N”. The plural hypernymy constraint (set-instance anaphora) The head of the
N”. The plural hypernymy constraint (set-instance anaphora) The head of the anaphoric NP is a plural hypernym of the antecedent, which corresponds to a conjunction of entities. This constraint accepts “CD1, CD2, and CD3” as antecedent for “these factors”. The meronymy constraint The head of the anaphoric NP is a meronym and the antecedent corresponds to a conjunction of entities. This constraint allows “IBR/F” as antecedent for the anaphoric NP “the dimer”. The event constraint The head of the anaphoric NP is associated with a trigger, P1, and the antecedent with another trigger, P2, where P1 and P2 are lexicalizations of the same event. This constraint aims to capture the coreference between, for instance, the anaphor the phosphorylation and the antecedent phosphorylated. We induced the hypernym list from the training corpus automatically PubMed ID:https://www.ncbi.nlm.nih.gov/pubmed/27741243 by considering the heads of the NPs with entities in modifier position. Such words include gene, protein, factor, and cytokine. Similarly, we induced the meronym list from the training data of the Static Relations supporting task [11]. These words essentially correspond to triggers for SUBUNIT-COMPLEX relations in that task, and include words such as complex, dimer, and subunit.Kilicoglu and Bergler BMC Bioinformatics 2012, 13(Suppl 11):S7 http://www.order MK-8742 biomedcentral.com/1471-2105/13/S11/SPage 14 ofSeveral structural constraints over the embedding graph block some of the possible antecedents for both coreference types: ?The antecedent directly embeds or is directly embedded by the anaphor. ?The antecedent is the subject and the anaphor is the object of the same relation. In addition, the anaphor is not reflexive (e.g., itself). ?The anaphor is in an adjunct position and the antecedent is in subject position of the same relation. The candidate that is closest to the anaphor in the embedding graph is selected as the antecedent and a COREF embedding relation is created between the anaphor and the antecedent. For plural anaphora, multiple entities or triggers may be considered as antecedents, and thus multiple COREF relations may be created. The integration of coreference information into the event extraction pipeline is trivial for all coreference types. In the composition phase, when an anaphoric expression appears in the argument position of a predication, it is naturally substituted by its antecedent(s) through argument propagation.Table 8 Official GENIA track resultsEvent Class Localization Binding Gene_expression Transcription Protein_catabolism Phosphorylation EVT-TOTAL Regulation Positive_regulation Negative_regulation REG-TOTAL Negation Speculation MOD-TOTAL ALL-TOTAL Recall 39.27 29.33 65.87 32.18 66.67 75.14 52.67 33.77 35.97 36.43 35.72 18.77 21.10 19.97 43.55 Precision 90.36 49.66 86.84 58.95 71.43 94.56 78.04 42.48 47.66 43.88 45.85 44.26 38.46 40.89 59.58 F1-score 54.74 36.88 74.91 41.64 68.97 83.73 62.90 37.63 41.00 39.81 40.16 26.36 27.25 26.83 50.32 Rank 7 7 5 9 2 4 6 3 7 5 5 2 1 2Official GENIA track results, with the approximate span matching/approximate recursive matching evaluation criteria.Results and discussion With the two-phase methodology presented above, we participated in three tracks: GENIA (Tasks 1 and 3), ID, and EPI. The official evaluation results we obtained for the GENIA track are presented in Table 8 and the results for the EPI and ID tracks in Table 9. With the official evaluation criteria, we were ranked 5th in the GENIA track (5/15), 7th in the EPI track (7/7) and 4th.
