The current leading perspective on temporal information As a first approach towards this goal, in this paper, extraction regards three phases: (1) a temporal we propose several initial time-line models in entity recognition phase, extracting events this paradigm, that directly predict - in a linear (blue boxes in Figure 1) and their attributes, and extracting fashion - start points and durations for each entity, temporal expressions (green boxes), and using text with annotated temporal entities as input normalizing their values to dates or durations, (2) (shown in Figure 1). The predicted start points and a relation extraction phase, where temporal links durations constitute a relative time-line, i.e. a total (TLinks) among those entities, and between events order on entity start and end points. The time-line and the document-creation time (DCT) are found is relative, as start and duration values cannot (yet) (arrows in Figure 1, left). And (3), construction of a be mapped to absolute calender dates or durations time-line (Figure 1, right) from the extracted temporal expressed in seconds. It represents the relative links, if they are temporally consistent. Much temporal order and inclusions that temporal entities research concentrated on the first two steps, but have with respect to each other by the quantitative very little research looks into step 3, time-line construction, start and end values of the entities. Relative which is the focus of this work.

Temporal relation classification is a pair-wise task for identifying the relation of a temporal link (TLINK) between two mentions, i.e. event, time, and document creation time (DCT). It leads to two crucial limits: 1) Two TLINKs involving a common mention do not share information. 2) Existing models with independent classifiers for each TLINK category (E2E, E2T, and E2D) hinder from using the whole data. This paper presents an event centric model that allows to manage dynamic event representations across multiple TLINKs. Our model deals with three TLINK categories with multi-task learning to leverage the full size of data. The experimental results show that our proposal outperforms state-of-the-art models and two transfer learning baselines on both the English and Japanese data.

For the past decade, temporal annotation has been sparse: only a small portion of event pairs in a text was annotated. We present NarrativeTime, the first timeline-based annotation framework that achieves full coverage of all possible TLinks. To compare with the previous SOTA in dense temporal annotation, we perform full re-annotation of TimeBankDense corpus, which shows comparable agreement with a significant increase in density. We contribute TimeBankNT corpus (with each text fully annotated by two expert annotators), extensive annotation guidelines, open-source tools for annotation and conversion to TimeML format, baseline results, as well as quantitative and qualitative analysis of inter-annotator agreement.

Time is deeply woven into how people perceive, and communicate about the world. Almost unconsciously, we provide our language utterances with temporal cues, like verb tenses, and we can hardly produce sentences without such cues. Extracting temporal cues from text, and constructing a global temporal view about the order of described events is a major challenge of automatic natural language understanding. Temporal reasoning, the process of combining different temporal cues into a coherent temporal view, plays a central role in temporal information extraction. This article presents a comprehensive survey of the research from the past decades on temporal reasoning for automatic temporal information extraction from text, providing a case study on the integration of symbolic reasoning with machine learning-based information extraction systems.

Time is deeply woven into how people perceive, and communicate about the world. Almost unconsciously, we provide our language utterances with temporal cues, like verb tenses, and we can hardly produce sentences without such cues. Extracting temporal cues from text, and constructing a global temporal view about the order of described events is a major challenge of automatic natural language understanding. Temporal reasoning, the process of combining different temporal cues into a coherent temporal view, plays a central role in temporal information extraction. This article presents a comprehensive survey of the research from the past decades on temporal reasoning for automatic temporal information extraction from text, providing a case study on how combining symbolic reasoning with machine learning-based information extraction systems can improve performance. It gives a clear overview of the used methodologies for temporal reasoning, and explains how temporal reasoning can be, and has been successfully integrated into temporal information extraction systems. Based on the distillation of existing work, this survey also suggests currently unexplored research areas. We argue that the level of temporal reasoning that current systems use is still incomplete for the full task of temporal information extraction, and that a deeper understanding of how the various types of temporal information can be integrated into temporal reasoning is required to drive future research in this area.