Abhilasha Ravichander

Language Technologies Institute
School of Computer Science
Carnegie Mellon University

aravicha [at] cs [dot] cmu [dot] edu
GHC 6114
Curriculum Vitae
Abhilasha Ravichander

Hi! I'm Abhilasha (/ɑ.bʰi.ˈla.ʃə/). I'm a Ph.D. student at Carnegie Mellon University, working in the Language Technologies Institute. I am very fortunate to be advised by Eduard Hovy and Norman Sadeh.

My research goal is to develop machines that are capable of understanding language at a human-level, and therefore can be useful to a variety of users, in a variety of scenarios. I think a lot about how to estimate and improve model generalization in real-world situations, 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.

I am also interested in exploring how NLP can help effect social change. Through my work at the Usable Privacy Policy Project, I am engaged in a multi-disciplinary effort to empower internet users to take back control of their privacy.

Outside my research interests, I also care a lot about helping students who identify with a minoritized gender identity, and who are 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 less-privileged institutions.

What's New

I will be interning at the Allen Institute of AI this summer, with Ana Marasović and Matt Gardner.
I was recognized as an outstanding reviewer at ACL 2020 and EMNLP 2020.
I started the NLP With Friends online seminar series, with my wonderful co-organizers Zeerak Waseem, Yanai Elazar and Liz Salesky.
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 lead a research team at 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, YRRSDS and SIGDIAL 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)).


(*) - Equal Contribution

Probing the Probing Paradigm: Does Probing Accuracy Entail Task Relevance?
Abhilasha Ravichander, Yonatan Belinkov, Eduard Hovy
16th Conference of the European Chapter of the Association for Computational Linguistics, (EACL 2021).
PDF Bib Code/Data Long Oral Conference

NoiseQA: Challenge Set Evaluation for User-Centric Question Answering
Abhilasha Ravichander, Siddharth Dalmia, Maria Ryskina, Florian Metze, Eduard Hovy, Alan W Black
16th Conference of the European Chapter of the Association for Computational Linguistics, (EACL 2021).
PDF Bib Code/Data Long Oral Conference Website

Measuring and Improving Consistency in Pretrained Language Models
Yanai Elazar, Nora Kassner, Shauli Ravfogel, Abhilasha Ravichander, Eduard Hovy, Hinrich Schütze, Yoav Goldberg
Transactions of the Association of Computational Linguistics, (TACL 2021).
PDF Bib Code/Data Long

Breaking Down Walls of Text: How Can NLP Benefit Consumer Privacy?
Abhilasha Ravichander, Alan W Black, Thomas Norton, Shomir Wilson and Norman Sadeh.
59th Annual Meeting of the Association for Computational Linguistics, (ACL 2021)
PDF Bib Long Conference

On the Systematicity of Probing Contextualized Word Representations: The Case of Hypernymy in BERT
Abhilasha Ravichander, Eduard Hovy, Kaheer Suleman, Adam Trischler, Jackie Chi Kit Cheung.
2020 Joint Conference on Lexical and Computational Semantics, (*SEM 2020).
PDF Bib Code/Data Long Oral Conference

EQUATE: A Benchmark Evaluation Framework for Quantitative Reasoning in Natural Language Inference
Abhilasha Ravichander*, Aakanksha Naik*, Carolyn Rose, Eduard Hovy
2019 Conference on Computational Natural Language Learning, (CoNLL 2019).
PDF Bib Code/Data Long Poster Conference

Question Answering for Privacy Policies: Combining Computational and Legal Perspectives
Abhilasha Ravichander, Alan W Black, Shomir Wilson, Thomas Norton and Norman Sadeh.
2019 Conference on Empirical Methods in Natural Language Processing, (EMNLP 2019)
PDF Bib Code/Data Long Poster Conference

Exploring Numeracy in Word Embeddings
Aakanksha Naik*, Abhilasha Ravichander*, Carolyn Rose, Eduard Hovy
57th Meeting of Association for Computational Linguistics, (ACL 2019).
PDF Bib Short Poster Conference

Evaluating How Global Privacy Principles Answer Consumers’ Questions About Mobile App Privacy.
Thomas Norton, Joel Reidenberg, Norman Sadeh and Abhilasha Ravichander
4th European Privacy Law Scholars Conference, (PLSC 2019).

Challenges in Automated Question Answering for Privacy Policies.
Abhilasha Ravichander, Alan Black, Eduard Hovy, Joel Reidenberg, N. Cameron Russell and Norman Sadeh
AAAI Spring Symposium Series, 2019
PDF Long

MAPS: Scaling Privacy Compliance Analysis to a Million Apps
Peter Story, Sebastian Zimmeck, Daniel Smullen, Abhilasha Ravichander, Ziqi Wang, Joel Reidenberg, N. Cameron Russell and Norman Sadeh
PETS 2019
PDF Bib Long Oral Conference

Stress Test Evaluation for Natural Language Inference     **Area Chair Favorite Paper**
Aakanksha Naik*, Abhilasha Ravichander*, Norman Sadeh, Carolyn Rose, Graham Neubig.
27th International Conference on Computational Linguistics, (COLING 2018).
PDF Bib Code/Data Long Oral Conference Website Slides

An Empirical Study of Self-Disclosure in Spoken Dialogue Systems
Abhilasha Ravichander, Alan Black.
19th Annual SIGdial Meeting on Discourse and Dialogue, (SIGDIAL 2018).
PDF Bib Long Oral Conference

Does the Geometry of Word Embeddings Help Document Classification? A Case Study on Persistent Homology-Based Representations
Paul Michel*, Abhilasha Ravichander*, Shruti Rijhwani*.
Workshop on Representation Learning For NLP, Association for Computational Linguistics, 2017 (ACL 2017).
PDF Bib Poster Short

Preserving Intermediate Objectives: One Simple Trick to Improve Learning for Hierarchical Models
Abhilasha Ravichander*, Shruti Rijhwani*, Rajat Kulshreshtha*, Chirag Nagpal, Tadas Baltruˇsaitis, Louis-Phillipe Morency.
arXiv. PDF Bib

How Would You Say It? Eliciting Lexically Diverse Data for Supervised Semantic Parsing
Abhilasha Ravichander*, Thomas Manzini*, Matthias Grabmair, Jonathan Francis, Graham Neubig, Eric Nyberg.
18th Annual SIGdial Meeting on Discourse and Dialogue, (SIGDIAL 2017).
PDF Bib Code/Data Long Poster Conference

Technical Reports

1. Helping Users Understand Privacy Notices with Automated Question Answering Functionality: An Exploratory Study
Kanthashree Mysore Sathyendra, Abhilasha Ravichander, Peter Garth Story, Alan W Black, Norman Sadeh
Carnegie Mellon University Technical Report CMU-LTI-17-005, Dec 2017 [PDF]

2. Building CMU Magnus from User Feedback
Shrimai Prabhumoye*, Fadi Botros*, Khyathi Chandu*, Samridhi Choudhary*, Esha Keni*, Chaitanya Malaviya*, Thomas Manzini*, Rama Pasumarthi*, Shivani Poddar*, Abhilasha Ravichander*, Zhou Yu, Alan Black.
Alexa Prize Proceedings, 2017. [PDF]