An integrated, dual learner for grammars and ontologies

We introduce a dual-use methodology for automating the maintenance and growth of two types of knowledge sources, which are crucial for natural language text understanding-background knowledge of the underlying domain and linguistic knowledge about the lexicon and the grammar of the underlying natural language. A particularity of this approach is that learning occurs simultaneously with the on-going text understanding process. The knowledge assimilation process is centered around the linguistic and conceptual 'quality' of various forms of evidence underlying the generation, assessment and on-going refinement of lexical and concept hypotheses. On the basis of the strength of evidence, hypotheses are ranked according to qualitative plausibility criteria, and the most reasonable ones are selected for assimilation into the already given lexical class hierarchy and domain ontology.

[1]  Wendy G. Lehnert,et al.  Wrap-Up: a Trainable Discourse Module for Information Extraction , 1994, J. Artif. Intell. Res..

[2]  Beatrice Santorini,et al.  Building a Large Annotated Corpus of English: The Penn Treebank , 1993, CL.

[3]  Fernando Gomez,et al.  Determining Prepositional Attachment, Prepositional Meaning, Verb Meaning, and Thematic Roles , 1997, Comput. Intell..

[4]  Robert Mac Gregor,et al.  THE EVOLVING TECHNOLOGY OF CLASSIFICATION-BASED KNOWLEDGE REPRESENTATION SYSTEMS , 1991 .

[5]  Lucy Vanderwende,et al.  MindNet: Acquiring and Structuring Semantic Information from Text , 1998, COLING-ACL.

[6]  Martin Romacker,et al.  An Empirical Assessment of Semantic Interpretation , 2000, ANLP.

[7]  Kathleen McKeown,et al.  Experiments in Automated Lexicon Building for Text Searching , 2000, COLING.

[8]  Christiane Fellbaum,et al.  Book Reviews: WordNet: An Electronic Lexical Database , 1999, CL.

[9]  Udo Hahn,et al.  QUALITY-BASED LEARNING , 1998 .

[10]  Ellen Riloff,et al.  An Empirical Study of Automated Dictionary Construction for Information Extraction in Three Domains , 1996, Artif. Intell..

[11]  Martin Romacker,et al.  Content management in the SYNDIKATE system - How technical documents are automatically transformed to text knowledge bases , 2000, Data Knowl. Eng..

[12]  Satoshi Shirai,et al.  Using Decision Trees to Construct a Practical Parser , 1999, COLING.

[13]  Steven L. Lytinen,et al.  The Ups and Downs of Lexical Acquisition , 1994, AAAI.

[14]  Eugene Charniak,et al.  Tree-Bank Grammars , 1996, AAAI/IAAI, Vol. 2.

[15]  Lisa F. Rau,et al.  Information extraction and text summarization using linguistic knowledge acquisition , 1989, Inf. Process. Manag..

[16]  James G. Schmolze,et al.  The KL-ONE family , 1992 .

[17]  Martin Romacker,et al.  Context-Based Ambiguity Management for Natural Language Processing , 2001, CONTEXT.

[18]  Eric Brill,et al.  Transformation-Based Error-Driven Learning and Natural Language Processing: A Case Study in Part-of-Speech Tagging , 1995, CL.

[19]  Eric Brill,et al.  Bagging and Boosting a Treebank Parser , 2000, ANLP.

[20]  Martin Romacker,et al.  Lean Semantic Interpretation , 1999, IJCAI.

[21]  Marti A. Hearst.  Automated Discovery of WordNet Relations , 2004 .

[22]  Claire Cardie,et al.  A Case-Based Approach to Knowledge Acquisition for Domain-Specific Sentence Analysis , 1993, AAAI.

[23]  Udo Hahn,et al.  A Text Understander that Learns , 1998, ACL.

[24]  Udo Hahn,et al.  Concurrent, object-oriented natural language parsing: the ParseTalk model , 1994, Int. J. Hum. Comput. Stud..

[25]  Béatrice Daille.  Morphological Rule Induction for Terminology Acquisition , 2000, COLING.

[26]  Steffen Staab,et al.  Discovering Conceptual Relations from Text , 2000, ECAI.

[27]  Patrick Brézillon,et al.  Lecture Notes in Artificial Intelligence , 1999 .

[28]  Atro Voutilainen.  A syntax-based part-of-speech analyser , 1995, EACL.

[29]  Udo Hahn,et al.  Let’s Parsetalk — Message-Passing Protocols for Object-Oriented Parsing , 2000 .

[30]  Patrick Brézillon,et al.  Modeling and Using Context , 1999, Lecture Notes in Computer Science.