Research Interests & Projects

My research interests lie in the fields of natural language processing, text mining, and information retrieval.  During my time at Heidelberg University and Max Planck Institute for Informatics, I was also involved in digital humanities projects (e.g., heureclea).

Research Competitions

• 1st place: AfriSenti, Sentiment Analysis for African Languages (monolinguial and multilingual classification)  [SemEval'23]

• 1st place: MEDDOPROF, Medical Documents Professions recognition shared task (Spanish) [IberLEF'21].

• 1st place: MEDDOCAN, Medical Document Anonymization task (Spanish) [IberLEF'19].

• 1st place: EVENTI, Italian temporal tagging task [EVALITA'14].

• 1st place: TempEval-3, English and Spanish temporal tagging tasks [SemEval'13].

• 1st place : TempEval-2, English temporal tagging task [SemEval'10].

Software

• heideltime (multilingual, domain-sensitive temporal tagger) 

Demos

The following links show some demos about research I participated in:

• heideltime (multilingual, domain-sensitive temporal tagger) [PhD thesis] [EMNLP'15]

• tiwoli (today in world literature): blog post, android app, iOS app, web app [DH'15]

• tiwiki (time-aware search engine for Wikipedia) [TempWeb@WWW'17]

• dateRome (date references on maps with explanations) [JCDL'18] [WWW'17]

• TEQUILA (temporal question answering over knowledge bases) [CIKM'18] [HQA@WWW'18]

• credeye (a credibility lens for analyzing and explaining misinformation) [WWW'18] [WWW'17][CIKM'16]

Corpora

I participated in the development of several corpora with annotated temporal expressions:

• corpora hosted at Heidelberg University: 

  • WikiWarsDE [GSCL'11] and WikiWarsVN [TALLIP'14]

  • Time4SMS and Time4SCI [LREC'12]

  •  AncientTimes [LREC'14]

  • improved versions of Arabic and Chinese corpora [TALLIP'14] [EACL'14] 

• KRAUTS [LREC'18]