Connor
News archives are an invaluable primary source for placing current events in historical context.
no code implementations • EMNLP 2017 • Katherine A. Keith, Abram Handler, Michael Pinkham, Cara Magliozzi, Joshua McDuffie, Brendan O'Connor
We propose a new, socially-impactful task for natural language processing: from a news corpus, extract names of persons who have been killed by police.
no code implementations • 30 Jun 2017 • Su Lin Blodgett, Brendan O'Connor
We highlight an important frontier in algorithmic fairness: disparity in the quality of natural language processing algorithms when applied to language from authors of different social groups.
no code implementations • EMNLP 2016 • Su Lin Blodgett, Lisa Green, Brendan O'Connor
Though dialectal language is increasingly abundant on social media, few resources exist for developing NLP tools to handle such language.
no code implementations • 20 Jun 2016 • Abram Handler, Su Lin Blodgett, Brendan O'Connor
We explore two techniques which use color to make sense of statistical text models.
no code implementations • EMNLP 2015 • Khanh Nguyen, Brendan O'Connor
Many models in natural language processing define probabilistic distributions over linguistic structures.
no code implementations • 8 Oct 2013 • Brendan O'Connor, Michael Heilman
At the time of writing, the last released version was in March 2011.
no code implementations • 28 Jul 2013 • Brendan O'Connor
We develop a probabilistic latent-variable model to discover semantic frames---types of events and their participants---from corpora.
1 code implementation • WS 2013 • Nathan Schneider, Brendan O'Connor, Naomi Saphra, David Bamman, Manaal Faruqui, Noah A. Smith, Chris Dyer, Jason Baldridge
We introduce a framework for lightweight dependency syntax annotation.
no code implementations • 18 Oct 2012 • Jacob Eisenstein, Brendan O'Connor, Noah A. Smith, Eric P. Xing
Computer-mediated communication is driving fundamental changes in the nature of written language.