A Text Understander that Learns

A Text Understander that Learns Udo Hahn gz Klemens Schnattinger Computational Linguistics Lab, Freiburg University Werthmannplatz 1, D-79085 Freiburg, Germany {hahn, schnatt inger}@coling, uni-fre±burg, de Abstract We introduce an approach to the automatic ac- quisition of new concepts from natural language texts which is tightly integrated with the under- lying text understanding process. The learning model is centered around tile 'quality' of differ- ent forms of linguistic and conceptual evidence which underlies the incremental generation and refinement of alternative concept hypotheses, each one capturing a different conceptual read- ing for an unknown lexical item. 1 Introduction The approach to learning new concepts as a result of understanding natural language texts we present here builds on two different sources of evidence -- the prior knowledge of the do- main the texts are about, and grammatical con- structions in which unknown lexical items oc- cur. While there may be many rea+sonable inter- pretations when an unknown item occurs for the very first time in a text, their number rapidly decreases when more and more evidence is gath- ered. Our model tries to make explicit tile rea- soning processes behind this learning pattern. Unlike the current mainstream in automatic linguistic knowledge acquisition, which can be characterized as quantitative, surface-oriented bulk processing of large corpora of texts (Hin- (tie, 1989; Zernik and aacobs, 1990; Hearst, 1992; Manning, 1993), we propose here a k++owledge-intensive model of concept learning from few, positive-only examples that is tightly integrated with tile non-learning mode of text understanding. Both learning and understand- ing build on a given core ontology in tile format of terminological assertions and, hence, make abundant use of terminological reasoning. The 'plain' text understanding mode can be consid- ered as tile instantiation and continuous filling y M+t hi~ Figure 1: Architectnre of the Text Learner of roles with respect to single concepts already available ill tile knowledge base. Under learning conditions, however, a set of alternative concept hypotheses has to be maintained for each nn- known item, with each hypothesis denoting a newly created conceptual interpretation tenta- tively associated with tile unknown item. Tile underlying methodology is summarized in Fig. 1. Tile text parser (for an overview, cf. BrSker et al. (1994)) yields information from tile grammatical constructions in which an un- known lexical item (symbolized by the black square) occurs in terms of the corresponding de- pendency parse tree. The kinds of syntactic coll- structions (e.g., genitive, apposition, compara- tive), in which unknown lexical items appear, are recorded and later assessed relative to the credit they lend to a particular hypothesis. The conceptual interpretation of parse trees involv- ing unknown lexical items in the domain knowl- e@e base leads to the derivation of concept hy- potheses, which are further enriched by concep- tual annotations. These reflect structurM pat- terns of consistency, mutual justification, anal- ogy, etc. relative to already available concept descriptions in the domain knowledge base or other hypothesis spaces. This kind of initial ev- idence, in particular its predictive "goodness" for tile learning task, …

Content truncated to 500 words