Linguistically-motivated Information Retrieval

Linguistically-motivated Information Retrieval Csi-r9918 September

$YWRPDWVNR OXãþHQMH L]UD]MD L] VORYHQVNR-angleških vzporednih besedil

The paper describes the design and structure of a Slovene-English term extraction system. Although the state-of-the-art systems operate on hybrid approaches using various levels of linguistic analysis, sometimes including semantic information, the aim here was to implement both statistical and linguistically motivated methods for both languages and compare the results. It is shown that some met...

What is the role of NLP in text retrieval?

This paper addresses the value of linguistically-motivated indexing (LMI) for document and text retrieval. After reviewing the basic concepts involved and the assumptions on which LMI is based, namely that complex index descriptions and terms are necessary, I consider past and recent research on LMI, and specifically on automated LMI via NLP. Experiments in the first phase of research, to the l...

Using Linguistically Motivated Features in Document Retrieval for Question Answering

5 Publications Arising from this Work 11

Towards the development of heuristics

In this paper we study the performance of linguistically-motivated connation techniques for Information Retrieval in Spanish. In particular, we have studied the application of productive derivational morphology for single word term connation and the extraction of syntactic dependency pairs for multi-word term connation. These techniques have been tested on several search engines implementing di...