Frustrated, Polite, or Formal: Quantifying Feelings and Tone in Email (2018 · 40 citations)
The paper asks whether frustration, a fine-grained affect common in workplace exchanges, can be measured from email text alone.
LynyrdSkynyrd at WNUT-2020 Task 2: Semi-Supervised Learning for Identification of Informative COVID-19 English Tweets (2020 · 4 citations)
The paper presents a system for the W-NUT 2020 shared task, which asks whether an English COVID-19 tweet is "informative," meaning it reports cases, deaths, recoveries, suspected infections, or the locations and travel of patients.
RAFFLES: Reasoning-based Attribution of Faults for LLM Systems (2026 · 1 citation)
Multi-step LLM systems such as agent pipelines and long reasoning chains are hard to debug. One early mistake can cascade into failure, and locating it usually requires slow manual inspection. Single-pass LLM-as-a-judge evaluators also struggle with long trajectories. The authors, from Capital One, propose RAFFLES…

All works

4 works of theirs in our library, the most cited first; 3 with a page here, the others link their original until we summarise them.

Frustrated, Polite, or Formal: Quantifying Feelings and Tone in EmailInternational Conference on Computational Linguistics (COLING)Niyati Chhaya, Kushal Chawla, Tanya Goyal, et al.2018 · 40 citations
Generating Formality-Tuned Summaries Using Input-Dependent Rewards ↗Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL) · no summary yetKushal Chawla, Balaji Vasan Srinivasan, Niyati Chhaya2019 · 5 citations
LynyrdSkynyrd at WNUT-2020 Task 2: Semi-Supervised Learning for Identification of Informative COVID-19 English TweetsWorkshop on Noisy User-generated TextAbhilasha Sancheti, Kushal Chawla, Gaurav Verma2020 · 4 citations
RAFFLES: Reasoning-based Attribution of Faults for LLM SystemsConference of the European Chapter of the Association for Computational Linguistics (EACL)Chenyang Zhu, Spencer Hong, Jingyu Wu, et al.2026 · 1 citation

Co-authors here

3 co-authors with a page, the most papers together first.

Where their works here were published, the most works first, with the editions of those that have a page.

Papers of our library cite their works 20 times (of the 149,439 papers whose bibliographies we read); 3 citing papers with a page here →.

Updated 31 October 2026