Event and Temporal Information Extraction towards Timelines of Wikipedia Articles
نویسنده
چکیده
This paper explores the task of creating a timeline for historical Wikipedia articles, such as those describing wars, battles, and invasions. It focuses on extracting only the major events from the article, particularly those associated with an absolute date. Existing tools extract all possible events, while we write tools to identify time expressions and anchor them in real time. From this set of all events, we identify the major ones using a classifier. We then place these events on a timeline and label them with a time interval as small as possible. The timeline is integrated into an online user interface that displays named entities for each event and finds its locations on a map; we separately list named entities and locations mentioned in the article but not around any event.
منابع مشابه
Extracting Event-Related Information from Article Updates in Wikipedia
Wikipedia is widely considered the largest and most up-todate online encyclopedia, with its content being continuously maintained by a supporting community. In many cases, real-life events like new scientific findings, resignations, deaths, or catastrophes serve as triggers for collaborative editing of articles about affected entities such as persons or countries. In this paper, we conduct an i...
متن کاملGPLSIUA: Combining Temporal Information and Topic Modeling for Cross-Document Event Ordering
Building unified timelines from a collection of written news articles requires cross-document event coreference resolution and temporal relation extraction. In this paper we present an approach event coreference resolution according to: a) similar temporal information, and b) similar semantic arguments. Temporal information is detected using an automatic temporal information system (TIPSem), wh...
متن کاملUnsupervised Timeline Generation for Wikipedia History Articles
This paper presents a generic approach to content selection for creating timelines from individual history articles for which no external information about the same topic is available. This scenario is in contrast to existing works on timeline generation, which require the presence of a large corpus of news articles. To identify salient events in a given history article, we exploit lexical cues...
متن کاملStorybase: Towards Building a Knowledge Base for News Events
To better organize and understand online news information, we propose Storybase1, a knowledge base for news events that builds upon Wikipedia current events and daily Web news. It first constructs stories and their timelines based on Wikipedia current events and then detects and links daily news to enrich those Wikipedia stories with more comprehensive events. We encode events and develop effic...
متن کاملAnalysing Timelines of National Histories Across Wikipedia Editions: A Comparative Computational Approach
Portrayals of history are never complete, and each description inherently exhibits a specific viewpoint and emphasis. In this paper, we aim to automatically identify such differences by computing timelines and detecting temporal focal points of written history across languages on Wikipedia. In particular, we study articles related to the history of all UN member states and compare them in 30 la...
متن کامل