Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Emily Allaway"'
Publikováno v:
Computational Linguistics (2024)
Externí odkaz:
https://doaj.org/article/4b4eed82c1d74937a776448d17c09796
Autor:
Emily Allaway, Kathleen McKeown
Publikováno v:
Frontiers in Artificial Intelligence, Vol 5 (2023)
A major challenge in stance detection is the large (potentially infinite) and diverse set of stance topics. Collecting data for such a set is unrealistic due to both the expense of annotation and the continuous creation of new real-world topics (e.g.
Externí odkaz:
https://doaj.org/article/8a9a14a129364d74aed002a2ffffe624
Publikováno v:
NAACL-HLT
Stance detection on social media can help to identify and understand slanted news or commentary in everyday life. In this work, we propose a new model for zero-shot stance detection on Twitter that uses adversarial learning to generalize across topic
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4657a6ba0e8a260ec2a6262165f39393
http://arxiv.org/abs/2105.06603
http://arxiv.org/abs/2105.06603
Autor:
Sahil Jayaram, Emily Allaway
Publikováno v:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d508dd9b59188d2a403af924fd763e36
https://doi.org/10.18653/v1/2021.emnlp-main.450
https://doi.org/10.18653/v1/2021.emnlp-main.450
Autor:
Alicia Parrish, William Huang, Omar Agha, Soo-Hwan Lee, Nikita Nangia, Alexia Warstadt, Karmanya Aggarwal, Emily Allaway, Tal Linzen, Samuel R. Bowman
Many crowdsourced NLP datasets contain systematic gaps and biases that are identified only after data collection is complete. Identifying these issues from early data samples during crowdsourcing should make mitigation more efficient, especially when
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::686a1977165b9c1f5d821cf9b89793c2
Autor:
Kathleen R. McKeown, Emily Allaway
Publikováno v:
EMNLP (1)
Stance detection is an important component of understanding hidden influences in everyday life. Since there are thousands of potential topics to take a stance on, most with little to no training data, we focus on zero-shot stance detection: classifyi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fecfe508574e0479183ee9ae06f1da2f
http://arxiv.org/abs/2010.03640
http://arxiv.org/abs/2010.03640
Autor:
Kathleen R. McKeown, Emily Allaway
Publikováno v:
EACL
Ideological attitudes and stance are often expressed through subtle meanings of words and phrases. Understanding these connotations is critical to recognizing the cultural and emotional perspectives of the speaker. In this paper, we use distant label
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::db086d3ed5d935412afa58cbfeeb8709
Publikováno v:
COLING
General purpose relation extraction has recently seen considerable gains in part due to a massively data-intensive distant supervision technique from Soares et al. (2019) that produces state-of-the-art results across many benchmarks. In this work, we
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6737844f96fcc4ba8f46472a2ac8b927
https://doi.org/10.18653/v1/2020.coling-main.131
https://doi.org/10.18653/v1/2020.coling-main.131
Autor:
Maarten Sap, Hannah Rashkin, Emily Allaway, Chandra Bhagavatula, Noah A. Smith, Ronan Le Bras, Brendan Roof, Yejin Choi, Nicholas Lourie
Publikováno v:
AAAI
We present ATOMIC, an atlas of everyday commonsense reasoning, organized through 877k textual descriptions of inferential knowledge. Compared to existing resources that center around taxonomic knowledge, ATOMIC focuses on inferential knowledge organi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b927814025d19bd4afce622c3d89b529
Publikováno v:
ACL (1)
We investigate a new commonsense inference task: given an event described in a short free-form text ("X drinks coffee in the morning"), a system reasons about the likely intents ("X wants to stay awake") and reactions ("X feels alert") of the event's
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::52928a9c3c90b6954bec4686d979ba61