Integrating Multiple Knowledge Sources for Robust Semantic Parsing
نویسندگان
چکیده
This work explores a new robust approach for Semantic Parsing of unrestricted texts. Our approach considers Semantic Parsing as a Consistent Labelling Problem (clp), allowing the integration of several knowledge types (syntactic and semantic) obtained from different sources (linguistic and statistic). The current implementation obtains 95% accuracy in model identification and 72% in case-role filling.
منابع مشابه
Putting Pieces Together: Combining FrameNet, VerbNet and WordNet for Robust Semantic Parsing
This paper describes our work in integrating three different lexical resources: FrameNet, VerbNet, and WordNet, into a unified, richer knowledge-base, to the end of enabling more robust semantic parsing. The construction of each of these lexical resources has required many years of laborious human effort, and they all have their strengths and shortcomings. By linking them together, we build an ...
متن کاملPROFER: predictive, robust finite-state parsing for spoken language
The natural languageprocessingcomponentof a speechunderstanding system is commonly a robust, semantic parser, implemented as either a chart-based transition network, or as a generalized leftright (GLR) parser. In contrast, we are developing a robust, semantic parser that is a single, predictive finite-state machine. Our approach is motivated by our belief that such a finite-state parser can ult...
متن کاملA Decision-Based Approach to Rhetorical Parsing
We present a shift-reduce rhetorical parsing algorithm that learns to construct rhetorical structures of texts from a corpus of discourse-parse action sequences. The algorithm exploits robust lexical, syntactic, and semantic knowledge sources.
متن کاملLODESTAR: a Mandarin spoken dialogue system for travel information retrieval
In this paper, we present LOADSTAR, a Mandarin Spoken Dialogue system developed for travel information retrieval, which could provide clients tourism information and plan proper itinerary according to clients’ favor. In addition to description of the system architecture and individual modules, several significant strategies such as mixed class-based and word-based language model, robust semanti...
متن کاملIntegrating Knowledge of City Entities Extracted from DBpedia and GeoLite into the EKOSS Failure Cases Repository to Enhance Semantic Search Capabilities
Domain-specific repositories of manually created semantic descriptors usually contain detailed knowledge with “heavy-weight” semantics about particular aspects of the domain, but they often lack common knowledge about the concepts and entities that are described. Integrating some of this common knowledge into the repository can enhance the capabilities of semantic search in the repository. We u...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
- CoRR
دوره cs.CL/0109023 شماره
صفحات -
تاریخ انتشار 2001