Title :
Shallow language processing, deep language processing and domain ontologies
Author_Institution :
Language Technol. Lab., DFKI, Saarbruecken, Germany
fDate :
30 Oct.-1 Nov. 2005
Abstract :
A new line of our research concerns the combination of shallow processing, deep processing and domain ontologies for question answering. In our QA system QUETAL, we combine question answering on the basis of structured data with open domain IR supported question answering as it can be employed for questioning the Web. The new approach exploits RMRS as the formalism for translating natural language questions into SQL queries. Ontologies are utilized for structuring the data, constructing the appropriate semantics for the QA systems and for the interpretation of the questions. We demonstrate the interaction of shallow and deep technologies in the QA system and stress the knowledge related aspects. We finally discuss the advantages and open problems connected with our approach. In a brief outlook we programmatically sketch the planned next steps in the DELPH-IN community towards bridging the gap between advanced semantic language processing and state-of-the-art knowledge technology.
Keywords :
SQL; computational linguistics; grammars; information retrieval; language translation; natural languages; ontologies (artificial intelligence); SQL query; deep language processing; domain ontologies; information retrieval; question answering; semantic language processing; shallow language processing; Data mining; Humans; IEEE news; Knowledge engineering; Large-scale systems; Logic; Natural languages; Ontologies; Robustness; Semantic Web;
Conference_Titel :
Natural Language Processing and Knowledge Engineering, 2005. IEEE NLP-KE '05. Proceedings of 2005 IEEE International Conference on
Print_ISBN :
0-7803-9361-9
DOI :
10.1109/NLPKE.2005.1598697