Paramita Mirza

Paramita Paramita (Paramita Mirza)

Max-Planck-Institut für Informatik
Department 5: Databases and Information Systems
 office: Campus E1 4, Room 420
Saarland Informatics Campus
66123 Saarbrücken
 email: Get my email address via email
 phone: +49 681 9325-5020


I am currently a postdoctoral researcher at the Max Planck Institute for Informatics in Saarbrücken, Germany. I received my PhD degree from the University of Trento, Italy in spring 2016. My PhD research focused on extracting temporal and causal relations between events from natural language texts, as part of the NewsReader project, with the ultimate goal of the automatic creation of event timelines from large volumes of news texts. My current research interests include causation and common sense knowledge harvesting, emotional aspect of relation extraction and the semantics of numbers in natural language texts. This particular interest in computational linguistics is motivated by my background in computer science and passion about human language.


  • Jan 21, 2019 -- Our paper "Listening between the Lines: Learning Personal Attributes from Conversations" (with Anna Tigunova, Andrew Yates and Gerhard Weikum) has been accepted as a FULL PAPER to The Web Conference 2019 (acceptance rate: 18%).
  • May 25, 2018 -- Our paper "Enriching Knowledge Bases with Counting Quantifiers" (with Simon Razniewski, Fariz Darari and Gerhard Weikum) has been accepted to the research track of ISWC 2018.
  • April 29, 2018 -- The abridged version of our ISWC 2017 paper "Completeness-aware Rule Learning from Knowledge Graphs" (with Thomas Pellissier Tanon, Daria Stepanova, Simon Razniewski and Gerhard Weikum) has been accepted to the "Sister Conference Best Paper Track" at IJCAI 2018.
  • April 17, 2018 -- Our system paper "KOI at SemEval-2018 Task 5: Building Knowledge Graph of Incidents" (with Fariz Darari and Rahmad Mahendra) has been invited for an oral presentation at SemEval 2018.
  • February 14, 2018 -- Our demo paper "EMOFIEL: Mapping Emotions of Relationships in a Story" has been accepted at WWW 2018.
  • February 14, 2018 -- NLP-highlight podcast offered by Matt Gardner and Waleed Ammar from AI2 about our paper "Cardinal Virtues: Extracting Relation Cardinalities from Text" at ACL 2017 is now live!

Short CV




Google Scholar, DBLP, ACL

  • P. Mirza, S. Razniewski, F. Darari and G. Weikum. Enriching Knowledge Bases with Counting Quantifiers. In Proceedings of ISWC 2018, to appear.
  • T. P. Tanon, D. Stepanova, S. Razniewski, P. Mirza and G. Weikum. Completeness-aware Rule Learning from Knowledge Graphs. In Proceedings of IJCAI-ECAI 2018 (Sister Conference Best Paper Track), to appear.
  • P. Mirza, F. Darari and R. Mahendra. KOI at SemEval-2018 Task 5: Building Knowledge Graph of Incidents. In Proceedings of SemEval 2018, to appear.
  • H. Jhavar and P. MirzaEMOFIEL: Mapping Emotions of Relationships in a Story. In Proceedings of WWW '18 Companion Proceedings of the The Web Conference 2018, pages 243-246, Lyon, France. [pdf] [bib]
  • T. P. Tanon, D. Stepanova, S. Razniewski, P. Mirza and G. Weikum. Completeness-aware Rule Learning from Knowledge Graphs. In Proceedings of ISWC 2017, pages 507–525, Vienna, Austria. [pdf] [bib]
  • P. Mirza, S. Razniewski, F. Darari and G. Weikum. Cardinal Virtues: Extracting Relation Cardinalities from Text. In Proceedings of ACL 2017 (short paper), pages 347–351, Vancouver, Canada. [pdf] [bib]
  • P. Mirza and S.Tonelli. On the contribution of word embeddings to temporal relation classification. In Proceedings of COLING 2016, pages 2818–2828, Osaka, Japan. [pdf] [bib]
  • P. Mirza and S.Tonelli. CATENA: CAusal and TEmporal relation extraction from NAtural language texts. In Proceedings of COLING 2016, pages 64–75, Osaka, Japan. [pdf] [bib]
  • P. Mirza, S. Razniewski and W. Nutt. Expanding Wikidata's Parenthood Information by 178%, or How To Mine Relation Cardinalities. In Proceedings of ISWC 2016 (poster), Kobe, Japan. [pdf] [bib]
  • P. Mirza and A. Minard. HLT-FBK: a Complete Temporal Processing System for QA TempEval. In Proceedings of SemEval 2015, pages 801–805, Denver, Colorado. [pdf] [bib]
  • P. Mirza. Recognizing and Normalizing Temporal Expressions in Indonesian Texts. In Proceedings of PACLING 2015, pages 135–147, Bali, Indonesia. [pdf]
  • P. Mirza and A. Minard. FBK-HLT-time: a complete Italian Temporal Processing system for EVENTI-Evalita 2014. In Proceedings of EVENTI-EVALITA 2014, pages 44–49, Pisa, Italy.
  • P. Mirza and S. Tonelli. An Analysis of Causality between Events and its Relation to Temporal Information. In Proceedings of COLING 2014, pages 2097–2106, Dublin, Ireland. [pdf] [ppt] [bib]
  • P. Mirza. Extracting Temporal and Causal Relations between Events. In Proceedings of ACL 2014 Student Research Workshop, pages 10–17, Baltimore, MD, United States. [pdf] [ppt] [bib] []
  • P. Mirza and S. Tonelli. Classifying Temporal Relations with Simple Features. In Proceedings of EACL 2014, pages 308–317, Gothenburg, Sweden. [pdf] [poster] [bib]
  • P. Mirza, R. Sprugnoli, S. Tonelli and M. Speranza. Annotating causality in the TempEval-3 corpus. In Proceedings of CAtoCL Workshop at EACL 2014, pages 10–19, Gothenburg, Sweden. [pdf] [ppt] [bib]
  • P. Mirza and R. Bernardi. CCG Categories for Distributional Semantic Models. In Proceedings of RANLP 2013, pages 467–474, Hissar, Bulgaria. [pdf] [bib]
  • Ognjen Savković, P. Mirza, Alex Tomasi, and Werner Nutt. Complete approximations of incomplete queries. In Proceedings of VLDB 2013, pages 1378–1381, Riva del Garda, Italy. [pdf]
2008 - 2012
  • O. Savković, P. Mirza, S. Paramonov and W. Nutt. MAGIK: managing completeness of data. In Proceedings of CIKM 2012, pages 2725–2727, New York, NY, USA, October. [pdf]
  • D. H. Widyantoro, A. Purwarianti and P. Mirza. Information Extraction Using SVM Uneven Margin for Multilanguage Document. In Proceedings of ICTS 2008, pages 249–253, Surabaya, Indonesia. [pdf]
  • CATENA: CAusal and Temporal relation Extraction from NAtural language texts
  • Causal-TimeBank: the TimeBank corpus completed with causality information
  • IndoTimex: Temporal expression extraction system for Indonesian language
  • TimeNorm for Italian
  • MAGIK: Managing Completeness of Data


  • Linkedin, Github
  • Personal interests: travelling, writing, hiking & climbing, web design