Knowledge Base Question Answering (KBQA) is a task where existing techniques have faced significant challenges, such as the need for complex question understanding, reasoning, and large training datasets. In this work, we demonstrate Deep Thinking (DTQA), semantic parsing reasoning-based KBQA system. DTQA (1) integrates multiple, reusable modules that are trained specifically their individual t...

This paper describes the CMCRC systems entered in the TAC 2010 entity linking challenge. The best performing system we describe implements the document-level entity linking system from Cucerzan (2007), with several additions that exploit global information. Our implementation of Cucerzan’s method achieved a score of 74.9% in development experiments. Additional global information improves perfor...

This paper describes the IBM systems for the Trilingual Entity Discovery and Linking (EDL) for the TAC 2015 KnowledgeBase Population track. The entity discovery or mention detection (MD) system is based on system combination of deep neural networks and conditional random fields. The entity linking (EL) system is based on a language independent probabilistic disambiguation model. The same EL mod...

Sulfur (S) cross-linking styrene butadiene rubber (SBR) foams show high shrinkage due to the cure reversion, leading to reduced yield and increased processing cost. In this paper, double cross-linking system by S and dicumyl peroxide (DCP) was used to decrease the shrinkage of SBR foams. Most importantly, the synergy of double cross-linking agents was reported for the first time to our knowledg...

data envelopment analysis (dea) is a method for measuring the efficiency of peer decision making units (dmus) with multiple inputs and outputs. the traditional dea treats decision making units under evaluation as black boxes and calculates their efficiencies with first inputs and last outputs. this carries the notion of missing some intermediate measures in the process of changing the inputs to...

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...

In this paper, we present an algorithm for improving named entity resolution and entity linking by using surface form generation and rewriting. Surface forms consist of a word or a group of words that matches lexical units like Paris or New York City. Used as matching sequences to select candidate entries in a knowledge base, they contribute to the disambiguation of those candidates through sim...

The extracellular matrix (ECM) is an essential element of mammalian organisms, and its cross-linking formation plays a vital role in ECM development and postnatal homeostasis. Defects in cross-link formation caused by aging, genetic, or environmental factors are known to cause numerous diseases in mammals. To augment the cross-linking formation of ECM, the present study established a ZsGreen re...

We present two methods for entity linking in two of our systems submitted to TAC-KBP 2012. The first one, implemented in JVNTDT1 system, learns coherence among cooccurrence entities referred to within a text by exploiting Wikipedia’s link structure and the second one, implemented in JVN_TDT2 system, combines some heuristics with a statistical model, for entity linking. The method implemented in...