A Sequential Model for Classifying Temporal Relations between Intra-Sentence Events
This work addresses the challenge of fine-grained temporal relation classification in natural language processing, representing an incremental improvement over previous feature-based methods.
The paper tackles the problem of classifying temporal relations between intra-sentence events by proposing a sequential model that uses bidirectional LSTM networks to learn syntactic and semantic representations from context sequences. The result shows that this approach outperforms a neural net model based on discrete features on the TimeBank corpus.
We present a sequential model for temporal relation classification between intra-sentence events. The key observation is that the overall syntactic structure and compositional meanings of the multi-word context between events are important for distinguishing among fine-grained temporal relations. Specifically, our approach first extracts a sequence of context words that indicates the temporal relation between two events, which well align with the dependency path between two event mentions. The context word sequence, together with a parts-of-speech tag sequence and a dependency relation sequence that are generated corresponding to the word sequence, are then provided as input to bidirectional recurrent neural network (LSTM) models. The neural nets learn compositional syntactic and semantic representations of contexts surrounding the two events and predict the temporal relation between them. Evaluation of the proposed approach on TimeBank corpus shows that sequential modeling is capable of accurately recognizing temporal relations between events, which outperforms a neural net model using various discrete features as input that imitates previous feature based models.