Classifying Temporal Relations by Bidirectional LSTM over Dependency Paths

Abstract

Temporal relation classification is becoming an active research field. Lots of methods have been proposed, while most of them focus on extracting features from external resources. Less attention has been paid to a significant advance in a closely related task: relation extraction. In this work, we borrow a state-of-the-art method in relation extraction by adopting bidirectional long short-term memory (Bi-LSTM) along dependency paths (DP). We make a "common root" assumption to extend DP representations of cross-sentence links. In the final comparison to two stateof-the-art systems on TimeBank-Dense, our model achieves comparable performance, without using external knowledge and manually annotated attributes of entities (class, tense, polarity, etc.).

Joint Event and Temporal Relation Extraction with Shared Representations and Structured Prediction

“…annotated temporal relation corpora with all events and relations fully annotated is reported to be a challenging task as annotators could easily overlook some facts (Bethard et al, 2007;Ning et al, 2017), which made both modeling and evaluation extremely difficult in previous event temporal relation research. The TB-Dense dataset mitigates this issue by forcing annotators to examine all pairs of events within the same or neighboring sentences, and it has been widely evaluated on this task Ning et al, 2017;Cheng and Miyao, 2017;Meng and Rumshisky, 2018). Recent data construction efforts such as MATRES (Ning et al, 2018a) further enhance the data quality by using a multi-axis annotation scheme and adopting a startpoint of events to improve inter-annotator agreements.…”

Embedding Time Expressions for Deep Temporal Ordering Models

“…We improve upon the model architecture proposed by Cheng and Miyao (2017) for temporal relation extraction, which involves classifying the temporal relation between a given pair of events e 1 and e 2 . Our proposed architecture is outlined in Figure 1.…”

“…The parameters are shared between these lower biL-STMs for the two sentences. Prior work (Cheng and Miyao, 2017) does not include these lower biLSTMs and only leverages the dependency encoding, explained next.…”

“…Inferring temporal event order is challenging as it often disagrees with the narrative order in text. Past work on temporal relation extraction has exploited cues such as global constraints on the temporal graph structure (Bramsen et al, 2006;Chambers and Jurafsky, 2008;Ning et al, 2017), world knowledge (Ning et al, 2018b), grouping of events (Tourille et al, 2017), or fusing these cues more effectively with deep models (Meng et al, 2017;Cheng and Miyao, 2017). One key component of temporal understanding is time expressions (timexes) that help anchor events to the time axis, but few recent systems effectively use the knowledge derivable from time expressions in their models.…”

Temporal Information Extraction by Predicting Relative Time-lines

“…Since then, much research focused on further improving the pairwise classification models, by exploring different types of classifiers and features, such as (among others) logistic regression and support vector machines (Bethard, 2013;Lin et al, 2015), and different types of neural network models, such as long short-term memory networks (LSTM) (Tourille et al, 2017;Cheng and Miyao, 2017), and convolutional neural networks (CNN) (Dligach et al, 2017). Moreover, different sievebased approaches were proposed Mirza and Tonelli, 2016), facilitating mixing of rule-based and machine learning components.…”