Negated bio-events: analysis and identification

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.

Conclusions: 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.

Figure 1

Typical structured representation of the bio-event contained in the above sentence.

Figure 2

A simple hypothetical sentence with complex event structure.

Figure 3

Inherently negative bio-event example (Source: GENIA Event Corpus; PMID: 9427533).

Figure 4

Bio-event example with negated event-trigger (Source: GENIA Event Corpus; PMID: 10022882).

Figure 5

Bio-event example with negated participant (Source: GENIA Event Corpus; PMID: 10358173).

Figure 6

Bio-event example with negated attribute (Source: BioNLP ST Corpus; PMID: 10022882).

Figure 7

Bio-event example with comparison and contrast (Source: GENIA Event Corpus; PMID: 10079106).

Figure 8

An instance of the word loss with positive contextual (biological) polarity; Source = PMID: 10202937.

Figure 9

An instance of the low manner indicator little being treated as a negation cue; Source = PMID: 20562282.

Figure 10

An instance of negation triggered by the construction no evidence; Source = PMID: 10221643.

Figure 11

Cue list comparison: Micro-averaged results for the three datasets.

Figure 12

Algorithm comparison: Micro-averaged results for the three datasets.