An End-to-end Model for Entity-level Relation Extraction using Multi-instance Learning

An End-to-end Model for Entity-level Relation Extraction using Multi-instance Learning Markus Eberts Adrian Ulges RheinMain University of Applied Sciences Wiesbaden, Germany {markus.eberts, adrian.ulges}@hs-rm.de Abstract We present a joint model for entity-level rela- tion extraction from documents. In contrast to other approaches – which focus on local intra-sentence mention pairs and thus require annotations on mention level – our model op- erates on entity level. To do so, a multi-task approach is followed that builds upon corefer- ence resolution and gathers relevant signals via multi-instance learning with multi-level repre- sentations combining global entity and local mention information. We achieve state-of-the- art relation extraction results on the DocRED dataset and report the first entity-level end-to- end relation extraction results for future ref- erence. Finally, our experimental results sug- gest that a joint approach is on par with task- specific learning, though more efficient due to shared parameters and training steps. 1 Introduction Information extraction addresses the inference of formal knowledge (typically, entities and relations) from text. The field has recently experienced a significant boost due to the development of neural approaches (Zeng et al., 2014; Zhang and Wang, 2015; Kumar, 2017). This has led to two shifts in research: First, while earlier work has focused on sentence level relation extraction (Hendrickx et al., 2010; Han et al., 2018; Zhang et al., 2017), more re- cent models extract facts from longer text passages (document-level). This enables the detection of inter-sentence relations that may only be implicitly expressed and require reasoning across sentence boundaries. Current models in this area do not rely on mention-level annotations and aggregate signals from multiple mentions of the same entity. The second shift has been towards multi-task learning: While earlier approaches tackle entity mention detection and relation extraction with sepa- rate models, recent joint models address these tasks The Portland Golf Club is a private golf club in the northwest United States, in suburban Portland, Oregon. The PGC is located in the unincorporated Raleigh Hills area of east- ern Washington County, southwest of down- town Portland and east of Beaverton. PGC was established in the winter of 1914, when a group of nine businessmen assembled to form a new club after leaving their respective clubs. The golf club hosted the Ryder Cup matches of 1947, the first renewal in a decade, due to World War II. The U.S. team defeated Great Britain 11 to 1 in wet conditions in early November. Figure 1: Our goal is to perform end-to-end entity-level relation extraction on whole documents. We extract entity mentions (“PGC”), entity clusters ({Portland Golf Club, PGC, golf club}), their types (ORG) and relations to other entities in the document, such as ({Portland Golf Club, PGC, golf club}ORG, inception, {1914}T IME), with a single, joint model. Note that document-level relation extraction requires the aggre- gation of relevant information from multiple sentences, such as in ({Raleigh Hills}LOC, country, {United States, U.S.})LOC). Other entities in the example doc- ument are omitted for clarity. at once (Bekoulis et al., 2018; Nguyen and Ver- …

Content truncated to 500 words