Head/Modifier Frames for Information Retrieval
نویسنده
چکیده
We describe a principled method for representing documents by phrases abstracted into Head/Modifier pairs. First the notion of aboutness and the characterization of full-text documents by HM pairs is didcussed. Based on linguistic arguments, a taxonomy of HM pairs is derived. We briefly describe the EP4IR parser/transducer of English and present some statistics of the distribution of HM pairs in newspaper text. Based on the HM pairs generated, a new technique to measure the accuracy of a parser is introduced, and applied to the EP4IR grammar of English. Finally we discuss the merits of HM pairs and HM trees as a document representation.
منابع مشابه
Syntactic and pseudo-syntactic approaches for text retrieval
We study how the use of syntactic information can improve the performance of Information Retrieval systems based on single-word terms. We consider two different approaches. The first one identifies the syntactic structure of the text by means of a shallow parser in order to extract the head-modifier pairs of the most relevant syntactic dependencies, which are used as complex
متن کاملPublic Transport Ontology for Passenger Information Retrieval
Passenger information aims at improving the user-friendliness of public transport systems while influencing passenger route choices to satisfy transit user’s travel requirements. The integration of transit information from multiple agencies is a major challenge in implementation of multi-modal passenger information systems. The problem of information sharing is further compounded by the multi-l...
متن کاملCompound Event Nouns of the 'Modifier-head' Type in Mandarin Chinese
Event nouns can lexically encode eventive information. Recently these nouns have generated considerable scholarly interest. However, little research has been conducted in their morphological and syntactic structure, qualia modification, event representing feature, and information inheritance characteristics. This study has these main findings. 1) Morphologically, the modifier and the head is ei...
متن کاملThe Effect of Syntactic Phrase Indexing on Retrieval Performance for Dutch Texts
In this paper we describe an experiment with syntactic phrase indexing for Dutch texts. We compare different choices for combining terms to form head-modifier pairs and we also investigate the effect of adding none, one, or all constituent parts of the pair as a separate index term. The results of our experiments show that using head-modifier pairs as index terms can improve both recall and pre...
متن کاملUtilisation des syntagmes nominaux dans un système de recherche d'information en langue arabe
We present in this paper an approach to extract and structure noun phrases from text corpora. The proposed structure is based on a syntax network (head-modifier relationship) and association rules (text mining). We present the elements to be taken into account during the textual documents analysis and we detail the process used. By an experimentation, we show the effect of using the structure a...
متن کامل