Predicting Event Time by Classifying Sub-Level Temporal Relations Induced from a Unified Representation of Time Anchors

• URL: http://arxiv.org/abs/2008.06452v1
• Date: Fri, 14 Aug 2020 16:30:07 GMT
• Title: Predicting Event Time by Classifying Sub-Level Temporal Relations Induced from a Unified Representation of Time Anchors
• Authors: Fei Cheng and Yusuke Miyao
• Abstract summary: We propose an effective method to decompose complex temporal relations into sub-level relations. Our approach outperforms the state-of-the-art decision tree model.
• Score: 10.67457147373144
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Extracting event time from news articles is a challenging but attractive task. In contrast to the most existing pair-wised temporal link annotation, Reimers et al.(2016) proposed to annotate the time anchor (a.k.a. the exact time) of each event. Their work represents time anchors with discrete representations of Single-Day/Multi-Day and Certain/Uncertain. This increases the complexity of modeling the temporal relations between two time anchors, which cannot be categorized into the relations of Allen's interval algebra (Allen, 1990). In this paper, we propose an effective method to decompose such complex temporal relations into sub-level relations by introducing a unified quadruple representation for both Single-Day/Multi-Day and Certain/Uncertain time anchors. The temporal relation classifiers are trained in a multi-label classification manner. The system structure of our approach is much simpler than the existing decision tree model (Reimers et al., 2018), which is composed by a dozen of node classifiers. Another contribution of this work is to construct a larger event time corpus (256 news documents) with a reasonable Inter-Annotator Agreement (IAA), for the purpose of overcoming the data shortage of the existing event time corpus (36 news documents). The empirical results show our approach outperforms the state-of-the-art decision tree model and the increase of data size obtained a significant improvement of performance.

Related papers

• Dynamically Updating Event Representations for Temporal Relation Classification with Multi-category Learning [35.27714529976667]
  Temporal relation classification is a pair-wise task for identifying the relation of a temporal link (Tlink) between two mentions. This paper presents an event centric model that allows to manage dynamic event representations across multiple Tlink categories. Our proposal outperforms state-of-the-art models and two transfer learning baselines on both the English and Japanese data.
  arXiv  Detail & Related papers  (2023-10-31T07:41:24Z)
• TIMELINE: Exhaustive Annotation of Temporal Relations Supporting the Automatic Ordering of Events in News Articles [4.314956204483074]
  This paper presents a new annotation scheme that clearly defines the criteria based on which temporal relations should be annotated. We also propose a method for annotating all temporal relations -- including long-distance ones -- which automates the process. The result is a new dataset, the TIMELINE corpus, in which improved inter-annotator agreement was obtained.
  arXiv  Detail & Related papers  (2023-10-26T22:23:38Z)
• More than Classification: A Unified Framework for Event Temporal Relation Extraction [61.44799147458621]
  Event temporal relation extraction(ETRE) is usually formulated as a multi-label classification task. We observe that all relations can be interpreted using the start and end time points of events. We propose a unified event temporal relation extraction framework, which transforms temporal relations into logical expressions of time points.
  arXiv  Detail & Related papers  (2023-05-28T02:09:08Z)
• Continuous-time convolutions model of event sequences [53.36665135225617]
  Huge samples of event sequences data occur in various domains, including e-commerce, healthcare, and finance. The amount of available data and the length of event sequences per client are typically large, thus it requires long-term modelling. We propose the COTIC method based on a continuous convolution neural network suitable for non-uniform occurrence of events in time.
  arXiv  Detail & Related papers  (2023-02-13T10:34:51Z)
• MAVEN-ERE: A Unified Large-scale Dataset for Event Coreference, Temporal, Causal, and Subevent Relation Extraction [78.61546292830081]
  We construct a large-scale human-annotated ERE dataset MAVEN-ERE with improved annotation schemes. It contains 103,193 event coreference chains, 1,216,217 temporal relations, 57,992 causal relations, and 15,841 subevent relations. Experiments show that ERE on MAVEN-ERE is quite challenging, and considering relation interactions with joint learning can improve performances.
  arXiv  Detail & Related papers  (2022-11-14T13:34:49Z)
• Towards Similarity-Aware Time-Series Classification [51.2400839966489]
  We study time-series classification (TSC), a fundamental task of time-series data mining. We propose Similarity-Aware Time-Series Classification (SimTSC), a framework that models similarity information with graph neural networks (GNNs)
  arXiv  Detail & Related papers  (2022-01-05T02:14:57Z)
• Self-Supervised Time Series Representation Learning by Inter-Intra Relational Reasoning [18.72937677485634]
  We present SelfTime: a general self-supervised time series representation learning framework. We explore the inter-sample relation and intra-temporal relation of time series to learn the underlying structure feature on the unlabeled time series. The useful representations of time series are extracted from the backbone under the supervision of relation reasoning heads.
  arXiv  Detail & Related papers  (2020-11-27T04:04:17Z)
• Learning Informative Representations of Biomedical Relations with Latent Variable Models [2.4366811507669115]
  We propose a latent variable model with an arbitrarily flexible distribution to represent the relation between an entity pair. We demonstrate that our model achieves results competitive with strong baselines for both tasks while having fewer parameters and being significantly faster to train.
  arXiv  Detail & Related papers  (2020-11-20T08:56:31Z)
• Learning to Decouple Relations: Few-Shot Relation Classification with Entity-Guided Attention and Confusion-Aware Training [49.9995628166064]
  We propose CTEG, a model equipped with two mechanisms to learn to decouple easily-confused relations. On the one hand, an EGA mechanism is introduced to guide the attention to filter out information causing confusion. On the other hand, a Confusion-Aware Training (CAT) method is proposed to explicitly learn to distinguish relations.
  arXiv  Detail & Related papers  (2020-10-21T11:07:53Z)
• Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks [91.65637773358347]
  We propose a general graph neural network framework designed specifically for multivariate time series data. Our approach automatically extracts the uni-directed relations among variables through a graph learning module. Our proposed model outperforms the state-of-the-art baseline methods on 3 of 4 benchmark datasets.
  arXiv  Detail & Related papers  (2020-05-24T04:02:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.