+47 73594455
Sem Sælands vei 9, IT-bygget * 360

Background and activities

I work as a researcher in the area of Computational Linguistics and Natural Language Processing. I am interested in basically all aspects of natural language and speech from a computational point of view. Some of things I worked on (roughly in reverse chronological order) are:
  • Text Mining from scientific literature (marine/climate/environmental science)
  • Information Retrieval (with Random Indexing)
  • Cross-lingual IR
  • Information Extraction
  • Machine Translation (without parallel corpora), in particular word translation disambiguation
  • Treebanks of monolingual parallel/comparable text
  • Semantic Textual Similarity
  • Paraphrasing
  • Text-to-Text Generation and Sentence Fusion
  • Sentence Compression
  • Multi-document Summarization
  • Recognizing Textual Entailment
  • Dependency Parsing
  • Prosody prediction, intonation in particular
  • Speech Synthesis, both Text-to-Speech and Concept-to-Speech conversion
  • Talking heads and Embodied Conversational Agents
  • Natural Language Generation
  • Corpus annotation and validation
  • Morphological analysis and POS tagging of Arabic
  • Machine Learning (memory-based learning in particular)

Scientific, academic and artistic work

A selection of recent journal publications, artistic productions, books, including book and report excerpts. See all publications in the database

Journal publications

Part of book/report

  • Barik, Biswanath; Marsi, Erwin. (2017) NTNU-2 at SemEval-2017 Task 10: Identifying Synonym and Hyponym Relations among Keyphrases in Scientific Documents. 11th International Workshop on Semantic Evaluations (SemEval-2017).
  • Barik, Biswanath; Marsi, Erwin; Öztürk, Pinar. (2017) Extracting Causal Relations among Complex Events in Natural Science Literature. Natural Language Processing and Information Systems; 22nd International Conference on Applications of Natural Language to Information Systems, NLDB 2017; Liège, Belgium, June 21-23, 2017, Proceedings.
  • Marsi, Erwin; Skidar, Utpal; Marco, Cristina; Barik, Biswanath; Sætre, Rune. (2017) NTNU-1@ScienceIE at SemEval-2017 Task 10: Identifying and Labelling Keyphrases with Conditional Random Fields. 11th International Workshop on Semantic Evaluations (SemEval-2017).
  • Bøhler, Henrik; Asla, Petter Fagerlund; Marsi, Erwin; Sætre, Rune. (2016) IDI@NTNU at SemEval-2016 Task 6: Detecting Stance in Tweets Using Shallow Features and GloVe Vectors for Word Representation. The 10th International Workshop on Semantic Evaluation. Proceedings of the Workshop..
  • Marsi, Erwin; Øzturk, Pinar. (2015) Extraction and generalisation of variables from scientific publications. Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing (EMNLP 2015).
  • Marsi, Erwin; Øzturk, Pinar; Aamot, Elias; Sizov, Gleb Valerjevich; Ardelan, Murat Van. (2014) Towards Text Mining in Climate Science: Extraction of Quantitative Variables and their Relations. Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14).
  • Moen, Hans; Marsi, Erwin; Ginter, Filip; Murtola, Laura-Maria; Salakoski, Tapio; Salanterä, Sanna. (2014) Care Episode Retrieval. Proceedings of the 5th International Workshop on Health Text Mining and Information Analysis (Louhi).
  • Bungum, Lars; Gambäck, Björn; Lynum, Andre; Marsi, Erwin. (2013) Improving Word Translation Disambiguation by Capturing Multiword Expressions with Dictionaries. Proceedings of the 9th Workshop on Multiword Expressions.
  • Marsi, Erwin; Krahmer, Emiel. (2013) Automatic Tree Matching for Analysing Semantic Similarity in Comparable Text. Essential Speech and Language Technology for Dutch.
  • Marsi, Erwin; Moen, Hans; Bungum, Lars; Sizov, Gleb Valerjevich; Gambäck, Björn; Lynum, Andre. (2013) NTNU-CORE: Combining strong features for semantic similarity. Second Joint Conference on Lexical and Computational Semantics (*SEM), Volume 1: Proceedings of the Main Conference and the Shared Task: Semantic Textual Similarity.
  • Moen, Hans; Marsi, Erwin; Gambäck, Björn. (2013) Towards Dynamic Word Sense Discrimination with Random Indexing. Proceedings of the Workshop on Continuous Vector Space Models and their Compositionality.
  • Lynum, Andre; Marsi, Erwin; Bungum, Lars; Gambäck, Björn. (2012) Disambiguating Word Translations with Target Language Models. Text, Speech and Dialogue: 15th International Conference, TSD 2012, Brno, Czech Republic, September 3-7, 2012, Proceedings.