Improving Implicit Semantic Role Labeling by Predicting Semantic Frame Arguments
This work addresses the challenge of predicting implicit semantic roles in natural language processing, which is important for tasks like discourse understanding, but it appears incremental as it builds on existing iSRL methods with a novel model.
The paper tackles the problem of implicit semantic role labeling (iSRL) by introducing a predictive recurrent neural semantic frame model (PRNSFM) that learns from unannotated data to predict semantic arguments, resulting in improved state-of-the-art performance on the NomBank iSRL test set with reduced reliance on manual resources.
Implicit semantic role labeling (iSRL) is the task of predicting the semantic roles of a predicate that do not appear as explicit arguments, but rather regard common sense knowledge or are mentioned earlier in the discourse. We introduce an approach to iSRL based on a predictive recurrent neural semantic frame model (PRNSFM) that uses a large unannotated corpus to learn the probability of a sequence of semantic arguments given a predicate. We leverage the sequence probabilities predicted by the PRNSFM to estimate selectional preferences for predicates and their arguments. On the NomBank iSRL test set, our approach improves state-of-the-art performance on implicit semantic role labeling with less reliance than prior work on manually constructed language resources.