| 
|
QuoteRef: krovR4_1992
topics >
all references >
ThesaHelp:
references i-l
ThesaHelp:
ACM references f-l
Topic:
problem of assigning names
Topic:
information retrieval with an index
Topic:
semantic networks
Topic:
alias names
Topic:
thesaurus and information retrieval
Topic:
dictionary for natural language
Topic:
names defined by context
Topic:
information retrieval with queries
Topic:
information retrieval by relevance
Reference
Krovetz, R., Croft, W.B., "Lexical ambiguity and information retrieval", ACM Transactions on Information Systems, 10, 2, pp. 115-141, April 1992. Google
116 ;;Quote: words are ambiguous and a document can be relevant without using words from the query; concepts more important
116 ;;Quote: a thesaurus represents the relations between word senses rather than words; be careful when expanding query words with a thesaurus
119 ;;Quote: collocation and syntax identified the senses of "danger" in approximately 70% of the examined cases
119 ;;Quote: people can often disambiguate words with only a few words of context, and frequently, only one word is needed
121 ;;Quote: developing a lexicon for disambiguation is expensive; e.g., 8 person-years for 5,000 words
124 ;;Quote: query words are more ambiguous than words in a document
124 ;;Quote: better information retrieval if weight words by frequency of use
124+;;Quote: TF.IDF weighting for query words uses the frequency of a term in the document and its inverse frequency in the collection
138 ;;Quote: no clear advantage for weighting query words by the number of senses they have
139 ;;Quote: query word sense mismatches are far more likely to appear in nonrelevant documents than for relevant documents
ThesaHelp: references i-l (342 items)
ThesaHelp: ACM references f-l (241 items)
Topic: problem of assigning names (25 items)
Topic: information retrieval with an index (32 items)
Topic: semantic networks (42 items)
Topic: alias names (39 items)
Topic: thesaurus and information retrieval (29 items)
Topic: dictionary for natural language (41 items)
Topic: names defined by context (36 items)
Topic: information retrieval with queries (18 items)
Topic: information retrieval by relevance (32 items)