Despite the semantic similarity between these two events, their event-argument relations to the Gene Expression event are syntactically different (Fig. These annotations are justifiable with respect to the meaning of these phrases, but there are alternatives, including one where the phrase ‘increased’ becomes the trigger of the Positive Regulation event.
The phrases ‘decreased’ and ‘increased numbers’ are annotated as event triggers of Negative and Positive Regulation events, respectively, that take a Gene Expression event with the event trigger ‘express’. express either decreased or increased numbers of VDR. We note that this paper reports an extension of our previous work with detailed discussions and more experimental results.įor example, consider sentence (1) from the training corpora, where the annotated event triggers are set in bold-face. In this study, we look into this possibility with the corpora provided by the 2009 BioNLP shared task. We anticipate that adjustments to event annotations to reduce such inconsistencies would lead to a meaningfully improved performance of even the state-of-the-art event extraction systems.
That is, there would be similar phrases where the span of their counterparts of event triggers is differently annotated, and as a result, such event triggers are syntactically characterized in a different way, suggesting a possibility that a statistical learning algorithm is hard to generalize from such event triggers that are similar, but differently annotated in a training corpus. Because of the ambiguity, these gold-standard corpora would manifest inconsistencies across the span of event triggers. Inspecting such corpora, we observed some cases where there is residual ambiguity in the span of event triggers (e.g., “transcriptional activity” vs. The readers are referred to if the tasks are not familiar.
Current state-of-the-art approaches to biological event extraction train statistical models in a supervised learning manner on annotated corpora, where event triggers, or the expressions indicative of events, and event-argument relations, or relations between events and their participant, are annotated (e.g., ).
0 kommentar(er)
