2 code implementations • EMNLP 2018 • Chris Kedzie, Kathleen McKeown, Hal Daume III
We carry out experiments with deep learning models of summarization across the domains of news, personal stories, meetings, and medical articles in order to understand how content selection is performed.
1 code implementation • WMT (EMNLP) 2020 • David Wan, Chris Kedzie, Faisal Ladhak, Marine Carpuat, Kathleen McKeown
In this paper, we present both autoregressive and non-autoregressive models for lexically constrained APE, demonstrating that our approach enables preservation of 95% of the terminologies and also improves translation quality on English-German benchmarks.
1 code implementation • WS 2019 • Chris Kedzie, Kathleen McKeown
Deep neural networks (DNN) are quickly becoming the de facto standard modeling method for many natural language generation (NLG) tasks.
1 code implementation • EMNLP 2018 • Serina Chang, Ruiqi Zhong, Ethan Adams, Fei-Tzin Lee, Siddharth Varia, Desmond Patton, William Frey, Chris Kedzie, Kathleen McKeown
Gang-involved youth in cities such as Chicago have increasingly turned to social media to post about their experiences and intents online.
1 code implementation • 8 Nov 2019 • Katy Gero, Chris Kedzie, Jonathan Reeve, Lydia Chilton
Despite the success of style transfer in image processing, it has seen limited progress in natural language generation.
no code implementations • 12 May 2016 • Chris Kedzie, Fernando Diaz, Kathleen McKeown
We present a system based on sequential decision making for the online summarization of massive document streams, such as those found on the web.
no code implementations • 23 Jul 2018 • Philipp Blandfort, Desmond Patton, William R. Frey, Svebor Karaman, Surabhi Bhargava, Fei-Tzin Lee, Siddharth Varia, Chris Kedzie, Michael B. Gaskell, Rossano Schifanella, Kathleen McKeown, Shih-Fu Chang
In this paper we partnered computer scientists with social work researchers, who have domain expertise in gang violence, to analyze how public tweets with images posted by youth who mention gang associations on Twitter can be leveraged to automatically detect psychosocial factors and conditions that could potentially assist social workers and violence outreach workers in prevention and early intervention programs.
no code implementations • WS 2019 • Katy Gero, Chris Kedzie, Jonathan Reeve, Lydia Chilton
Despite the success of style transfer in image processing, it has seen limited progress in natural language generation.
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.
no code implementations • 19 Oct 2020 • David Wan, Zhengping Jiang, Chris Kedzie, Elsbeth Turcan, Peter Bell, Kathleen McKeown
In this work, we focus on improving ASR output segmentation in the context of low-resource language speech-to-text translation.
no code implementations • EMNLP 2020 • Chris Kedzie, Kathleen McKeown
We study the degree to which neural sequence-to-sequence models exhibit fine-grained controllability when performing natural language generation from a meaning representation.
no code implementations • EACL 2021 • David Wan, Chris Kedzie, Faisal Ladhak, Elsbeth Turcan, Petra Galuščáková, Elena Zotkina, Zhengping Jiang, Peter Bell, Kathleen McKeown
Typical ASR systems segment the input audio into utterances using purely acoustic information, which may not resemble the sentence-like units that are expected by conventional machine translation (MT) systems for Spoken Language Translation.
no code implementations • ACL 2021 • Yanda Chen, Chris Kedzie, Suraj Nair, Petra Galuščáková, Rui Zhang, Douglas W. Oard, Kathleen McKeown
This paper proposes an approach to cross-language sentence selection in a low-resource setting.
no code implementations • 22 Oct 2021 • Katy Ilonka Gero, Chris Kedzie, Savvas Petridis, Lydia Chilton
Language models are known to produce vague and generic outputs.
no code implementations • 27 Nov 2021 • Fei-Tzin Lee, Chris Kedzie, Nakul Verma, Kathleen McKeown
Prior work in AMR-based summarization has automatically merged the individual sentence graphs into a document graph, but the method of merging and its effects on summary content selection have not been independently evaluated.
no code implementations • 28 Dec 2023 • Sky CH-Wang, Benjamin Van Durme, Jason Eisner, Chris Kedzie
We design probes trained on the internal representations of a transformer language model that are predictive of its hallucinatory behavior on in-context generation tasks.