“A Spousal Relation Begins with a Deletion of engage and Ends with an Addition of divorce”: Learning State Changing Verbs from Wikipedia Revision History

Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 518–523, Lisbon, Portugal, 17-21 September 2015. c⃝2015 Association for Computational Linguistics. “A Spousal Relation Begins with a Deletion of engage and Ends with an Addition of divorce”: Learning State Changing Verbs from Wikipedia Revision History Derry Tanti Wijaya Carnegie Mellon University 5000 Forbes Avenue Pittsburgh, PA, 15213 dwijaya@cs.cmu.edu Ndapandula Nakashole Carnegie Mellon University 5000 Forbes Avenue Pittsburgh, PA, 15213 ndapa@cs.cmu.edu Tom M. Mitchell Carnegie Mellon University 5000 Forbes Avenue Pittsburgh, PA, 15213 tom.mitchell@cs.cmu.edu Abstract Learning to determine when the time- varying facts of a Knowledge Base (KB) have to be updated is a challenging task. We propose to learn state changing verbs from Wikipedia edit history. When a state-changing event, such as a marriage or death, happens to an entity, the in- fobox on the entity’s Wikipedia page usu- ally gets updated. At the same time, the article text may be updated with verbs ei- ther being added or deleted to reflect the changes made to the infobox. We use Wikipedia edit history to distantly super- vise a method for automatically learning verbs and state changes. Additionally, our method uses constraints to effectively map verbs to infobox changes. We observe in our experiments that when state-changing verbs are added or deleted from an en- tity’s Wikipedia page text, we can predict the entity’s infobox updates with 88% pre- cision and 76% recall. One compelling application of our verbs is to incorporate them as triggers in methods for updating existing KBs, which are currently mostly static. 1 Introduction Extracting relational facts between entities and storing them in knowledge bases (KBs) has been a topic of active research in recent years. The result- ing KBs are generally static and are not updated as the facts change (Suchanek et al., 2007; Carl- son et al., 2010; Fader et al., 2011; Mitchell et al., 2015). One possible approach to updating KBs is to extract facts from dynamic Web content such as news (Nakashole and Weikum, 2012). In this paper, we propose to predict state changes caused by verbs acting on entities in text. This is differ- ent from simply applying the same text extraction pipeline, that created the original KB, to dynamic Web content. In particular, our approach has the following ad- vantages: (1) Consider for example the SPOUSE relation, both marry and divorce are good patterns for extracting this relation. In our work, we wish to learn that they cause different state changes. Thus, we can update the entity’s fact and its tem- poral scope (Wijaya et al., 2014a). (2) Learning state changing verbs can pave the way for learn- ing the ordering of verbs in terms of their pre- and post-conditions. Our approach learns state changing verbs from Wikipedia revision history. In particular, we seek to establish a correspondence between infobox ed- its and verbs edits in the same article. The infobox of a Wikipedia article is a structured box that sum- marizes an entity as a set of …

Content truncated to 500 words