Research Summary: Intelligent Natural Language Processing Techniques and Tools
My research path started with my master thesis (supervisor Prof. Stefania Costantini) about a neurobiologically-inspired proposal in the field of natural language processing. In more detail, we proposed the “Semantic Enhanced DCGs” (for short SE-DCGs) extension to the well-known DCG’s to allow for parallel syntactic and semantic analysis, and generate semantically-based description of the sentence at hand. The analysis carried out through SE-DCG’s was called “syntactic-semantic fully informed analysis”, and it was designed to be as close as possible (at least in principle) to the results in the context of neuroscience that I had revised and studied. As proof-of-concept, I implemented the prototype of semantic search engine, the Mnemosine system. Mnemosine is able to interact with a user in natural language and to provide contextual answer at different levels of detail. Mnemosine has been applied to a practical case-study, i.e., to the WikiPedia Web pages. A brief overview of this work was presented during CICL 08 .
- 1.S. Costantini, Paolucci, A.: Semantically augmented dcg analysis for next-generation search engineGoogle Scholar
- 2.Bos, J., Markert, K.: Recognising textual entailment with logical inference, pp. 628–635 (2005)Google Scholar
- 3.Baral, C., Dzifcak, J., Son, T.C.: Using answer set programming and lambda calculus to characterize natural language sentences with normatives and exceptions, 818–823 (2008)Google Scholar
- 4.Moldovan, D.I., Harabagiu, S.M., Girju, R., Morarescu, P., Lacatusu, V.F., Novischi, A., Badulescu, A., Bolohan, O.: Lcc tools for question answering, TRECGoogle Scholar