Hi, I am a Research Scientist in the R&D division at Educational Testing Services (ETS) in Princeton, NJ. Before coming to ETS in January 2013, I was a Research Scientist at the Knowledge and Decision Systems group at Siemens Corporate Research (SCR), Princeton, New Jersey. At SCR, I worked on lexical semantics and relationship mining, amongst other things. I received my PhD from Computer Science department of the  University of Pittsburgh. While at Pitt, I was a member of the Natural Language Processing Group. My primary research areas are NLP and AI. I am interested in many aspects of Natural Language Processing like subjectivity and sentiment analysis, discourse, dialogs and multi-perspective question answering.
At ETS, I continue to work on discourse, opinion, narratives and many other aspects of language, applying them specifically for the task of automated assessments.

Here is my CV

 

 

Data and Resources

Product Debate Data

This was the data used in the following paper: Swapna Somasundaran and Janyce Wiebe, (2009), Recognizing Stances in Online Debates ,  ACL 2009
It can be obtained by requesting the MPQA resource site here
This is how this data should be cited: bib 


Political Debate Data

This was the data used in the following paper: Swapna Somasundaran and Janyce Wiebe, (2010), Recognizing Stances in Ideological On-line Debates.  Workshop on Computational Approaches to Analysis and Generation of Emotion in Text, NAACL HLT 2010
It can be obtained by requesting the MPQA resource site here
This is how this data should be cited: bib

 

Arguing Lexicon

This is the lexicon created and used in the following paper: Swapna Somasundaran, Josef Ruppenhofer and Janyce Wiebe (2007)  Detecting Arguing and Sentiment in Meetings SIGdial Workshop on Discourse and Dialogue
It can be obtained by requesting the MPQA resource site here
This is how this data should be cited: bib

 

Publications

 
Swapna Somasundaran, Chong Min Lee, Martin Chodorow and Xinhao Wang (2015) Automated Scoring of Picture-based Story Narration, The 10th Workshop on Innovative Use of NLP for Building Educational Applications, NAACL 2015, Denver, CO, USA
 
Noura Farra, Swapna Somasundaran and Jill Burstein (2015) Scoring Persuasive Essays Using Opinions and their Targets. The 10th Workshop on Innovative Use of NLP for Building Educational Applications, NAACL 2015, Denver, CO, USA
 
 
Swapna Somasundaran Jill Burstein and Martin Chodorow, (2014) Lexical Chaining for Measuring Discourse Coherence Quality in Test-taker Essays , COLING 2014, Dublin, Ireland

Swapna Somasundaran and Martin Chodorow, (2014) Automated Measures of Specific Vocabulary Knowledge from Constructed Responses (“Use TheseWords to Write a Sentence Based on this Picture”), In Proceedings of the Ninth Workshop on Innovative Use of NLP for Building Educational Applications, Baltimore, Maryland, ACL 2014

Jill Burstein, Swapna Somasundaran and Martin Chodorow, (2014) Finding your “inner-annotator”: An experiment in annotator independence for rating discourse coherence quality in essays. 8th Linguistic Annotation Workshop (LAW VIII 2014) , Dublin, Ireland.

Beata Beigman Klebanov, Nitin Madnani, Jill Burstein and Swapna Somasundaran (2014) Content Importance Models for Scoring Writing From Sources. , In Poceedings of ACL 2014 (short papers) Baltimore, Maryland

 
Kateryna Tymoshenko, Swapna Somasundaran, Vinodkumar Prabhakaran, Vinay Damodar Shet (2012) Relation Mining in the Biomedical Domain using Entity-level Semantics ECAI 2012: 20th European Conference on Artificial Intelligence, Montpellier, France, August 27-31 (acceptance rate = 28%)
 
Swapna Somasundaran, Vinodkumar Prabhakaran, Vinay Damodar Shet, Kateryna Tymoshenko, Mathäus Dejori (2014 patent issued; filed in 2012)  System for generating a medical knowledge base US Patent 8,639,678.

Kateryna Tymoshenko, Swapna Somasundaran, Vinay Damodar Shet. (2014 patent issued; filed in 2012) System for linking medical terms for a medical knowledge base. US Patent 8,700,589. 

Dingcheng Li, Swapna Somasundaran and Amit Chakraborty (2012) ERD-MedLDA: Entity relation detection using supervised topic models with maximum margin learning Journal of Natural Language Engineering (JNLE), 18 , pp 263-289 doi:10.1017/S1351324912000058

 
Swapna Somasundaran, Dingcheng Li and Amit Chakraborty (2011) Information relation generation (Patent pending: EP2434415 A3, US20120078918 A1)

Dingcheng Li, Swapna Somasundaran and Amit Chakraborty (2011) A Combination of Topic Models with Max-margin Learning for Relation Detection In Proceedings of TextGraphs-6: Graph-based Methods for Natural Language Processing, Workshop at ACL-HLT 2011, Portland, Oregon

 
Swapna Somasundaran (2010), Discourse-level relations for Opinion Analysis, PhD Thesis, University of Pittsburgh.

Swapna Somasundaran and Janyce Wiebe, (2010), Recognizing Stances in Ideological On-line Debates. ,  In Proceedings of the NAACL HLT 2010 Workshop on Computational Approaches to Analysis and Generation of Emotion in Text, pages 116-124, Los Angeles, CA. Association for Computational Linguistics, 2010. Data for this paper can be downloaded from here
 
Swapna Somasundaran and Janyce Wiebe, (2009), Recognizing Stances in Online Debates ,  ACL 2009: Joint conference of the 47th Annual Meeting of the Association for Computational Linguistics and the 4th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, August 2-7, 2009, Singapore. Data for this paper can be downloaded from here

Swapna Somasundaran, Galileo Namata, Janyce Wiebe and Lise Getoor (2009) Supervised and Unsupervised Methods in Employing Discourse Relations for Improving Opinion Polarity Classification ,  EMNLP 2009: conference on Empirical Methods in Natural Language Processing August 6-7, 2009, Singapore.

Swapna Somasundaran, Galileo Namata, Lise Getoor and Janyce Wiebe, (2009) Opinion Graphs for Polarity and Discourse Classification , TextGraphs-4: Graph-based Methods for Natural Language Processing, 7th August 2009, Singapore
 
Swapna Somasundaran, Janyce Wiebe and Josef Ruppenhofer (2008) Discourse Level Opinion Interpretation,  Coling, Manchester, 18-22 August, 2008

Swapna Somasundaran, Josef Ruppenhofer and Janyce Wiebe (2008) Discourse Level Opinion Relations: An Annotation Study, SIGdial Workshop on Discourse and Dialogue, Columbus, Ohio,  June 2008

Josef Ruppenhofer, Swapna Somasundaran and Janyce Wiebe (2008)  Finding the Sources and Targets of Subjective Expressions. LREC 2008, Marrakech, Morocco.  
 
Swapna Somasundaran, Josef Ruppenhofer and Janyce Wiebe (2007)  Detecting Arguing and Sentiment in Meetings SIGdial Workshop on Discourse and Dialogue, Antwerp, Belgium, September  2007

Swapna Somasundaran, Theresa Wilson, Janyce Wiebe and Veselin Stoyanov (2007) QA with Attitude: Exploiting Opinion Type Analysis for Improving Question Answering in On-line Discussions and the News, International Conference on Weblogs and Social Media March 26-28, 2007, Boulder, Colorado, U.S.A.
 
Swapna Somasundaran, Janyce Wiebe, Paul Hoffmann, Diane Litman  (2006).Manual Annotation of Opinion Categories in Meetings. ACL Workshop: Frontiers in Linguistically Annotated Corpora(Coling/ACL 2006) , Sydney, Australia

Theresa Wilson, Paul Hoffmann, Swapna Somasundaran, Jason Kessler, JanyceWiebe, Yejin Choi, Claire Cardie, Ellen Riloff, Siddharth Patwardhan (2005). OpinionFinder: A system for subjectivity analysis Demo in Human Language Technologies Conference/Conference on Empirical Methods in Natural Language Processing (HLT/EMNLP 2005), Vancouver, Canada.

 


 

 

Contact