2 code implementations • 9 Sep 2018 • Dorottya Demszky, Kelvin Guu, Percy Liang
Existing datasets for natural language inference (NLI) have propelled research on language understanding.
1 code implementation • NAACL 2019 • Dorottya Demszky, Nikhil Garg, Rob Voigt, James Zou, Matthew Gentzkow, Jesse Shapiro, Dan Jurafsky
We provide an NLP framework to uncover four linguistic dimensions of political polarization in social media: topic choice, framing, affect and illocutionary force.
8 code implementations • ACL 2020 • Dorottya Demszky, Dana Movshovitz-Attias, Jeongwoo Ko, Alan Cowen, Gaurav Nemade, Sujith Ravi
Understanding emotion expressed in language has a wide range of applications, from building empathetic chatbots to detecting harmful online behavior.
Ranked #1 on Emotion Classification on GoEmotions
no code implementations • LREC 2020 • Zolt{\'a}n Kmetty, Veronika Vincze, Dorottya Demszky, Orsolya Ring, Bal{\'a}zs Nagy, Martina Katalin Szab{\'o}
P{\'a}rt{\'e}let was the official journal of the governing party during the Hungarian socialism from 1956 to 1989, hence it represents the direct political agitation and propaganda of the dictatorial system in question.
no code implementations • 16 Jun 2020 • Dorottya Demszky, László Kálmán, Dan Jurafsky, Beth Levin
We test the effect of lexical semantics on the ordering of verbs and their objects by grouping verbs into 11 semantic classes.
no code implementations • WS 2020 • Audrey Acken, Dorottya Demszky
In this study, we apply NLP methods to learn about the framing of the 2020 Democratic Presidential candidates in news media.
no code implementations • NAACL 2021 • Dorottya Demszky, Devyani Sharma, Jonathan H. Clark, Vinodkumar Prabhakaran, Jacob Eisenstein
Evaluation on a test set of 22 dialect features of Indian English demonstrates that these models learn to recognize many features with high accuracy, and that a few minimal pairs can be as effective for training as thousands of labeled examples.
1 code implementation • ACL 2021 • Dorottya Demszky, Jing Liu, Zid Mancenido, Julie Cohen, Heather Hill, Dan Jurafsky, Tatsunori Hashimoto
In conversation, uptake happens when a speaker builds on the contribution of their interlocutor by, for example, acknowledging, repeating or reformulating what they have said.
1 code implementation • NAACL (BEA) 2022 • Sterling Alic, Dorottya Demszky, Zid Mancenido, Jing Liu, Heather Hill, Dan Jurafsky
Responsive teaching is a highly effective strategy that promotes student learning.
1 code implementation • 21 Nov 2022 • Dorottya Demszky, Heather Hill
Classroom discourse is a core medium of instruction - analyzing it can provide a window into teaching and learning as well as driving the development of new tools for improving instruction.
no code implementations • 19 May 2023 • Jacob Eisenstein, Vinodkumar Prabhakaran, Clara Rivera, Dorottya Demszky, Devyani Sharma
We introduce a new dataset of conversational speech representing English from India, Nigeria, and the United States.
1 code implementation • 5 Jun 2023 • Rose E. Wang, Dorottya Demszky
In doing so, we propose three teacher coaching tasks for generative AI: (A) scoring transcript segments based on classroom observation instruments, (B) identifying highlights and missed opportunities for good instructional strategies, and (C) providing actionable suggestions for eliciting more student reasoning.
1 code implementation • 15 Jun 2023 • Rose E. Wang, Pawan Wirawarn, Noah Goodman, Dorottya Demszky
To overcome this challenge, we propose a set of best practices for using large language models (LLMs) to cheaply classify the comments at scale.
no code implementations • 12 Sep 2023 • Ahmed Adel Attia, Jing Liu, Wei Ai, Dorottya Demszky, Carol Espy-Wilson
Recent advancements in Automatic Speech Recognition (ASR) systems, exemplified by Whisper, have demonstrated the potential of these systems to approach human-level performance given sufficient data.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • 16 Oct 2023 • Kunal Handa, Margaret Clapper, Jessica Boyle, Rose E Wang, Diyi Yang, David S Yeager, Dorottya Demszky
Teachers' growth mindset supportive language (GMSL)--rhetoric emphasizing that one's skills can be improved over time--has been shown to significantly reduce disparities in academic achievement and enhance students' learning outcomes.
2 code implementations • 16 Oct 2023 • Rose E. Wang, Qingyang Zhang, Carly Robinson, Susanna Loeb, Dorottya Demszky
We evaluate state-of-the-art LLMs on our dataset and find that the expert's decision-making model is critical for LLMs to close the gap: responses from GPT4 with expert decisions (e. g., "simplify the problem") are +76% more preferred than without.
no code implementations • 2 Nov 2023 • Ashlee Kupor, Candice Morgan, Dorottya Demszky
To build scalable measures of instruction, we fine-tune RoBERTa and GPT models to identify five instructional talk moves inspired by accountable talk theory: adding on, connecting, eliciting, probing and revoicing students' ideas.
1 code implementation • 7 Feb 2024 • Rose E. Wang, Dorottya Demszky
We introduce Edu-ConvoKit, an open-source library designed to handle pre-processing, annotation and analysis of conversation data in education.
1 code implementation • 6 Mar 2024 • Rose E. Wang, Pawan Wirawarn, Omar Khattab, Noah Goodman, Dorottya Demszky
While information retrieval (IR) systems may provide answers for such user queries, they do not directly assist content creators -- such as lecturers who want to improve their content -- identify segments that _caused_ a user to ask those questions.