Shamima Mithun

Exploiting rhetorical relations in blog summarization

With the goal of developing an efficient query-based opinion summarization approach, we have targeted to resolve Question Irrelevancy and Discourse Incoherency problems which have been found to be the most frequently occurring problems for opinion summarization To address these problems, we have utilized rhetorical relations of texts with the help of text schema and Rhetorical Structure Theory (RST).

Resolving Quantifier and Number Restriction to Question OWL Ontologies

This paper describes an approach to resolve quantifiers and number restrictions in natural language questions to query ontologies. Incorporating this feature enables natural language query interfaces to capture a wider range of user queries. To deal with quantifiers and number restrictions, we analyzed a corpus of such questions and derived constraints at the syntactic level to recognize and parse them. The approach was implemented and evaluated through a system called ONLI+. Our method has been evaluated by conducting different experiments using the mean reciprocal rank (MRR) measure. Experimental results show that this feature has been incorporated into ONLI+ without degrading its performance in terms of transforming natural language queries into the nRQL queries, but definitely increases the expressivity of the user. To the best of our knowledge no other natural language interface to query ontologies can deal with quantifiers and number restrictions.

Comparing approaches to tag discourse relations

It is widely accepted that in a text, sentences and clauses cannot be understood in isolation but in relation with each other through discourse relations that may or may not be explicitly marked. Discourse relations have been found useful in many applications such as machine translation, text summarization, and question answering; however, they are often not considered in computational language applications because domain and genre independent robust discourse parsers are very few. In this paper, we analyze existing approaches to identify five discourse relations automatically (namely, comparison, contingency, illustration, attribution, and topic-opinion), and propose a new approach to identify attributive relations. We evaluate the accuracy of each approach with respect to the discourse relations it can identify and compare it to a human gold standard. The evaluation results show that the state of the art systems are rather effective at identifying most of the relations considered, but other relations such as attribution are still not identified with high accuracy.