Do coreferential arguments make event mentions coreferential?
نویسنده
چکیده
This paper explores features of arguments in coreferential chains of events using the NP4E corpus, which has been previously annotated for entity and event coreference. The analysis takes event chains as a starting point and examines the way entities in the argument slots of event mentions contribute to establishing coreference. The investigation revealed that in many cases the arguments of coreferential event mentions are not coreferential themselves. The paper offers an explanation of this phenomenon and discusses the notion of event coreference with the help of examples from the corpus.
منابع مشابه
Coreferential Relations in Basque: The Annotation Process.
In this paper we present the coreferential tagging of part of the EPEC Corpus of Basque. Although coreference is a pragmatic linguistic phenomenon highly dependent on the situational context, it shows some language-specific patterns that vary according to the features of each language. Due to the fact that Basque is not an Indo-European language, it differs considerably in grammar from the lang...
متن کاملA Search Based Method for Clinical Text Coreference Resolution
This paper describes a novel method and system developed to address the coreference task of the 2011 i2b2 NLP Challenge, which involved analyzing clinical texts of several types and identifying the coreferential mentions within them. The method uses an open source search library component to do the heavy lifting for string matching, allowing a lightweight rule-based processing engine to cluster...
متن کاملSingleton Detection using Word Embeddings and Neural Networks
Singleton (or non-coreferential) mentions are a problem for coreference resolution systems, and identifying singletons before mentions are linked improves resolution performance. Here, a singleton detection system based on word embeddings and neural networks is presented, which achieves state-of-the-art performance (79.6% accuracy) on the CoNLL2012 shared task development set. Extrinsic evaluat...
متن کاملRPI BLENDER TAC-KBP2015 System Description
To extract English name mentions, we apply a linear-chain CRFs model trained from ACE 20032005 corpora (Li et al., 2012a). For Chinese and Spanish, we use Stanford name tagger (Finkel et al., 2005). We also encode several regular expression based rules to extract poster name mentions in discussion forum posts. In this year’s task, person nominal mentions extraction is added. There are two major...
متن کاملResolución de Correferencia de Nombres de Persona para Extracción de Información Biográfica
Information extraction systems need a previous processing step in order to recognize coreferential elements, such as personal name variants. This paper has two aims: the first is to describe the main types of personal name coreference found in encyclopedic and journalistic texts in Spanish. Furthermore, we introduce an algorithm that solves most coreferential links between personal name variant...
متن کامل