Entity linking is the task of disambiguating entities in unstructured text by linking them to an entity in a catalog. Several collective entity linking approaches exist that attempt to collectively disambiguate all mentions in the text by leveraging both local mention-entity context and global entity-entity relatedness. However, the complexity of these models makes it unfeasible to employ exact...

The Knowledge Base Population (KBP) track at the Text Analysis Conference 2010 marks the second year of this important information extraction evaluation. This paper describes the design and implementation of LCC’s systems which participated in the tasks of Entity Linking, Slot Filling, and the new task of Surprise Slot Filling. For the entity linking task, our top score was achieved through a r...

It has been strongly argued that information technology (IT) infrastructure has a strategic impact on an organization. However, no empirical examination of this relationship has been performed. In this paper, based on a survey of 236 firms, the organizational impact of IT infrastructure is assessed using a research model incorporating both direct and indirect impacts. Our results show that, alt...

Wikipedia is often used a source of surface forms, or alternative reference strings for an entity, required for entity linking, disambiguation or coreference resolution tasks. Surface forms have been extracted in a number of works from Wikipedia labels, redirects, disambiguations and anchor texts of internal Wikipedia links, which we complement with anchor texts of external Wikipedia links from...

We study the task of entity linking for tweets, which tries to associate each mention in a tweet with a knowledge base entry. Two main challenges of this task are the dearth of information in a single tweet and the rich entity mention variations. To address these challenges, we propose a collective inference method that simultaneously resolves a set of mentions. Particularly, our model integrat...

The following paper will describe the systems we have created for the Knowledge Base Population (KBP) and Recognizing Textual Entailment (RTE) tracks of TAC. Sections 2 and 3 will describe a set of tools used to perform the entity-linking and slot-filling tasks of the KBP track respectively. Section 4 will give an overview of a complex tool for recognizing textual entailment. Each section descr...

The HLTCOE participated in the entity linking and slot filling tasks at TAC 2009. A machine learning-based approach to entity linking, operating over a wide range of feature types, yielded good performance on the entity linking task. Slot-filling based on sentence selection, application of weak patterns and exploitation of redundancy was ineffective in the slot filling task.

This paper presents the system we developed for Task 11 of SemEval 2015. Our system had two stages: The first one was based on deep autoencoders for extracting features to compactly represent tweets. The next stage consisted of a classifier or a regression function for estimating the polarity value assigned to a given tweet. We tested several techniques in order to choose the ones with the high...