Language Technologies Institute School of Computer Science Carnegie Mellon Universityaravicha [at] cs [dot] cmu [dot] edu
My research interests lie broadly in robustly representing semantic meaning in text. I think a lot about how to estimate and improve model generalization in real-world scenarios, by ensuring models are capable of the kinds of reasoning necessary to understand natural language. This is also concerned with designing better NLP methodology- how to build high-quality datasets and evaluations that reflect meaningful progress towards language understanding.
For more about my work, please see my publications list.
Outside my research interests, I care a lot about helping women interested in getting started with, or furthering, research in natural language processing—feel free to email me! I would be particularly happy to be able to help students from marginalized groups, or less-privileged institutions.
|I will be speaking in a panel on "The Role of Active Privacy Management in a World Where the Consent Model Breaks Down" at CPDP 2020 in Brussels, Belgium.|
|I will be helping organize the OurCS workshop at CMU. If you are an undergraduate woman, please do consider attending! Funds for hotels and meals will be provided.|
|I will be spending the summer interning at MSR Montreal with Adam Trischler and Kaheer Suleman, working on teaching machines commonsense reasoning.|
|I will be attending ACL, SIGDIAL and YRRSDS 2018 in Melbourne. Ping me if you'd like to chat!|
|Our work, "Stress Test Evaluation for Natural Language Inference" was an Area Chair Favorite Paper at COLING 2018!|
|I will be at the Generalization in Deep Learning workshop at NAACL 2018. Ping me if you'd like to chat!|
|I will be starting my PhD at the Language Technologies Institute, Carnegie Mellon University in Fall 2018.|
|I am at the Machine Learning Summer School in Tubingen. Let me know if you'd like to meet up!|
|Our team was selected to participate in the Alexa Prize with a 100,000$ stipend and additional support from Amazon! Congratulations to all the selected teams.|
|Our work on "A Persistent Homology Approach to Document Clustering" won the best poster award in 10-701 (Introduction to Machine Learning (PhD)).|