Towards unsupervised learning of temporal relations between events

DOI10.1613/JAIR.3693MaRDI QIDQ3143570zbMATH OpenOpenAlexFDO

Authors Seyed Abolghasem Mirroshandel, Gholamreza Ghassem-Sani

Publication date 3 December 2012

Published in Journal of Artificial Intelligence Research (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1401.6427

zbMATH Keywords

classificationclusterexpectation maximizationinformation extractiontemporal relationsunsupervised learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Pattern recognition, speech recognition (68T10) Natural language processing (68T50)

Abstract: Automatic extraction of temporal relations between event pairs is an important task for several natural language processing applications such as Question Answering, Information Extraction, and Summarization. Since most existing methods are supervised and require large corpora, which for many languages do not exist, we have concentrated our efforts to reduce the need for annotated data as much as possible. This paper presents two different algorithms towards this goal. The first algorithm is a weakly supervised machine learning approach for classification of temporal relations between events. In the first stage, the algorithm learns a general classifier from an annotated corpus. Then, inspired by the hypothesis of "one type of temporal relation per discourse, it extracts useful information from a cluster of topically related documents. We show that by combining the global information of such a cluster with local decisions of a general classifier, a bootstrapping cross-document classifier can be built to extract temporal relations between events. Our experiments show that without any additional annotated data, the accuracy of the proposed algorithm is higher than that of several previous successful systems. The second proposed method for temporal relation extraction is based on the expectation maximization (EM) algorithm. Within EM, we used different techniques such as a greedy best-first search and integer linear programming for temporal inconsistency removal. We think that the experimental results of our EM based algorithm, as a first step toward a fully unsupervised temporal relation extraction method, is encouraging.

Recommendations

• Learning sentence-internal temporal relations
• Integer programming ensemble of temporal relations classifiers
• Evaluating temporal graphs built from texts via transitive reduction
• scientific article; zbMATH DE number 1974007
• Acquisition of part-whole relations based on unsupervised learning

Cited in

(11)

• Semi-supervised approach to event time annotation using longitudinal electronic health records
• Integer programming ensemble of temporal relations classifiers
• Multi-task transfer learning for timescale graphical event models
• Estimating timestamp from incomplete news corpus
• Evaluating temporal graphs built from texts via transitive reduction
• Learning sentence-internal temporal relations
• Unsupervised methods for determining object and relation synonyms on the web
• Acquisition of part-whole relations based on unsupervised learning
• Joint Chinese event extraction based multi-task learning
• Event inference for semi-supervised Chinese event extraction
• Unsupervised Learning of Temporal Abstractions With Slot-Based Transformers

This page was built for publication: Towards unsupervised learning of temporal relations between events

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3143570)