Allyson Ettinger

aetting (at) umd (dot) edu

Allyson

News

We've just completed the first Workshop on Building Linguistically Generalizable NLP Systems and associated Build It, Break It: The Language Edition shared task, hosted at EMNLP 2017. If you are interested in participating in future iterations, check it out!

I also co-chaired the ACL Student Research Workshop 2017, which took place in Vancouver this summer.



About

Current

I am a fifth-year PhD student in the Department of Linguistics at University of Maryland, College Park. I'm advised by Colin Phillips and Philip Resnik, in addition to collaborations with numerous faculty and students across the linguistics and computer science departments. I am an active member of the Maryland Language Science Center.

My work focuses on sentence comprehension, from perspectives of cognitive neuroscience and natural language processing. I have two primary threads of research, serving scientific (cognitive) and engineering (NLP) goals, respectively.

In my cognitive research, I work on computational models to simulate response measures like the N400 and P600, for the purpose of fleshing out and testing hypotheses about the mechanisms underlying human sentence comprehension. One theme of this work has been drawing on current models and techniques from NLP, and applying these to the investigation of cognitive questions. 

In my NLP research, my interest is in improving models' capacity for sentence composition. For this purpose I am currently developing a system for analyzing the meaning content captured by sentence-level vector representations (“embeddings”) produced by NLP models. The method that I use is inspired by the decoding / multi-voxel pattern analysis method for analyzing information encoded in brain activations. This approach allows us to probe for particular types of meaning information despite the opacity of vector representations, with the goal of using this analysis to improve the quality of sentence encoders.

Research

Publications

Ettinger, A., Rao, S., Daumé III, H., Bender, E. M. (2017). Towards Linguistically Generalizable NLP Systems: A Workshop and Shared Task. Proceedings of the First Workshop on Building Linguistically Generalizable NLP Systems. PDF

Ettinger, A., Elgohary, A., Resnik, P. (2016). Probing for semantic evidence of composition by means of simple classification tasks. Proceedings of the First Workshop on Evaluating Vector Space Representations for NLP, ACL 2016. Recipient of Best Proposal Award. PDF

Ettinger, A., Feldman, N.H., Resnik, P., Phillips, C. (2016). Modeling N400 amplitude using vector space models of word representation. Proceedings of the 38th Annual Conference of the Cognitive Science Society. PDF

Ettinger, A., Linzen, T. (2016). Evaluating vector space models using human semantic priming results. Proceedings of the First Workshop on Evaluating Vector Space Representations for NLP, ACL 2016. PDF

Ettinger, A., Resnik, P., Carpuat, M. (2016). Retrofitting sense-specific word vectors using parallel text. Proceedings of NAACL HLT 2016. PDF, Supplementary material

Rao, S., Ettinger, A., Daumé III, H., Resnik, P. (2015). Dialogue focus tracking for zero pronoun resolution. Proceedings of NAACL HLT 2015. PDF

Ettinger, A., Linzen, T., Marantz, A. (2014). The role of morphology in phoneme prediction: Evidence from MEG. Brain and Language 129, 14-23. PDF

Ettinger, A. & Malamud, S. (2014) Mandarin utterance-final particle ba in the conversational scoreboard. Proceedings of Sinn und Bedeutung. PDF

Conference Presentations

Ettinger, A., Elgohary, A., Resnik, P. (2016). Probing for semantic evidence of composition by means of simple classification tasks. Talk presented at the First Workshop on Evaluating Vector Space Representations for NLP, ACL 2016, Berlin, Germany.

Ettinger, A., Linzen, T. (2016). Evaluating vector space models using human semantic priming results. Poster presented at the First Workshop on Evaluating Vector Space Representations for NLP, ACL 2016, Berlin, Germany.

Ettinger, A., Feldman, N.H., Resnik, P., Phillips, C. (2016). Modeling N400 amplitude using vector space models of word representation. Poster presented at Annual Conference of the Cognitive Science Society, Philadelphia, PA.

Ettinger, A., Resnik, P., Carpuat, M. (2016). Retrofitting sense-specific word vectors using parallel text. Talk presented at NAACL HLT 2016, San Diego, CA.

Rao, S., Ettinger, A., Daumé III, H., Resnik, P. (2015). Dialogue focus tracking for zero pronoun resolution. Poster presented at NAACL HLT 2015, Denver, CO.

Ettinger, A. & Malamud, S. (2013). Mandarin utterance-final particle ba in the conversational scoreboard. Talk presented at Linguistic Society of America Annual Meeting, Boston, MA, and 19th International Congress of Linguists, Geneva, Switzerland.

Ettinger, A., Linzen, T., Marantz, A. (2013). The role of morphological structure in phoneme prediction: evidence from MEG. Poster presented at Cognitive Neuroscience Society Annual Meeting and CUNY Conference on Human Sentence Processing.

Ettinger, A. & Malamud, S. (2012). Mandarin utterance-final particle ba and conversational goals. Talk presented at NYU Semantics Discussion Group Meeting, New York, NY.

Ettinger, A., Moua, M.Y., Stanford, J. (2010). Linguistic construction of gender and generations in Hmong-American communities. Talk presented at Linguistic Society of America Annual Meeting, Baltimore, MD.

Teaching

Undergraduate

Meaning in Language: Brains and Machines (LING449R, Spring 2017)
I designed and led this course independently, teaching a class of 16 undergraduates from linguistics and computer science. The course explored the concept of "meaning" from perspectives of linguistics, cognitive neuroscience of language, and natural language processing.

Computational Approaches in Language Science (CMSC289J/LING499J, Fall 2015)
I served as TA for this course, in addition to designing and teaching a five-class segment on meaning and vector space models.

Language and Mind (LING240, Fall 2014)
I served as teaching assistant for this course (Intro to Linguistics for linguistics majors).

Graduate

For two years I also led the organization of the annual Winter Storm graduate training workshop, designing a two-week graduate training curriculum targeting key research skills, professional development, and interdisciplinary collaboration. During one of these workshops I led a two-week morning session on science communication.



More about me

Past

I grew up in a small coastal town in the great state of Maine. I graduated from Brandeis University in 2010 with degrees in linguistics and psychology, after which I did a year of graduate-level work in Nanjing, China. I then spent two years conducting MEG research with Alec Marantz at the Neuroscience of Language Lab at NYU, before joining the community at the University of Maryland.

I'm the oldest of four children and a longtime soccer player. I fell in love with foreign languages at the age of fourteen, when I first had the opportunity to travel abroad. I enjoy theater and literature and most every kind of fruit, and I am adamantly opposed to cashews.

CV

*Photo credit: Todd Dickson