Non-linear models recently receive a lot of attention as people are starting to discover the power of statistical and embedding features. However, tree-based models are seldom studied in the context of structured learning despite their recent success on various classification and ranking tasks. In this paper, we propose S-MART, a tree-based structured learning framework based on multiple additi...

Recent work on Web-extracted data sets has produced an interesting new source of structured Web data. These data sets can be viewed as knowledge bases (KB) – large heterogeneous linked entity collections with millions of unique edge and node labels, often encoding rich semantic information over entities. For example, YAGO [5] and ExDB [2] have fact collections numbering in the tens and hundreds...

We present a prototype of a Web querying interface which is capable of searching and querying unified Web sources of data that have sufficient hidden relational structure. The system converts query-related parts of Web pages into relational data and provides for SQL-like or QBE-like querying capability. The relational query is parsed for relevant information such as selection conditions and tab...

Recent experiments indicate that a case-based approach to the problem of word pronunciation is effective as the basis for a system that learns to pronounce English words. More generally, the approach taken here illustrates how a case-based reasoner can access a large knowledge base containing hundreds of potentially relevant cases and consolidate these multiple knowledge sources using numerical...

Given the large collections of unstructured and semi-structured data available on the web, there is a crucial need to enable quick and efficient access to the knowledge content within them. Traditionally, the field of information extraction has focused on extracting such knowledge from unstructured text documents, such as job postings, scientific papers, news articles, and emails. However, the ...

This paper describes the SECLIPS system, which provides a restricted English grammar and vocabulary designed to express the facts and rules of a rules-based knowledge base. SECLIPS is an extension of ECLIPS and allows the user to extend a core vocabulary to express a knowledge base of facts and rules for a particular problem domain. SECLIPS employs an LL(1) based translator with the grammar for...

This paper describes the establishment of an XML Metadata Knowledge Base (XMKB) to assist integration of distributed heterogeneous structured data residing in relational databases and semi-structured data held in wellformed XML documents (XML documents that conform to the XML syntax rules but have no referenced DTD or XML schema) produced by internet applications. We propose an approach to comb...

Accounts of category-based inductive reasoning can be distinguished by the emphasis they place on associative retrieval processes versus structural knowledge representation. Using an open-ended category-based induction task with a secondary task manipulation, we explored whether the relative importance of these two processes in determining the reasoning output depends upon the availability of m...

This paper describes a neural semantic parser that maps natural language utterances onto logical forms which can be executed against a task-specific environment, such as a knowledge base or a database, to produce a response. The parser generates tree-structured logical forms with a transition-based approach which combines a generic tree-generation algorithm with domain-general operations define...

A method of capturing the complete knowledge of a process plant, for making system is proposed. Provisions have been made to acquire the knowledge of the plant in a hybrid way, which describes the domain-specific, heuristic and the control knowledge. The domain knowledge includes structural and behavioral information about a plant. The heuristic knowledge includes hypotheses regarding fault-loc...