Current research in the field of chatterbots lacks detailed information on the evolution of prototypes after the startup, where the system exploitation reveals engine performance and biases. This paper presents the tuning and evolution of PTAH, an AI system that interacts in natural language using a precise combination of linguistic processing tools. This analysis aims to introduce not only a methodology but also to show and compare how certain parameterization considerations impact on the results despite the sophistication of algorithmic. Results allow to affirm that the post-deployment treatment is critical for the correct parameterization of NLP systems using AI approaches, due the bias and entropy speed required to feed the intelligent learning of the optimized model in chatter contexts.

Searching contents from a query performed using Natural Language is a hard task when there is a limited time to response and no other information but a reduced set of documents. This paper presents a novel approach to expand queries in Natural Language. The working hypothesis, a short introduction to some concepts of Morphosyntactic Linguistic Wavelets that are of interest, and a use case of the implemented model are within the scope of this paper. Preliminary results indicate the self-expansion proposal is fast, and produces a good number of correct re-phrasings that can be used to recall more documents with proper answers to the original query.

This paper presents a proposal for automatically detecting the structure of regulatory documents, tagging management and text segmentation in units able to be processed as entries in a database. The information stored in that way must be adequate to be efficiently managed by a chatter bot named PTAH, which aims to answer user questions in Natural Language. As part of this work, the usage, main difficulties and characteristics of managing the information in this context is explained. Then, there is a step by step derivation using the proposed method with a small test set of 27 documents. Finally, the results are analyzed and evaluated. The proposal is flexible and robust, based on simple processing, clustering and a rule-based automatic algorithm.

Chatbots belong to a large family of software robots that aim to gracefully integrate human spoken interactions as interface. Most of the proposals in the field intend to solve severe limitations of the automatic processing of natural language. This paper is part of a project called PTAH, that implements a prototype able to ask and answer about a topic in Spanish. Although previous work solved much of the training and language-based strategies, there is still poor resources to make the bot understand alternatives to answer specific questions or problems. This paper presents an approach called auto-expansion with an original combination of Morphosyntactic-Linguistic-Wavelets and certain Machine Learning techniques. As part of the scope, the basic preliminary theory is introduced, along with detailed description of the self-expansion proposal and some of the prototype's state of implementation, tests and statistical analysis. Authors intend to show the goodness of the proposal.

Metric Spaces model databases allowing similarity searching. e.g., looking for objects similar to a given one. Spatial databases are used to store and efficiently retrieve data with some spatial attribute. Some applications need to search both by similarity and space at the same time. This kind of queries cannot be solved efficiently using spatial o metric indexes separately. Recently, Metric Spatial queries were formalized and a new access method, the MeTree, was proposed to solve them. In this article, we present new experiments that show the performance of this index.

This paper presents a restricted domain approach for handling information in the context of regulation search. Information Retrieval (IR) using a chatterbot as front-end is especially complex due to the interaction with Natural Language. The problem becomes more complicated when the IR is for a Restricted Domain: there is no statistical error compensation. The slang in the documentation usually does not match the common language usage, and dialogs tend to be informal, making people tend to perform incomplete questions to the system. PTAH is a chatterbot developed to interact with students, administrative employees, professors and many other people of the university community. Cultural diversity and big age differences present an interesting challenge for the Natural Language Processing area, since many approaches tend to overcome only one of the previous aspects. This paper presents the chatterbot PTAH, and specifically depicts an IR approach that intends to improve the quality of the answers. Results are evaluated with traditional precision and recall metrics, and an additional one to assess the quality of the heuristics involved in the retrieval process. Statistics indicate that it is possible to apply a specific combination of simple and traditional heuristics with good results.

Fil: Herrera, Norma Edith. Universidad Nacional de San Luis. Departamento de Informatica; Argentina.

This paper presents a tuned Intelligent Code Recognition (ICR) model using a self-adapting dictionary, combined with a version of Levenshtein distance for checking word similarity. It is part of a broader project named PTAH (Procesamiento de Trámites con Asistente Hispanohablante), an intelligent chatterbot that uses this ICR to collect knowledge from documents. Due to its critical activity, it is mandatory to get the best result for the image to text conversion. The success in getting information determines the knowledge database quality and therefore the accuracy of the answers upon queries to the chatterbot. A blueprint of the global Project is included as well as the ICR, statistics progression obtained with the sequence of improvements applied to the ICR, and a final analysis of the failures.

This paper presents the first results of a functional prototype implementing a linguistic model focused on regulations in Spanish. Its global architecture, the reasoning model, a case-study and short statistics are provided for the prototype named PTAH. It mainly has a conversational robot linked to an Expert System by a module with many intelligent linguistic filters, implementing the reasoning model of an expert. It is focused in bylaws, regulations, jurisprudence and customized background representing entity mission, vision and profile. This structure and model are generic enough to self adapt to any regulatory environment, but as a first step, it was limited to academic field. This way it is possible to limit the slang and data number. The foundations of the linguistic model and the way the architecture implements the key features of the behavior, are also outlined. The cases presented are a few just to show the usability, flexibility and prospectives of this proposal.

This communication presents a functional prototype, named PTAH, implementing a linguistic model focused on regulations in Spanish. Its global architecture, the reasoning model and short statistics are provided for the prototype. It is mainly a conversational robot linked to an Expert System by a module with many intelligent linguistic filters, implementing the reasoning model of an expert. It is focused on bylaws, regulations, jurisprudence and customized background representing entity mission, vision and profile. This Structure and model are generic enough to self-adapt to any regulatory environment, but as a first step, it was limited to an academic field. This way it is possible to limit the slang and data numbers. The foundations of the linguistic model are also outlined and the way the architecture implements the key features of the behavior.

Fil: Blanc, Rafael Lujan. Universidad Tecnologica Nacional. Facultad Regional Concepcion del Uruguay; Argentina.

Pascal, Andres Jorge. Universidad Tecnologica Nacional. Facultad Regional Concepcion del Uruguay ; Argentina.

Pascal, Andres Jorge. Universidad Tecnologica Nacional. Facultad Regional Concepcion del Uruguay ; Argentina.

De Battista, Anabella C. Universidad Tecnologica Nacional. Facultad Regional Concepcion del Uruguay ; Argentina.