Dr. Preslav Nakov, Ph.D.

Artificial Intelligence

6A South Hall
Department of Electrical Engineering and Computer Science
Computer Science Division
University of California, Berkeley
Berkeley, California, 94720
email: nakov@cs.berkeley.edu
phone: (510) 643-4806

I am now a Senior Scientist at the Qatar Computing Research Institute.

President of Bulgaria Award
Awarded the John Atanasoff Award
by the President of Bulgaria.

Research, publications, CV:
  • Ph.D. thesis: Using the Web as an Implicit Training Set: Application to Noun Compound Syntax and Semantics (University of California at Berkeley, advisor: Marti Hearst)
  • Selected publications: [List here]
  • Curriculum Vitae (ask me for more detailed versions): [EuroPass] [plain]
  • Research Interests: Computational Linguistics, Natural Language Processing (NLP), Lexical Semantics, Machine Translation, Web as a Corpus, Bioinformatics, and BioNLP.

    Recent Awards
  • RANLP'2011 Young Researcher Award


    Some Recent Publications
    2014:
  • EMNLP'2014: Learning to Differentiate Better from Worse Translations. Francisco Guzman, Shafiq Joty, Lluis Marquez, Alessandro Moschitti, Preslav Nakov and Massimo Nicosia
  • The BOOK! 2013:
  • BOOK: Semantic Relations Between Nominals. Vivi Nastase, Preslav Nakov, Diarmuid O Seaghdha, Stan Szpakowicz. Synthesis Lectures on Human Language Technologies. Morgan & Claypool Publishers. [Amazon]
  • ACM TSLP: Semantic Interpretation of Noun Compounds Using Verbal and Other Paraphrases. Preslav Nakov and Marti Hearst, ACM Transactions on Speech and Language Processing, 10(3):13:1-13:51, July 2013.
  • NLE: On the Interpretation of Noun Compounds: Syntax, Semantics, and Entailment. Preslav Nakov, Natural Language Engineering, 19(3):192-330, July 2013.
  • ACL'2013: A Tale about PRO and Monsters. Preslav Nakov, Francisco Guzman and Stephan Vogel
  • ICML'2013: A non-IID Framework for Collaborative Filtering with Restricted Boltzmann Machines. Kostadin Georgiev, Preslav Nakov
  • RANLP'2013: Analyzing the Use of Character-Level Translation with Sparse and Noisy Datasets. Jorg Tiedemann, Preslav Nakov
  • RANLP'2013: Parameter Optimization for Statistical Machine Translation: It Pays to Learn from Hard Examples. Preslav Nakov, Fahad Al Obaidli, Francisco Guzman and Stephan Vogel
  • IWSLT'2013: QCRI at IWSLT 2013: Experiments in Arabic-English and English-Arabic Spoken Language Translation. Hassan Sajjad, Francisco Guzman, Preslav Nakov, Ahmed Abdelali, Kenton Murray, Fahad Al Obaidli, Stephan Vogel
  • SemEval'2013: SemEval-2013 Task 2: Sentiment Analysis in Twitter. Preslav Nakov, Sara Rosenthal, Zornitsa Kozareva, Veselin Stoyanov, Alan Ritter, Theresa Wilson
  • SemEval'2013: SemEval-2013 Task 4: Free Paraphrases of Noun Compounds. Iris Hendrickx, Zornitsa Kozareva, Preslav Nakov, Diarmuid O Seaghdha, Stan Szpakowicz, Tony Veale
  • 2012:
  • JAIR: Improving Statistical Machine Translation for a Resource-Poor Language Using Related Resource-Rich Languages Preslav Nakov, Hwee Tou Ng, Journal of Artificial Intelligence Research (JAIR), vol. 44, pp. 179-222, May 2012.
  • Advances in Bioinformatics: Do Peers See More in a Paper than its Authors? Anna Divoli, Preslav Nakov, and Marti Hearst, Advances in Bioinformatics, 2012.
  • EMNLP'2012: Source Language Adaptation for Resource-Poor Machine Translation Pidong Wang, Preslav Nakov, Hwee Tou Ng
  • ACL'2012: Combining Word-Level and Character-Level Models for Machine Translation Between Closely-Related Languages Preslav Nakov, Jorg Tiedemann
  • EACL'2012: Feature-rich Part-of-speech Tagging for Morphologically Complex Languages: Application to Bulgarian Georgi Georgiev, Valentin Zhikov, Kiril Simov, Petya Osenova, Preslav Nakov
  • COLING'2012: Optimizing for Sentence-Level BLEU+1 Yields Short Translations Preslav Nakov, Francisco Guzman, Stephan Vogel *** The proposed fix to PRO has been implemented (i) in Rampion, see also this Adendum to (Gimpel&Smith,2012) ***; (ii) in Moses: just add this when calling mert-moses.perl:
    --pairwise-ranked --proargs='--smooth-brevity-penalty'
  • WMT'2012: QCRI at WMT12: Experiments in Spanish-English and German-English Machine Translation of News Text Francisco Guzman, Preslav Nakov, Ahmed Thabet, Stephan Vogel


  • Current Program Committees:
  • 2015: Metaphor in NLP'2015,
  • 2014: EACL'2014, EACL-SRW'2014, MWE'2014, LT4CloseLang'2014. DeepLP4QApp'2014.
  • 2013: ACL'2013, NAACL-HLT'2013, EMNLP'2013, SIGIR'2013, IJCAI'2013, IJCNLP'2013, RANLP'2013, CICLING'2013, *SEM'2013, SemEval'2013, ACL-SRW'2013, RANLP-SRW'2013, WMT'2013, MWE'2013, WAC'2013, TextGraphs'2013, MUMTTT'2013, AICCSA'2013, NLP&LOD'2013, MIE'2013.

    Ongoing and Recent Activities:
  • SemEval'2016: 10th International Workshop on Semantic Evaluation, co-chair.
  • MWE'2016: 12th Workshop on Multiword Expressions, at ACL'2016, co-chair.
  • RANLP'2015: Conference on Recent Advances in Natural Language Processing, co-organizer.
  • SemEval'2015: 9th International Workshop on Semantic Evaluation, co-chair.
  • DiscoMT'2015: Shared Task on Pronoun Translation, co-organizer.
  • LT4VarDial'2015: Joint Workshop on Language Technology for Closely Related Languages, Varieties and Dialects, co-chair.
  • LT4VarDial'2015: DSL Shared Task 2015 on Discriminating between Similar Languages, co-organizer.
  • EMNLP'2014: Conference on Empirical Methods in Natural Language Processing, local co-organizer.
  • SemEval'2014: 8th International Workshop on Semantic Evaluation, co-chair.
  • LT4CloseLang'2014: EMNLP 2014 Workshop on Language Technology for Closely Related Languages and Language Variants, co-organizer.
  • JNLE: 2013 Journal of Natural Language Engineering, special issue on the Semantics of Noun Compounds, guest co-editor.
  • RANLP'2013: Conference on Recent Advances in Natural Language Processing, co-organizer.
  • *SEM'2013: Second Joint Conference on Lexical and Computational Semantics, area co-chair for Morphology/Semantics Interface.
  • ACL-SRW'2013: ACL 2013 Student Research Workshop, faculty advisor.
  • NLP&LOD'2013: RANLP 2013 Workshop on Natural Language Processing and Linked Open Data, co-organizer.
  • RANLP'2011: Conference on Recent Advances in Natural Language Processing, co-organizer.
  • AISB'2011: Artificial Intelligence and Simulation of Behaviour Convention, track co-chair.
  • LLMMC'2011: Symposium on Learning Language Models from Multilingual Corpora, co-organizer.
  • RELMS'2011: Workshop on Relational Models of Semantics, at ACL'2011, co-organizer.
  • IEKA'2011: Workshop on Information Extraction and Knowledge Acquisition, at RANLP'2011, co-organizer.
  • MWE'2011: Workshop on Multiword Expressions: from Parsing and Generation to the Real World, at ACL'2011, consulting body.
  • AIRS'2010: The Sixth Asia Information Retrieval Societies Conference, publication chair.
  • MWE'2010: Workshop on Multiword Expressions: from Theory to Applications, at COLING'2010, co-organizer.
  • MWE'2009: Workshop on Multiword Expressions: Identification, Interpretation, Disambiguation and Applications, at ACL/IJCNLP'2009, co-organizer.
  • SemEval'2016, task #3 on Community Question Answering, co-organizer.
  • SemEval'2016, task #4 on Sentiment Analysis in Twitter, co-organizer.
  • SemEval'2015, task #3 on Answer Selection in Community Question Answering, co-organizer.
  • SemEval'2015, task #10 on Sentiment Analysis in Twitter, co-organizer.
  • SemEval'2014, task #9 on Sentiment Analysis in Twitter, co-organizer.
  • SemEval'2013, task #2 on Sentiment Analysis in Twitter, co-organizer.
  • SemEval'2013, task #4 on Free Paraphrases of Noun Compounds, co-organizer.
  • SemEval'2010, task #8 on Multi-Way Classification of Semantic Relations Between Pairs of Nominals, co-organizer.
  • SemEval'2010, task #9 on Noun Compound Interpretation Using Paraphrasing Verbs, co-organizer.
  • SemEval'2007, task #4 on Classification of Semantic Relations between Nominals, co-organizer.
  • NLP Reading Group at NUS

    Tutorial speaker
  • Learning Semantic Relations from Text at the Conference on Empirical Methods in Natural Language Processing (EMNLP'2015), September 18, 2015, Lisbon, Portugal [pdf]
  • Learning Semantic Relations from Text at RANLP'2013 [pdf]
  • Web Knowledge Extraction and Applications at RANLP'2011

    Keynote/Invited Talks at Conferences, Workshops, Olympiads
  • December 10, 2015: SAIL @ MIKE'2015 (Hyderabad, India), keynote talk: "Sentiment Analysis on Twitter: a SemEval Perspective"
  • July 30, 2015: Novel Computational Approaches to Keyphrase Extraction Workshop, co-located with ACL 2015 (Beijing, China), keynote talk: "The Web as an Implicit Training Set: Application to Noun Compounds Syntax and Semantics"
  • July 22, 2015: 13th International Linguistics Olympiad, IOL'2015 (Blagoevgrad, Bulgaria), invited talk: "Statistical Machine Translation"
  • June 29, 2015: AComIn Workshop on Big Data in NLP, Education and Digital Collections (Sofia, Bulgaria), invited talk: "The Web as an Implicit Training Set: application to noun compounds syntax and semantics"
  • June 5, 2015: Fourth Joint Conference on Lexical and Computational Semantics (*SEM'2015) (Denver, Colorado, USA), keynote talk: "60 Years Ago People Dreamed of Talking with a Machine. Are We Any Closer?"
  • May 29, 2015: International Conference on Computational Linguistics, Dialog'2015 (Moscow, Russia), keynote talk: "Sentiment Analysis of Social Media Texts: a SemEval Perspective"
  • May 28, 2015: International Conference on Computational Linguistics, Dialog'2015 (Moscow, Russia), round table talk: "Linguistic Analysis of Social Media Texts"
  • April 26, 2014: 10th Workshop on Multiword Expressions (MWE'2014), (Gothenburg, Sweden), invited talk: "The Web as an Implicit Training Set: Application to Noun Compounds Syntax and Semantics"
  • Keynote speaker at ICEKMT'2011
  • Invited speaker at AEPC'2011
  • Panelist at ROBUS-UNSUP'2012
  • Panelist at MWE'2011

    Talks at Universities, Research Institutions, Societies, Companies
  • July 23, 2015: Data Science Society (Sofia, Bulgaria), invited talk: "The Web as a Training Set"
  • July 3, 2015: University of Veliko Tarnovo (Veliko Tarnovo, Bulgaria), talk: "Why are Computers Bad Translators?" (in Bulgarian: "Защо компютрите са лоши преводачи?")
  • June 25 and 26, 2015: Software University (Sofia, Bulgaria), guest lecture in the course on Data Structures: "Data Structures, Algorithms and Complexity"
  • June 22, 2015: Summer School in Informatics for preparation of the extended Bulgarian national teams (Sofia, Bulgaria), lecture: "Algorithmic Games"
  • May 26, 2015: ABBYY (Moscow, Russia), invited talk: "The Web as an Implicit Training Set"
  • May 17, 2015: Sofia Science Festival (Sofia, Bulgaria), keynote talk: "Translation Impossible?" (in Bulgarian: "Преводът невъзможен")
  • May 15, 2015: Software University (Sofia, Bulgaria), talk at the seminar series: "Why are Computers Bad Translators?" (in Bulgarian: "Защо компютрите са лоши преводачи?")
  • September 11, 2014: University of Bergen (Bergen, Norway), guest talk and a master class: "The Web as an Implicit Training Set: Application to Noun Compound Syntax and Semantics"
  • November, 2012: Massachusetts Institute of Technology (USA)
  • June, 2011: Microsoft Research (USA), Yahoo! Labs (USA), University of Washington (USA), Macquarie University (Australia), University of Otago (New Zealand)
  • May, 2011: Goethe University of Frankfurt (Germany)
  • March, 2011: University of Saarland (Germany)
  • February, 2011: University of Heidelberg and HITS gGmbH (Germany)
  • January, 2011: Max Planck Society (Germany)
  • December, 2010: The University of Melbourne (Australia)
  • November, 2010: University of Rome, La Sapienza (Italy)
  • August, 2010: University of Basel (Switzerland), University of Darmstadt (Germany), and XRCE in Grenoble (France)
  • July, 2010: NICTA and The University of Melbourne (Australia).
  • February, 2010: University of Wolverhampton (UK).
  • January, 2010: University of Cambridge (UK), University of Karlsruhe (Germany), and University of Stuttgart (Germany).
  • November, 2009: NICT, Kyoto (Japan).



    My books (in Bulgarian):
  • "Programming=++Algorithms;" (Official Web Site)
  • "Fundamentals of Computer Algorithms" (source code)

    Bulgarian Bay Area:
  • Bulgarian Club at Berkeley (email to majordomo@listlink.berkeley.edu with "subscribe bulgarian_club")
  • Stanford Bulgarians (email to majordomo@lists.stanford.edu with "subscribe stanford-bulgarians")
  • BG Guide
  • BulgariaHiTech
  • Bulgarian/Balkan Music and Dance Events Group


    My advisor at Berkeley was Prof. Marti Hearst.