Manfred Wettler

A Freely Available Morphological Analyzer, Disambiguator and Context Sensitive Lemmatizer for German

In this paper we present Morphy, an integrated tool for German morphology, part-of-speech tagging and context-sensitive lemmatization. Its large lexicon of more than 320, 000 word forms plus its ability to process German compound nouns guarantee a wide morphological coverage. Syntactic ambiguities can be resolved with a standard statistical part-of-speech tagger. By using the output of the tagger, the lemmatizer can determine the correct root even for ambiguous word forms. The complete package is freely available and can be downloaded from the World Wide Web.

Free Word Associations Correspond to Contiguities Between Words in Texts

A free associative response is the first word a person comes up with after perceiving another word, the so-called associative stimulus. People commonly associate hot to cold, church to priest, and hard to work. According to traditional association theory this behaviour is the result of learning by contiguity: “Objects once experienced together tend to become associated in the imagination, so that when any one of them is thought of, the others are likely to be thought of also, in the same order of sequence or coexistence as before” (James, 1890). This explanation has been rejected by cognitive psychologists who explain the production of associations as the result of symbolic processes which make use of complex semantic structures (Clark, 1970). We will show, however, that human associative responses can be predicted from contiguities between words in language use. This finding supports the hypothesis that the behaviour of participants in the free association task can be explained by associative learning.

Prediction of free word associations based on Hebbian learning

An associative lexical net whose weights are computed on the basis of the co-occurrences of words using Hebbs rule has been built. The co-occurrences of word pairs are determined by shifting a window over a large body of text. To estimate the associative response to a given stimulus word, the corresponding node is activated and its activity is propagated in the net. The proposed model assumes that words with high activities after propagation correspond to the associative responses of human subjects. These predictions have been tested and confirmed using the association norms collected by Russel and Jenkins.<<ETX>>

An associative model of word selection in the generation of search queries

To generate a search query based on a end‐user request, a database searcher has to select appropriate search terms. These terms can either be taken from the request, or they can be added by the searcher. This selection process is simulated by an associative lexical net; the nodes of the net are the terms used in 94 records of written requests to a psychological information agency and the respective on‐line searches. The weights connecting the nodes are calculated from the co‐occurrences of these terms in the abstracts of the database PsycLIT. To simulate the term selection process for a query, the nodes of all terms used in the written request are activated, and one or more spreading activation cycles are performed. The result of the simulation is a ranking of the terms according to the activities of their nodes. Simulations for all 94 records show a low mean activity rank for the terms selected from the request; the mean activity rank for new terms added by the searcher is lower than the mean activity rank for those terms of the request that were not used in the query.

Cognitive Processes in Information Retrieval: Production Rules and Lexical Nets

Abstract Information Retrieval is described as the translation of a problem description into an expression of a query language. This operation is determined by two kinds of processes. On the level of parallel information processing, the attention to the problem description induces associative activities. These associations determine which words of the problem description and which additional words will be included in the query. The generation of the syntactic structure of the query and the subsequent testing of its quality and scope are determined by rule-governed processes. We present an autoassociative connectionist net in which the relations between 269 words are described. This net is used to simulate the associative processes of searchers in online reference databases. It produces a list of activated words which is passed on to a production system. This system uses the grammar of the query language, several heuristics, and the information from the system about the scope of previous queries in order to execute an iterative optimization of the query.

A connectionist simulation of human word associations

Summary form only given, as follows. On the basis of the frequencies and co-occurrences of words in large bodies of text, autoassociative lexical nets which describe the connective weights between 371 words were computed. These nets were used to predict the free associative responses of the word association norms collected by Russel and Jenkins from college students. Different assumptions about the learning of the connective weights, the influence of word order, and the generation of associative responses were compared. It was shown quantitatively that there is a high level of correspondence between the present predictions and the experimental data.<<ETX>>