Caroline Barrière

METHODOLOGIES FOR EVALUATING THINNING ALGORITHMS FOR CHARACTER RECOGNITION

This paper investigates three different methods of comparing preference structures for thinning algorithms. The first method involves a series of experiments with human subjects. The second makes use of neural networks and the third is based on dissimilarities and distance measures that is computer generated. Several statistical tests have been performed to analyze the preference structures exhibited by the data. This study highlights human coherence in comparing skeletons and the novelty of using reference skeletons to facilitate the evaluation of thinning algorithms. None of the automatic approaches provides a useful insight although a measure of information content manifests some consistency. The overall study suggests a systematic protocol involving human coherence to evaluate preprocessing algorithms.

Knowledge-Rich Contexts Discovery

Within large corpora of texts, Knowledge-Rich Contexts (KRCs) are a subset of sentences containing information that would be valuable to a human for the construction of a knowledge base. The entry point to the discovery of KRCs is the automatic identification of Knowledge Patterns (KPs) which are indicative of semantic relations. Machine readable dictionary serves as our starting point for investigating the types of knowledge embodied in definitions and some associated KPs. We then move toward corpora analysis and discuss issues of generality/specificity as well as KPs efficiency. We suggest an expansion of the lexical-syntactic definitions of KPs to include a semantic dimension, and we briefly present a tool for knowledge acquisition, SeRT, which allows user such flexible definition of KPs for automatic discovery of KRCs.

Concept clustering and knowledge integration from a children's dictionary

Knowledge structure called Concept Clustering Knowledge Graphs (CCKGs) are introduced along with a process for their construction from a machine readable dictionary. CCKGs contain multiple concepts interrelated through multiple semantic relations together forming a semantic cluster represented by a conceptual graph. The knowledge acquisition is performed on a childrens first dictionary. The concepts involved are general and typical of a daily life conversation. A collection of conceptual clusters together can form the basis of a lexical knowledge base, where each CCKG contains a limited number of highly connected words giving useful information about a particular domain or situation.

Cognitive-Based Model for the Development of a Reading Tool in FSL

This paper investigates reading comprehension from a cognitive perspective. It explores the cognitive-based models used in language teaching to represent a learners acquisition of a second language (SLL). It also explores how the same models are used in natural language processing (NLP) to describe text comprehension. Expertise from the two fields is brought together in the design and development of a cognitive-based software tool to help the learner of French as a second language (FSL) develop better reading strategies.

Human identification of letters in mixed-script handwriting: an upper bound on recognition rates

This paper focuses on a reading task consisting of the identification of letters in mixed-script handwritten words. This task is performed by humans using extended or limited linguistic context. Their performance rate is to give an upper bound on recognition rates of computer programs designed to recognize handwritten letters in mixed-script writing. Many recognition algorithms are being developed in the research community, and there is a need for establishing ways to compare them. As some effort is on its way to give large test sets with standard formats, we propose an algorithm to determine a test set of reduced size that is appropriate for the task to achieve (the type of texts or words to be recognized). Also, with respect to a particular task, we propose a method for finding an upper limit to the letter recognition rate to aim for.

Handwritten sentence recognition: from signal to syntax

This paper describes a system dedicated to online handwritten sentence recognition. The prototype is made up of two basic processors. The first controls the data acquisition, pentip trace segmentation, letter identification. The second aims at identifying and correcting the words candidates by integrating syntactic and lexical information. Sentences are parsed to list the grammatical classes of each incorrect candidates then lexical query searches for words in a lexicon according to grammatical classes. A final decision is made using a string comparison algorithm. Tests of the complete system are reported at the end for a typical writer-dependent application.

English to chinese translation of prepositions

Machine translation of prepositions is a difficult task; little work has been done, to date, in this area This article suggests addressing the problem using a semantic framework for the interpretation of the surrounding elements of a preposition in the source language This framework, called Use Types, will reduce the set of possible prepositions in the target language, therefore helping the translation process This approach is not language dependent, but we focus, here, on English and Chinese, and we also specifically look at three prepositions: in, on and at The article describes machine learning experiments designed and conducted in which WordNet is employed to lead to an automatic discovery of the Use Types Results are analyzed and discussed and a practical use of the system is suggested along with the preliminary results it obtains.

Redundancy: Helping Semantic Disambiguation

Redundancy is a good thing, at least in a learning process. To be a good teacher you must say what you are going to say, say it, then say what you have just said. Well, three times is better than one. To acquire and learn knowledge from text for building a lexical knowledge base, we need to find a source of information that states facts, and repeats them a few times using slightly different sentence structures. A technique is needed for gathering information from that source and identify the redundant information. The extraction of the commonality is an active learning of the knowledge expressed. The proposed research is based on a clustering method developed by Barriere and Popowich (1996) which performs a gathering of related information about a particular topic. Individual pieces of information are represented via the Conceptual Graph (CG) formalism and the result of the clustering is a large CG embedding all individual graphs. In the present paper, we suggest that the identification of the redundant information within the resulting graph is very useful for disambiguation of the original information at the semantic level.