Syntactic sentence compression in the biomedical domain: facilitating access to related articles

Abstract

We explore a syntactic approach to sentence compression in the biomedical domain, grounded in the context of result presentation for related article search in the PubMed search engine. By automatically trimming inessential fragments of article titles, a system can effectively display more results in the same amount of space. Our implemented prototype operates by applying a sequence of syntactic trimming rules over the parse trees of article titles. Two separate studies were conducted using a corpus of manually compressed examples from MEDLINE: an automatic evaluation using BLEU and a summative evaluation involving human assessors. Experiments show that a syntactic approach to sentence compression is effective in the biomedical domain and that the presentation of compressed article titles supports accurate ''interest judgments'', decisions by users as to whether an article is worth examining in more detail.

AnnoPharma: Detection of substances responsible of ADR by annotating and extracting information from MEDLINE abstracts

“…In the other side VigiTermes has 67% Precision and 77% Recall. 2 We explain the higher recall by the correctly detection of concepts. For example we recognize the chronicle form of Carbamazepine (CBZ) 8 times.…”

“…MEDLINE contains actually articles related to biomedicine and health, but also encompasses those of the life sciences, chemical sciences, behavioral sciences, and bioengineering needed by health professionals interested to researches and clinical care, public health, etc. [2] All articles in MEDLINE are indexed and annotated manually to give the user a brief idea about the article and to highlight most important terms.…”

Trends in Multi-document Summarization System Methods

“…Also, it is deduced that syntactic based compression does not improve a generic summarization system [27,28,29,31] when evaluated by state-of-the-art standard but can achieve better performance if semantic role information can be incorporated into the model.…”

Leveraging structural relations for fluent compressions at multiple compression rates

“…Sentence compression systems have been tested on product review data from the Ziff-Davis (ZD, henceforth) Corpus by Knight and Marcu (2000), general news articles by Clarke and Lapata (CL, henceforth) corpus (2007) and biomedical articles (Lin and Wilbur, 2007). To evaluate our system, we used 2 test sets: Set 1 contained 50 sentences; all 32 sentences from the ZD test set and 18 additional sentences chosen randomly from the CL test set; Set 2 contained 40 sentences selected from the CL corpus, 20 of which were compressed at 75% of GSCR and 20 at 50% of GSCR (the percentages denote the enforced compression rates The example below has compressions at 50% compression rate for M06 and ARC systems:…”