Previous work has shown how a back-propagation network with recurrent connections can successfully model many aspects of human spoken word recogni-tion (Norris, 1988, 1990, 1992, 1993). However, such networks are unable to revise their decisions in the light of subsequent context. TRACE (McClelland & Elman, 1986), on the other hand, manages to deal appropriately with following context, but only by using a highly implausible architecture that fails to account for some important experimental results. A new model is presented which displays the more desirable properties of each of these models. In contrast to TRACE the new model is entirely bottom-up and can readily perform simulations with vocabularies of tens of thousands of words. 1.

Recognition of degraded text is a challenging problem. To improve the performance of an OCR system on degraded images of text, postprocessing techniques are critical. The objective of postprocessing is to correct errors or to resolve ambiguities in OCR results by using contextual information. Depending on the extent of context used, there are different levels of postprocessing. In current commercial OCR systems, word-level postprocessing methods, such as dictionary-lookup, have been applied successfully. However, many OCR errors cannot be corrected by word-level postprocessing. To overcome this limitation, passage-level postprocessing, in which global contextual information is utilized, is necessary. In most current studies on passage-level postprocessing, linguistic context is the major resource to be exploited. This thesis addresses problems in degraded text recognition and discusses potential solutions through passage-level postprocessing. The objective is to develop a postprocessin...

We present an active chart parser which parses left connected wordgraphs in a strictly time synchronous way. The parser performs a beam search on the possible paths through the word graph and on the possible derivations of the unification grammar simultaneously. A metric is given to assign scores to edges, taking into account the whole left context thereby combining acoustic probabilities, n-gram probabilities and unification grammar probabilities. A specialized model for the derivation of typed unification grammars is introduced. Different ways of coupling the parser with an LR beam decoder in an online time synchronous fashion are defined and several experimental results are presented. Two top down and one bottom up method are investigated. In bottom up mode, the decoder sends word hypotheses as they are found from left to right, while the parser keeps step. In verify mode, the decoder is always a frame ahead, while the parser verifies received hypotheses, providing language informat...

This report is concerned with a new method of evaluation for the Linguistic Word Recognition component of the Verbmobil-Project: Architektur. A two stage model of diagnostic evaluation is presented consisting of logical and empirical evaluation steps. Logical evaluation is carried out according to a data model which acts as optimal input in order that each component participating in the evaluation process can be tested for soundness and completeness. Inconsistencies can thus be remedied before empirical evaluation of the model is undertaken using real data. The diagnostic evaluation method has been operationalised within the Bielefeld Extended Evaluation Toolkit for Lattices of Events (BEETLE). 1 Introduction This report is concerned with a new approach to evaluation which has been developed in connection with Linguistic Word Recognition in the Verbmobil Project 15.6 Interactive Phonological Interpretation. In the sections below, it is demonstrated how current evaluation procedures...

29. Lari. K., Young, S.l: The estimation of st.ochastie =text-free grammars using the Inside·Outside