TAILIEUCHUNG - Unsupervised Learning of Narrative Event Chains

If people express concerns it is worth agreeing to meet them in person and talking through the event with them so that they understand in detail how they may be affected. If there’s a particular business which you foresee could be a problem, for example a courier firm with vehicles coming and going throughout the day, approach them in person first and see if they’re willing to work with you and reduce (or eliminate) the number of vehicle movements. Some businesses may need to be alerted to the fact that they could benefit from the event (eg a. | Unsupervised Learning of Narrative Event Chains Nathanael Chambers and Dan Jurafsky Department of Computer Science Stanford University Stanford CA 94305 natec jurafsky @ Abstract Hand-coded scripts were used in the 1970-80S as knowledge backbones that enabled inference and other NLP tasks requiring deep semantic knowledge. We propose unsupervised induction of similar schemata called narrative event chains from raw newswire text. A narrative event chain is a partially ordered set of events related by a common protagonist. We describe a three step process to learning narrative event chains. The first uses unsupervised distributional methods to learn narrative relations between events sharing coreferring arguments. The second applies a temporal classifier to partially order the connected events. Finally the third prunes and clusters self-contained chains from the space of events. We introduce two evaluations the narrative cloze to evaluate event relatedness and an order coherence task to evaluate narrative order. We show a 36 improvement over baseline for narrative prediction and 25 for temporal coherence. 1 Introduction This paper induces a new representation of structured knowledge called narrative event chains or narrative chains . Narrative chains are partially ordered sets of events centered around a common protagonist. They are related to structured sequences of participants and events that have been called scripts Schank and Abelson 1977 or Fillmorean frames. These participants and events can be filled in and instantiated in a particular text situation to draw inferences. Chains focus on a single actor to facili tate learning and thus this paper addresses the three tasks of chain induction narrative event induction temporal ordering of events and structured selection pruning the event space into discrete sets . Learning these prototypical schematic sequences of events is important for rich understanding of text. Scripts were central to natural .

• Tổ chức sự kiện
• necessarily exclude
• altruism and systems
• financial losses
• recommendations
• decision to prescribe
• healthcare professional
• hazardous effects
• nanomaterials derived
• protein aggregation
• Worthington College
• young Kentuckian
• rapidly and proved