Learning for Semantic Parsing

Semantic parsing is the process of mapping a natural-language sentence into a formal representation of its meaning. A shallow form of semantic representation is a case-role analysis (a.k.a. a semantic role labeling), which identifies roles such as agent, patient, source, and destination. A deeper semantic analysis provides a representation of the sentence in predicate logic or other formal language which supports automated reasoning. We have developed methods for automatically learning semantic parsers from annotated corpora using inductive logic programming and other learning methods. We have explored learning semantic parsers for mapping natural-language sentences to case-role analyses, formal database queries, and formal command languages (i.e. the Robocup coaching language for use in advice-taking learners ). We have also explored methods for learning semantic lexicons, i.e. databases of words or phrases paired with one or more alternative formal meaning representations. Semantic lexicons can also be learned from semantically annotated sentences and are an important source of knowledge for semantic parsing. Learning for semantic parsing is part of our research on natural language learning.

Patent Search News

Hello readers,

Have you checked the latest news over Setrue Patent Search???

The popular blog Infringement Updates has posetd a nice review over Setrue Patent Searching system.

Enjoy…

Why use Setrue Semantic Patent Search Engine?

Setrue Semantic Patent Search Engine is one of the most powerful patent search engine ever published and it’s the first professional patent search engine offered freely for non-commercial users. Its ease of use makes the search process enjoyable and fun to use, while maintaining powerful features such as:

	Semantic natural language query capabilities.
	Query auto-complete suggestions.
	Detailed uspto class directory structure enabling a one click segmentation of search results to a specific uspto patent class.
	Clustering of search results by uspto classes.
	Clustering of search results by years.
	Clustering of search results by assignees.
	Similar patents segmentation.
	Dynamic weighting of search terms.
	Highlighting of search terms in documents.
	A well formed tabbed patent representation.
	Detailed advanced search capabilities.
	Dynamic list of law firms and attorney sites specialized in the field of the user’s query filtered by expertise and the user’s geo location proximity.
	Professional services maintained by an expert patent attorney team and law firms.

the inventors corner

Hello readers,

In the next few posts I will explain “Why there is a growing need for a semantic search?” and “Why semantic search is far better than key word search?”

A good example for the semantic power that can be achieved by search engines is utilized by Setrue Patent Search, this engine is one of the best in the world and its ability to find patents in a very demanding environment of patent searching is remarkable. It was developed by Transformer software Ltd. Setrue Patent search holds two world records in precision score.