Andrés Melgar

Ship-LemmaTagger: Building an NLP Toolkit for a Peruvian Native Language.

Natural Language Processing deals with the understanding and generation of texts through computer programs. There are many different functionalities used in this area, but among them there are some functions that are the support of the remaining ones. These methods are related to the core processing of the morphology of the language (such as lemmatization) and automatic identification of the part-of-speech tag. Thereby, this paper describes the implementation of a basic NLP toolkit for a new language, focusing in the features mentioned before, and testing them in an own corpus built for the occasion. The obtained results exceeded the expected results and could be used for more complex tasks such as machine translation.

Comparison of software process models. A systematic literature review

Nowadays, there are several software process models, which fulfill different purposes, approaches and requirements. However, this proliferation causes some confusion in the industry about the benefits or advantages of each proposal. In this context, studies have been conducted to determine the existing equivalence or the extent of coverage between these models having used different approaches to the comparisons. This work aims to present a study of techniques and experiences on comparison of software process models. For this study, a systematic literature review was conducted in relevant databases and available documents finding that there are few works or experiences in this area and it represents an aspect in software engineering the requires a higher level of research and development. Five different methods to compare process models were found and it was identified that the CCT - Comparison Composition Tree method is the unique that have a graphic representation.

ExperTI: A Knowledge Based System for Intelligent Service Desks Using Free Text

When many users consult service desks simultaneously, these typically saturate. This causes the customer attention to be delayed more than usual. To increase the amount of human agents is a costly process for organizations. All this has motivated the design of a knowledge-based system that automatically assists both customers and human agents at the service desk. Web technology was used to enable clients to communicate with a software agent via chat. Techniques of Natural Language Processing were used for the software agent to understand the customer requests. The domain knowledge used by the software agent to understand customer requests has been codified in an ontology. A rule-based expert system (ES) was designed to perform the diagnostic task. This paper presents a knowledge-based system allowing client to communicate with the service desk through a chat system using free text. Evaluations conducted with users have shown an improvement in the attention of service desks when the software developed is used.

Competitive Intelligence Using Domain Ontologies on Facebook of Telecommunications Companies of Peru

Telecommunications companies (TELCOs) in Peru offers promotions almost daily in social networks, mainly Facebook. There’s a lot of data in Facebook, written in natural language without meaning for computer, that TELCOs are not using to have Competitive Intelligence (CI). CI is a process that identifies decision makers information needs about competitors, collects data from public sources, gives meaning and analyze data to answer information needs and communicates results to decision makers.

SenseDependency-Rank: A Word Sense Disambiguation Method Based on Random Walks and Dependency Trees

Word Sense Disambiguation (WSD) is the field that seeks to determine the correct sense of a word in a given context. In this paper, we present a WSD method based on random walks over a dependency tree, whose nodes are word-senses from the WordNet. Besides, our method incorporates prior knowledge about the frequency of use of the word-senses. We observed that our results outperform several graph-based WSD methods in All-Word task of SensEval-2 and SensEval-3, including the baseline, where the nouns and verbs part-of-speech show the better improvement in their F-measure scores.

Corpus Creation and Initial SMT Experiments between Spanish and Shipibo-konibo.

In this paper, we present the first attempts to develop a machine translation (MT) system between Spanish and Shipibo-konibo (es-shp). There are very few digital texts written in Shipibo-konibo and even less bilingual texts that can be aligned, hence we had to create a parallel corpus using both bilingual and monolingual texts. We will describe how this corpus was made, as well as the process we followed to improve the quality of the sentences used to build a statistical MT model or SMT. The results obtained surpassed the baseline proposed (dictionary based) and made a promising result for further development considering the size of corpus used. Finally, it is expected that this MT system can be reinforced with the use of additional linguistic rules and automatic language processing functions that are being implemented.

An architecture for organizational memory systems in institutions of higher education

The purpose of this paper is to define architecture for organizational memory systems in institutions of higher education. The aim arose from the identified problem, where the constructions of knowledge management systems are being handled in a rapid prototyping approach. In the rapid prototyping approach the acquired knowledge was encoded directly into an iteratively developed computer system and provides early versions of the system, however its difficult to manage and maintain the final system. Furthermore, a state of the art survey identified few organizational memories studies in institutions of higher education despite being a natural place for research and knowledge management. This work proposes architecture for organizational memory that is based on CESM model and CommonKADS methodology; this architecture is concerned with the knowledge representation for semantic search of documents. Furthermore, a systematic review of the state of the art was performed to support the design of the architecture and compare the proposed architecture with the proposed architectures in the academic community.

A classification model for Portuguese documents in the juridical domain

The attorneys office in Brazil, receive daily a lot of notifications. These notifications must be manually analyzed by procurators to determine what kind of document should they prepare to respond. This situation causes in many cases notifications are not answered in time causing these prescribed. All this has motivated the development of this work whose main objective is the development of a computational model to understand the meaning of each notification and indicate what kind of response should be prepared for every situation. For the construction of this model, machine-learning algorithms are used. The problem is modeled as one of classification using free text documents. The texts were extracted from notification documents, which were written in Portuguese. The method to assess the performance of the algorithms was the area under the curve. During the experiment, four algorithms were evaluated, including k-Nearest Neighbor, Support Vector Machine, Naive Bayes and Complement Naive Bayes. The algorithms were trained using a collection of Portuguese documents in the juridical domain, which includes 5471 documents divided into 8 categories. A 25-fold cross validation method was used to measure the unbiased estimate of these prediction models. This paper is a comparative study of machine learning algorithms for the problem of categorization of notifications. As a result of this study, an algorithm model was constructed in order to classify the documents in the corresponding class. The area under the curve value of Support Vector Machine, k-Nearest Neighbor, Naive Bayes and Complement Naive Bayes was 0.846, 0.831, 0.815 and 0.712 respectively. Our study shows that out of these four classification models Support Vector Machine predicts with highest area under the curve value.

A framework for organizational memory management of research projects in institutions of higher education

An institution of higher education that develops research projects can learn and remember the knowledge generated by these projects. In this paper we propose a framework for the management of organizational memory oriented research projects in higher education institutions. This framework supports the capture, storage and retrieval of knowledge from research projects, which could provide access to documents or documentation thereof. The construction of the framework is done using semantic technology that includes the development of an ontology and semantic retrieval engine.

An Automated Semantic Annotation Tool Supported by an Ontology in the Computer Science Domain

The annotation of documents can be performed manually, semi-assisted or automated, also it can use the help of different knowledge resources as a set of rules or ontology. In this paper, we show the design of a semantic annotation tool that works automatically on power in order to efficiently manage academic documents in spanish produced in the university related to computer science. The tool uses an ontology annotations to provide a corpus of documents the necessary attributes to be managed using other tools that use annotations as searchers or indexers. This is done by relating the concepts found in documents with concepts in the ontology performing semantic and syntactic comparisons, it is produced using open source tools for natural language processing and knowledge management.