Welcome to my personal site! I am a postdoctoral researcher at the Allen Institute for AI, or AI2 for short, working on the Aristo team. I am also affiliated with Prof. Hanna Hajishirzi’s group at the University of Washington. I received my PhD from Georgia Tech in 2022, advised by Prof. Mark Riedl.
My research interest is interpretability methods for deep learning applied to natural language processing (NLP). This encompasses three threads:
- defining and standardizing terminology, desiderata, and evaluation methods;
- understanding the strengths and weaknesses of existing models within this framework; and
- designing architectures which address these weaknesses.
Updates
- Spring 2023: New preprint! Attentiveness to Answer Choices Doesn’t Always Entail High QA Accuracy
- Spring 2023: Quoted in this article about language model interpretability.
- Spring 2023: I am an area chair for ACL 2023 and will also be giving a talk at the Natural Language Reasoning and Structured Explanations workshop. See you there!
- Spring 2023: Preprint that was a result of a large collaborative effort out- Self-Refine: Iterative Refinement with Self-Feedback
- Fall 2022: Talks at various NLP groups at the University of Washington (Tsvetshop, H2Lab, and Treehouse).
- Fall 2022: Co-organizing the BlackBoxNLP workshop at EMNLP 2022.
- Fall 2022: I am an area chair for EMNLP 2022.
- Fall 2022: Started postdoc at AI2.
- Summer 2022: Paper on generating few-shot free-text explanations at NAACL 2022.
- Summer 2022: I defended my PhD dissertation!
Contact me
Email: wiegreffesarah[at]gmail[dot]com
CV (last updated 10/05/22)
How to pronounce my last name (click on German left-side audio)
Older Updates
- Spring 2022: Giving a talk at the Oxford NLP reading group.
- Fall 2021: I passed my PhD dissertation proposal!
- Fall 2021: Paper and companion website– a survey on explainable NLP datasets– accepted to NeurIPS 2021 Datasets & Benchmarks.
- Fall 2021: Paper accepted to EMNLP 2021.
- Fall 2021: I am a TA for CS 7650 Natural Language Processing.
- Summer 2021: I am returning to AI2 to intern on the Mosaic team, working with Swabha Swayamdipta, Jack Hessel, and Yejin Choi.
- Summer 2021: Paper at NAACL 2021 Narrative Understanding workshop.
- Spring-Summer 2021: Publicity Co-Chair for NAACL 2021. Checkout our social initiative People of Natural Language Processing; follow us on Twitter (@NAACLHLT) and Weibo (@国际计算语言学年会ACL2021).
- Spring 2021: I gave a (recorded) talk at NLP with Friends.
- Spring 2021: I am a TA for CS 7643 Deep Learning.
- Summer and Fall 2020: I was a research intern at the Allen Institute for AI, working with Noah Smith and Ana Marasović. Awarded the AI2 Outstanding Intern award!
- Summer 2020: Paper at ACL 2020 with collaborators at Northeastern University.
- Spring 2020: Gave a (recorded) talk at the USC/ISI NLP Seminar: “BlackBox NLP: What are we looking for, and where do we stand?”.
- Fall 2019: Presented a poster at WiML 2019.
- Fall 2019: Paper accepted to EMNLP 2019: Attention is not not Explanation. Recorded talk here.
- Fall 2019: I am a TA for CS 7643 Deep Learning taught by Dhruv Batra. Slides from my guest lecture are here.
- Summer 2019: I am a research intern at Google Medical Brain, working with Dr. Edward Choi and Gerardo Flores.
- Summer 2019: Paper accepted at the ACL BioNLP 2019 workshop: Clinical Concept Extraction for Document-Level Coding
- Spring 2019: I passed my qualifying exam! (in intelligent systems: machine learning and NLP subareas)
- Spring 2019: I am a TA for CS 4641 Machine Learning.
- Spring 2019: Attended ACM FAT* 2019 as a student volunteer.
- Summer 2018: I was an intern at Sutter Health working with the Research, Development and Dissemination Team on deep learning models for outcome prediction using text.
- Summer 2018: Attended NAACL in New Orleans as a student volunteer.
- Spring 2018: Paper accepted to NAACL 2018 (Explainable Prediction of Medical Codes from Clinical Text)
- Spring 2018: Attended the CRA-W Graduate Cohort Workshop in San Francisco, CA.