Collective entity disambiguation, or collective entity linking aims to jointly resolve multiple mentions by linking them to their associated entities in a knowledge base. Previous works largely based on the underlying assumption that entities within the same document are highly related. However, the extend to which these mentioned entities are actually connected in reality is rarely studied and...

This paper reports on work in progress on extending the entity-based approach on measuring coherence (Barzilay & Lapata, 2005; Lapata & Barzilay, 2005) from coreference to semantic relatedness. We use a corpus of manually annotated German newspaper text (TüBa-D/Z) and aim at improving the performance by grouping related entities with the WikiRelate! API (Strube & Ponzetto, 2006).

We define a model of discourse coherence based on Barzilay and Lapata’s entity grids as a stylometric feature for authorship attribution. Unlike standard lexical and character-level features, it operates at a discourse (cross-sentence) level. We test it against and in combination with standard features on nineteen booklength texts by nine nineteenth-century authors. We find that coherence alone...

in iranian language learning contexts, writing in english is an important challenge for learners, since it is usually treated as a secondary skill and is led to the periphery of language classes, due to its time-consuming nature. computer technology and namely the free online environments available in the world wide web (www) offer possibilities for moving beyond such confinements. asynchronous...

Previous studies have highlighted the necessity for entity linking systems to capture the local entity-mention similarities and the global topical coherence. We introduce a novel framework based on convolutional neural networks and recurrent neural networks to simultaneously model the local and global features for entity linking. The proposed model benefits from the capacity of convolutional ne...

This paper presents a joint model designed to measure local text coherence that uses Rhetorical Structure Theory (RST) and entity grids. The purpose is to learn patterns of entity distribution in texts by considering entity transition sequences and organizational/discourse information using RST relations in order to create a predictive model that is able to distinguish coherent from incoherent ...

Relation extraction aims to extract semantic relationships between two specified named entities in a sentence. Because sentence often contains several entity pairs, neural network is easily bewildered when learning relation representation without position and information about the considered pair. In this paper, instead of an abstract from raw inputs, task-related indicators are designed enable...

Maintaining coherence between the independent views of multiple participants at distributed locations is essential in an Embedded Simulation environment. Currently, the Distributed Interactive Simulation (DIS) protocol maintains coherence by broadcasting the entity state streams from each simulation station. In this dissertation, a novel alternative to DIS that replaces the transmitting sources...

Block-LDA is a topic modeling approach to perform data fusion between entity-annotated text documents and graphs with entity-entity links. We evaluate Block-LDA in the yeast biology domain by jointly modeling PubMed R © articles and yeast protein-protein interaction networks. The topic coherence of the emergent topics and the ability of the model to retrieve relevant scientific articles and pro...