no code implementations • LREC 2020 • David Wan, Zhengping Jiang, Chris Kedzie, Elsbeth Turcan, Peter Bell, Kathy Mckeown
In this work, we focus on improving ASR output segmentation in the context of low-resource language speech-to-text translation.
1 code implementation • IJCNLP 2019 • Tuhin Chakrabarty, Christopher Hidey, Smaranda Muresan, Kathy Mckeown, Alyssa Hwang
Our approach for relation prediction uses contextual information in terms of fine-tuning a pre-trained language model and leveraging discourse relations based on Rhetorical Structure Theory.
1 code implementation • IJCNLP 2019 • Ruiqi Zhong, Yanda Chen, Desmond Patton, Charlotte Selous, Kathy Mckeown
Gang-involved youth in cities such as Chicago sometimes post on social media to express their aggression towards rival gangs and previous research has demonstrated that a deep learning approach can predict aggression and loss in posts.
no code implementations • ACL 2019 • Jessica Ouyang, Kathy Mckeown
We present a monolingual alignment system for long, sentence- or clause-level alignments, and demonstrate that systems designed for word- or short phrase-based alignment are ill-suited for these longer alignments.
no code implementations • NAACL 2019 • Jessica Ouyang, Boya Song, Kathy Mckeown
We present a robust neural abstractive summarization system for cross-lingual summarization.
1 code implementation • NAACL 2019 • Christopher Hidey, Kathy Mckeown
Understanding contrastive opinions is a key component of argument generation.
no code implementations • WS 2019 • Fei-Tzin Lee, Derrick Hull, Jacob Levine, Bonnie Ray, Kathy McKeown
We propose to apply dialogue act classification to therapy transcripts, using a therapy-specific labeling scheme, in order to gain a high-level understanding of the flow of conversation in therapy sessions.
no code implementations • WS 2017 • Christopher Hidey, Elena Musi, Alyssa Hwang, Smar Muresan, a, Kathy Mckeown
Argumentative text has been analyzed both theoretically and computationally in terms of argumentative structure that consists of argument components (e. g., claims, premises) and their argumentative relations (e. g., support, attack).
no code implementations • EACL 2017 • Jessica Ouyang, Serina Chang, Kathy Mckeown
We present an iterative annotation process for producing aligned, parallel corpora of abstractive and extractive summaries for narrative.
no code implementations • LREC 2014 • Jessica Ouyang, Kathy Mckeown
Using this corpus, we explore the correspondence between LabovÂ’s elements of narrative structure and the implicit discourse relations of the Penn Discourse Treebank, and we construct a mapping between the elements of narrative structure and the discourse relation classes of the PDTB.