Learn More
In this report, we study the effects of lexical analysis on Marathi monolingual search over the news domain corpus (obtained through FIRE-2008). Specifically, we observe the effect of processes such as lemmatization, inclusion of suffixes in indexing and stop-words elimination on the retrieval performance. The results show that lemmatization significantly(More)
In this paper, we present our work on the classical problem of prepositional phrase attachment. This forms part of an interlingua based machine translation system, in which the semantics of the source language sentences is captured in the form of Universal Networking Language (UNL) expressions. We begin with a thorough linguistic analysis of six common(More)
In this paper we describe Agro Explorer, a language independent search engine with multilingual information access facility. Instead of searching on plain text it does the search on the meaning representation, an Interlingua form called Universal Networking Language (UNL) expressions. Most of the current search engines(e.g. Google, Altavista, Yahoo) are(More)
This project largely deals with the prepositional phrase attachment problem and generation of semantic relations, which are difficult problems in the field of natural language processing. In this work we looked at it through the knowledge based perspective, i.e., by encoding the world knowledge and language phenomena in terms of rules and dictionary(More)
'To' is one of the most common lexemes in English (as found in 34% of the sentences in the Penn Tree Bank corpus). This paper describes the analysis of the sentences involving `to'. `To' poses problems at lexical, syntactic and semantic level, as we need to resolve whether the phrase which is fronted by `to' is a prepositional phrase (PP) or an infinitival(More)
  • 1