Verginica Barbu Mititelu

A trainable multi-factored QA system

This paper reports on the construction and testing of a new Question Answering (QA) system, implemented as an workflow which builds on several web services developed at the Research Institute for Artificial Intelligence (RACAI).The evaluation of the system has been independently done by the organizers of the Romanian-Romanian task of the ResPubliQA 2009 exercise and has been rated the best performing system with the highest improvement due to the NLP technology over a baseline state-of-the-art IR system. We describe a principled way of combining different relevance measures for obtaining a general relevance (to the users question) score that will serve as the sort key for the returned paragraphs. The system was trained on a specific corpus, but its functionality is independent on the linguistic register of the training data. The trained QA system that participated in the ResPubliQA shared task is available as a web application at http://www2.racai.ro/sir-resdec/.

A data-driven approach to verbal multiword expression detection. PARSEME Shared Task system description paper

Multiword expressions are groups of words acting as a morphologic, syntactic and semantic unit in linguistic analysis. Verbal multiword expressions represent a subgroup of multiword expressions, namely that in which a verb is the syntactic head of the group considered in its canonical (or dictionary) form. All multiword expressions are a great challenge for natural language processing, but the verbal ones are particularly interesting for tasks such as parsing, as the verb is the central element in the syntactic organization of a sentence. In this paper we introduce our data-driven approach to verbal multiword expressions, which was objectively validated during the PARSEME shared task on verbal multiword expressions identification. We tested our approach on 12 languages, and we provide detailed information about corpora composition, feature selection process, validation procedure and performance on all languages.

The Lexical Ontology for Romanian

Lexical resources have taken different forms throughout time. Nowadays, they occur in forms serving several types of users: the traditional human user, the modern human users and the computer. This last type of user explains the appearance of lexical knowledge representation forms, with semantic networks as one of the most frequently used forms. We present here the semantic network for Romanian. It was created primarily for use in various applications involving natural language: question answering, document and word-alignment, parallel data extraction from comparable documents, machine translation. During its exploitation, several inaccuracies were detected and consistent cleaning steps were necessary due to errors from the initial construction phase (typos in the definitions, alternation of the old and new orthography, duplicate entries, semantic conflicts) or were required by the mapping to the new versions of Princeton WordNet. The first proper content extension was in-line importing of the SUMO/MILO concept labels, via the alignment to the Princeton WordNet. A second extension was the association of each synset with a connotation vector, a representation of the multifactorial meaning variation, according to a generalized Osgoodian methodology. Recently, we started to add a series of new lexical relations (language specific) based on an in-depth analysis of the Romanian derivational morphology. In the end of the paper we present the results of a word sense disambiguation algorithm based on wordnets.