I am a fifth year PhD student in Computer Science at Columbia University working with Professor Julia Hirschberg. My research goal is to extend current NLP methods and design new ones for code-switched language. Currently I'm focusing on discovering mixed-language web resources, and neural part-of-speech tagging and language modeling for English-Spanish sentences. You can find my CV here.
"The Role of Cognate Words, POS Tags, and Entrainment in Code-Switching, " V. Soto, N. Cestero, J. Hirschberg, Interspeech, Hyderabad, India, September 2018 [WEB]
"Joint Part-of-Speech and Language ID Tagging for Code-Switched Data," V.Soto, J. Hirschberg, Third Workshop on Computational Approaches to Linguistic Code-Switching at ACL , Melbourne, Australia, July 2018 [WEB]
"Named Entity Recognition on Code-Switched Data: Overview of the CALCS 2018 Shared Task," G. Aguilar, F. AlGhamdi, V.Soto, M. Diab, J. Hirschberg, T. Solorio, Third Workshop on Computational Approaches to Linguistic Code-Switching at ACL , Melbourne, Australia, July 2018 [WEB]
"Collecting Code-Switched Data from Social Media, " G. Mendels∗, V. Soto∗, A. Jaech, J. Hirschberg, LREC, Miyazaki, Japan, May 2018 [WEB]
"Crowdsourcing Universal Part-Of-Speech Tags for Code-Switching, " V. Soto, J. Hirschberg, Interspeech, Stockholm, Sweden, August 2017 [WEB]
"An urn model for majority voting in classification ensembles," V. Soto, G. Martinez-Munoz, A. Suarez, NIPS, Barcelona, Spain, 2016 [WEB] [CODE]
"Part of Speech Tagging for Code Switched Data," F. AlGhamdi, G. Molina, M. Diab, T. Solorio, A. Hawwari, V. Soto and J. Hirschberg, EMNLP, Austin TX, USA, 2016 [WEB]
"Selection and Combination of Hypotheses for Dialectal Speech Recognition," V. Soto, O. Siohan, M. Elfeky and P. Moreno, ICASSP, Shanghai, China, 2016 [PDF]
"Multi-Dialectical Languages Effect on Speech Recognition," M. Elfeky, P. Moreno and V. Soto, ICNSLP, Algiers, 2015 [PDF]
"Improving Speech Recognition and Keyword Search for Low Resource Languages Using Web Data," G. Mendels, E. Cooper, V. Soto, J. Hirschberg, M. Gales, K. Knill, A. Ragni and H. Wang, Interspeech, Dresden, Germany, 2015 [PDF]
"A Comparison of Multiple Methods for Rescoring Keyword Search Lists for Low Resource Languages," V. Soto , L. Mangu, A. Rosenberg and J. Hirschberg, Interspeech Singapore, 2014 [PDF]
"Strategies for Rescoring Keyword Search Results Using Word-Burst and Acoustic Features," M. Ma, J. Richards, V. Soto and A. Rosenberg, Interspeech, Singapore, 2014 [PDF]
"A Double Pruning Scheme for Boosting Ensembles," V. Soto, S. Garcia-Moratilla, G. Martinez-Munoz, D. Hernandez-Lobato and A. Suarez, IEEE Transactions on Cybernetics Issue 99 [PDF]
"Rescoring Confusion Networks for Keyword Search," V. Soto, E. Cooper, L. Mangu, A. Rosenberg and J. Hirschberg, ICASSP Florence, Italy, 2014 [PDF]
"Consensus Clustering for Urban Land Use Analysis using Cell-Phone Network Data", V. Frias-Martinez, V. Soto, A. Sanchez and E. Frias-Martinez, International Journal of Ad-Hoc and Ubiquitous Computing Accepted, 2013 [PDF]
"Can Cell-Phone Traces Measure Social Development?," V. Frias-Martinez, V. Soto, J. Virseda and E. Frias-Martinez, NetMob, 2013 [PDF]
"Cross-Language Phrase Boundary Detection," V. Soto, E. Cooper, A. Rosenberg and J. Hirschberg, ICASSP Vancouver, Canada, 2013 [PDF]
"Finding Emotion in Image Descriptions," M. Ulinski, V. Soto and J. Hirschberg, Workshop on Issues of Sentiment Discovery and Opinion Mining (WISDOM) with KDD Beijing, China, 2012 [PDF]
"Characterizing Urban Landscapes using Geolocated Tweets," V. Frias-Martinez, V. Soto, H. Hohwald, E. Frias-Martinez, Int. Conference on Social Computing (SocialCom), Amsterdam, The Nederlands, 2012 [PDF]
"Computing Cost-Effective Census Maps From Cell Phone Traces," V. Frias-Martinez, V. Soto, J. Virseda and E. Frias-Martinez, Pervasive Urban Applications -PURBA 2012, Newscastle, UK, 2012 [PDF]
"Automated Land Use Identification using Cell-phone Records," V. Soto, E. Frias-Martinez, 3rd ACM Int. Workshop on Hot Topics in Planet-Scale Measurement, in conjuntion with ACM MobiSys2011, Washington DC, 2011 [PDF]
"Robust Land Use Characterization of Urban Landscapes using Cell Phone Data," V.Soto, E. Frias-Martinez, Workshop on Pervasive Urban Applications in conjuntion with 9th Int. Conf. on Pervasive Computing, San Francisco, CA,2011 [PDF]
"Prediction of Socioeconomic Levels using Cell Phone Records," V. Soto, V. Frias-Martinez, J. Virseda and E. Frias-Martinez International Conference on User Modeling, Adaptation and Personalization (UMAP), Industrial Track, Girona, Spain, 2011[PDF]
"A double pruning algorithm for classification ensembles", V. Soto, G. Martinez-Muñoz, D. Hernandez-Lobato and A. Suarez, Multiple Classifier Systems: 9th International Workshop (MCS),Cairo, Egypt, 2010 [PDF]
"Dynamic and Static Pruning Techniques for Classification Ensembles", V. Soto. Advisor G. Martinez-Muñoz, UAM 2011 [PDF] [External Link]
Please contact me at vsoto -at- cs -dot- columbia -dot- edu
