Number of found records: 40
|
CRAVEN, Timothy C. |
|
Sentence dependency structures in abstracts |
|
Library and Information Science Research, 1988, vol. 10, n. 4, pp. 401-410 |
|
On line (11/05/2005) |
|
A collection of 87 non-formulaic abstracts was analysed for structures of semantic dependency between sentences. According to this analysis, 26 of the abstracts contained at least one sentence that was dependent upon more than one other sentence for its meaning. But the automatic structural simplification, based upon an assumption about the use of the dependency structure, allowed the structures of all but 6 abstracts to be represented as trees. At least some degree of branching was found in the structures of 58 of the abstracts, a number reduced to 35 by automatic simplification. (AU) |
|
Technical services; Information storage and retrieval; Information work; Subject indexing; Terms; Staff relations; Semantic relations; Sentences; Abstracts |
Assessment |
|
|
|
|
D’AVANZO, Ernesto; MAGNINI, Bernardo; VALLIN, Alessandro |
|
Keyphrase Extraction for Summarization Purposes: The LAKE System at DUC-2004 |
|
PDF |
|
We report on ITC-irst participation at Task 1 (very short document summaries) at DUC-2004. We propose to exploit a keyphrase extraction methodology in order to identify relevant terms in the document. The LAKE algorithm first considers a number of linguistic features to extract a list of well motivated candidate keyphrases, then uses a machine learning framework to select significant keyphrases for a document. With respect to other approaches to keyphrase extraction, LAKE makes use of linguistic processors such as multiword and named entities recognition, which are not usually exploited (AU) |
|
extraction; summarization; LAKE |
Assessment |
|
|
|
|
GEORGANTOPOULOS, Byron |
|
MSc in Speech and Language Processing Dissertation: Automatic summarising based on sentence extraction: A statistical approach |
|
On line (11/05/2005) |
|
The present dissertation and project describes a system for automatic summarising of texts. Instead of generating abstracts, a hard NLP task of questionable effectiveness, the system tries to identify the most important sentences of the original text, thus producing an extract. The proposed, corpus-based and statistical approach exploits several heuristics to determine the summary-worthiness of sentences. It actually uses statistical appearances of words, word-pairs and noun phrases to calculate sentence weights and then extract the highest scoring sentences. The statistical model used in the scoring function is a slight variation of the Term-Frequency Inverse-Document-Frequency (TFIDF) term weighting formula. The results obtained by application of the system to 5 test texts, separately and cumulatively for the three afore-mentioned heuristics were subjectively judged for their quality. This evaluation showed that the noun phrases, as a separate method, produce the best extracts and that they also are parts of the best performing combinations. (AU) |
|
automatic summarization; |
Assessment |
|
|
|
|
JOHNSON, F.C. |
|
Automatic abstracting research |
|
Library Review, 1995, vol. 44, n. 8, pp.28-36 |
|
On line (11/05/2005) |
|
Part of an issue published as a Festschrift to mark the retirement of Anthony Wood as Head of the Department of Library and Information Studies at Manchester Metropolitan University, UK. Discusses the attraction for researchers of the prospect of automatically generating abstracts but notes that the promise of superseding the human effort has yet to be realized. Notes ways in which progress in automatic abstracting research may come about and suggests a shift in the aim from reproducing the conventional benefits of abstracts to accentuating the advantages to users of the computerized representation of information in large textual databases. (DB) |
|
Automatic abstracting; Research |
Assessment |
|
|
|
|
