[Corpora-List] New publication about analysis and identification of negated bio-events in literature

Fri Jan 18 10:41:44 UTC 2013

Dear Anita,

Thank you for your email and your interest in our paper.

We would certainly be very interested to compare our algorithm to BioNOT in the future, although unfortunately we do not have a public version of our system available at present.

It should be noted that there is a difference between our system and the BioNOT system, i.e., the BioNOT system detects negated sentences, whilst our system detects negated bio-events, the latter of which correspond to particular biological processes. Thus, our system helps to detect exactly which information within a sentence is negated.  It may therefore be the case that a sentence may contain negation terms, but that no bio-events will be negated.  It would certainly be interesting to discover the proportion of sentences that are marked as negated by BioNOT actually contain negated bio-events, and investigate whether the output of BioNOT could be used to further improve the results of detecting negated bio-events.

Best wishes,

Paul

On 17 Jan 2013, at 19:57, anita bandrowski wrote:

Thanks for the interesting link, this is a very interesting paper.
I wonder how the algorithm does head to head against BioNOT?
https://neuinfo.org/mynif/search.php?q=%22Cerebellum%20neuron%22&t=indexable&nif=nlx_143912-1&b=0&r=20

Looks like this comparison is not made in the paper, but would be quite interesting.

The negated statements in BioNOT are certainly fun to play with, but the typical issues of false positives/negatives are present such as NO (as in nitric oxide) being flagged as indicative of a negated statement. Is there a place I can play with these data?

Best,
anita

On Thu, Jan 17, 2013 at 2:11 AM, Paul Thompson <Paul.Thompson at manchester.ac.uk<mailto:Paul.Thompson at manchester.ac.uk>> wrote:

Raheel Nawaz, Paul Thompson and Sophia Ananiadou

"Negated bio-events: analysis and identification"

BMC Bioinformatics 2013, 14:14

http://www.biomedcentral.com/1471-2105/14/14/

doi:10.1186/1471-2105-14-14

Abstract

========

Background

----------------

Negation occurs frequently in scientific literature, especially in biomedical literature. It has previously been reported that around 13% of sentences found in biomedical research articles contain negation. Historically, the main motivation for identifying negated events has been to ensure their exclusion from lists of extracted interactions. However, recently, there has been a growing interest in negative results, which has resulted in negation detection being identified as a key challenge in biomedical relation extraction. In this article, we focus on the problem of identifying negated bio-events, given gold standard event annotations.

Results

----------

We have conducted a detailed analysis of three open access bio-event corpora containing negation information (i.e., GENIA Event, BioInfer and BioNLP'09 ST), and have identified the main types of negated bio-events. We have analysed the key aspects of a machine learning solution to the problem of detecting negated events, including selection of negation cues, feature engineering and the choice of learning algorithm. Combining the best solutions for each aspect of the problem, we propose a novel framework for the identification of negated bio-events. We have evaluated our system on each of the three open access corpora mentioned above. The performance of the system significantly surpasses the best results previously reported on the BioNLP'09 ST corpus, and achieves even better results on the GENIA Event and BioInfer corpora, both of which contain more varied and complex events.

Conclusion

---------------

Recently, in the field of biomedical text mining, the development and enhancement of event-based systems has received significant interest. The ability to identify negated events is a key performance element for these systems. We have conducted the first detailed study on the analysis and identification of negated bio-events. Our proposed framework can be integrated with state-of-the-art event extraction systems. The resulting systems will be able to extract bio-events with attached polarities from textual documents, which can serve as the foundation for more elaborate systems that are able to detect mutually contradicting bio-events.

--------

Paul Thompson
Research Associate
School of Computer Science
National Centre for Text Mining
Manchester Institute of Biotechnology
University of Manchester
131 Princess Street
Manchester
M1 7DN
UK
Tel: 0161 306 3091
http://personalpages.manchester.ac.uk/staff/Paul.Thompson/

--
Anita Bandrowski, Ph.D.
NIF Project Lead
UCSD 858-822-3629
http://neuinfo.org<http://neuinfo.org/>
9500 Gillman Dr.#0446
la Jolla, CA 92093-0446

--------

Paul Thompson
Research Associate
School of Computer Science
National Centre for Text Mining
Manchester Institute of Biotechnology
University of Manchester
131 Princess Street
Manchester
M1 7DN
UK
Tel: 0161 306 3091
http://personalpages.manchester.ac.uk/staff/Paul.Thompson/

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://listserv.linguistlist.org/pipermail/corpora/attachments/20130118/6b984670/attachment.htm>
-------------- next part --------------
_______________________________________________
UNSUBSCRIBE from this page: http://mailman.uib.no/options/corpora
Corpora mailing list
Corpora at uib.no
http://mailman.uib.no/listinfo/corpora