Gauch, S., and Smith, J.B. An Expert System for Automatic Query Reformulation. In Journal of the American Society of Information Science, 1993, 44 (3), 124-136. 223  Home/Search   Document Details and Download   Summary   Related Articles   Check

....user to conduct interactive searches over single documents; there is usually a tight loop between posing a query over an entire document collection and examining the results of that query. Furthermore, there has only been a limited amount of work on retrieving items smaller than an entire document [46, 16]. When these items (sentences, passages, etc. have been evaluated, they have been used primarily to augment the score of the document, rather than for independent retrieval [6, 71, 64] In some cases documents have been broken into smaller elements for evaluation against a query, but the total ....

....discussed within a text. Since the discussion of our features is frequently on the order of one or two sentences long and may be scattered throughout the text, we are not able to take advantage of the TextTiling methods. Gauch and Smith investigated the expansion of queries that retrieved passages [16]. Their corpus was a textbook on computer architecture and searchers were to locate sentences that were relevant to a set of five questions topics. They tested the ability of a domain specific semantic network used in conjunction with an expert system to refine queries. A third point of comparison ....

Gauch, Susan, and Smith, John B. An Expert System for Automatic Query Reformulation. Journal of the American Society of Information Scientists. 44, 3 (April 1993), 124--136.

....show that all three kinds of support are important and needed in user interfaces to information retrieval systems. Different modalities, though, should be adopted for delivering them. 2. User interfaces to IR systems A User Interface to an IR System (UIIRS) Ingwersen, 1992; Marchionini, 1992; Gauch and Smith, 1993] is a front end program which interacts with the user and controls an underlying information retrieval system accessing information resources. Its main goal is to empower the user with the capability to operate effectively without the need of an experienced human intermediary. The absence from ....

S. Gauch and J.B. Smith, An expert system for automatic query reformulation. Journal of the American Society for Information Science, 44(3), 1993, pp. 124--136.

.... feedback systems where the related terms come from the contents of user identified relevant documents have been shown to be quite effective [Harman, 1992] An expert system which automatically reformulated queries by including terms from an online thesaurus was also able to improve search results [Gauch Smith, 1993; Gauch Smith 1991] without requiring relevance judgments from the user. Some systems [Anick et al., 1990] present related terms to the user and allow them to selectively augment the query. However, the latter two approaches require the presence of an online thesaurus whose words closely match ....

....that information in an 3 vector space information retrieval system. We will modify and apply techniques from the field of corpus linguistics which seem particularly wellsuited for this task. These techniques may also prove useful for summarizing the contents of retrieval sets [Futrelle Gauch, 1993a] and for syntactic as well as semantic classification [Futrelle Gauch, 1993b] 2. Corpus Linguistics Approach Excellent methods have been developed for part of speech (POS) tagging using Markov models trained on partially tagged corpora [Church, 1988; Cutting, et al., 1992; Kupiec, 1992] ....

[Article contains additional citation context not shown here]

Gauch, S., & Smith, J.B. (1993). An Expert System for Automatic Query Reformulation. J. of the Amer. Society of Inf. Sci., 44 (3), 124-136.

.... contents of user identified relevant documents, have been shown to be quite effective (Harman 1992) Our earlier work showed that an expert system which automatically reformulated Boolean queries by including terms from an online thesaurus was able to improve search results (Gauch and Smith 1991; Gauch and Smith 1993) without requiring relevance judgments from the user. Some systems (Anick, Brennan et al. 1990) present related terms to the user and allow them to selectively augment the query. However, the latter two approaches require the presence of an online thesaurus whose words closely match the contents ....

Gauch, S., & Smith, J.B. (1993). An Expert System for Automatic Query Reformulation. J. of the Amer. Society of Inf. Sci., 44 (3), 124-136.

....expansion adds other terms related to the same concepts, providing a richer representation of the user s query. Our earlier work showed that an expert system which automatically reformulated Boolean queries by including terms from an online thesaurus was, indeed, able to improve search results [Gauch Smith, 1993]. But, where are the expansion terms to come from There are three main sources for related words which vary in their level of specificity: 1) query specific; 2) corpus specific; and 3) language specific. Query specific terms can be identified by locating new terms in a subset of the documents ....

Gauch, S., & Smith, J.B. (1993). An Expert System for Automatic Query Reformulation. J. of the Amer. Society of Inf. Sci., 44 (3), pp. 124-136.

.... contents of user identified relevant documents, have been shown to be quite effective (Harman 1992) Our earlier work showed that an expert system which automatically reformulated Boolean queries by including terms from an online thesaurus was able to improve search results (Gauch and Smith 1991; Gauch and Smith 1993) without requiring relevance judgments from the user. Some systems (Anick, Brennan et al. 1990) present related terms to the user and allow them to selectively augment the query. However, the latter two approaches require the presence of an online thesaurus whose words closely match the contents ....

Gauch, S., & Smith, J.B. (1993). An Expert System for Automatic Query Reformulation. J. of the Amer. Society of Inf. Sci., 44 (3), 124-136.

No context found.

Gauch, S., and Smith, J.B. An Expert System for Automatic Query Reformulation. In Journal of the American Society of Information Science, 1993, 44 (3), 124-136. 223

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC