TIC018 - Capítulos de Libroshttps://hdl.handle.net/10481/196052024-03-29T04:43:19Z2024-03-29T04:43:19ZA proposal for Developing and Deploying Statistical Dialog Management in Commercial Conversational PlatformsCañas, PabloGriol Barres, DavidCallejas Carrión, Zoraidahttps://hdl.handle.net/10481/802602023-04-18T22:17:28ZA proposal for Developing and Deploying Statistical Dialog Management in Commercial Conversational Platforms
Cañas, Pablo; Griol Barres, David; Callejas Carrión, Zoraida
Conversational interfaces have recently become ubiquitous in the personal sphere by improving
an individual’s quality of life and industrial environments by automating services and their corre-
sponding cost savings. However, designing the dialog model used by these interfaces to decide
the following response is a hard-to-accomplish task for complex conversational interactions. This
paper proposes a statistical-based dialog manager architecture, which provides flexibility to develop
and maintain this module. Our proposal has been integrated using DialogFlow, a natural language
understanding platform provided by Google to design conversational user interfaces. The proposed
hybrid architecture has been assessed with a real use case for a train scheduling domain, proving that
the user experience is highly valued and can be integrated into commercial setups
Comparison of Learning Approaches to Dialogue Management in Conversational SystemsGriol Barres, DavidCallejas Carrión, Zoraidahttps://hdl.handle.net/10481/802562023-02-27T08:42:25ZComparison of Learning Approaches to Dialogue Management in Conversational Systems
Griol Barres, David; Callejas Carrión, Zoraida
Dialogue systems have an increasingly higher number of applications and so their development
is raising interest both in academic and industrial setting. Dialogue management is a key aspect
for the development of these systems, as it is in charge of the decision making processes and the
identification of the most appropriate responses to the user inputs. In this paper we compare different
statistical techniques to train dialogue managers using generally available corpora at the disposal
for the scientific community. Our results show that the use of generative models and in particular
an intent classifier with Neural Networks and Seq2Seq using GRU cells attain the best accuracy for
dialogue management.
Feature Set Ensembles for Sentiment Analysis of TweetsGriol Barres, DavidKanagal-Balakrishna, C.Callejas Carrión, Zoraidahttps://hdl.handle.net/10481/802552023-02-27T08:38:51ZFeature Set Ensembles for Sentiment Analysis of Tweets
Griol Barres, David; Kanagal-Balakrishna, C.; Callejas Carrión, Zoraida
In recent years, sentiment analysis has attracted a lot of research attention due to the explosive growth of online social media usage and the abundant user data they generate. Twitter is one of the most popular online social networks and a microblogging platform where users share their thoughts and opinions on various topics. Twitter enforces a character limit on tweets, which makes users find creative ways to express themselves using acronyms, abbreviations, emoticons, etc. Additionally, communication on Twitter does not always follow standard grammar or spelling rules. These peculiarities can be used as features for performing sentiment classification of tweets. In this chapter, we propose a Maximum Entropy classifier that uses an ensemble of feature sets that encompass opinion lexicons, n-grams and word clusters to boost the performance of the sentiment classifier. We also demonstrate that using several opinion lexicons as feature sets provides a better performance than using just one, at the same time as adding word cluster information enriches the feature space.
Managing Multi-task Dialogs by Means of a Statistical Dialog Management TechniqueGriol Barres, DavidCallejas Carrión, ZoraidaQuesada, José F.https://hdl.handle.net/10481/802542023-02-27T08:38:30ZManaging Multi-task Dialogs by Means of a Statistical Dialog Management Technique
Griol Barres, David; Callejas Carrión, Zoraida; Quesada, José F.
One of the most demanding tasks when developing a dialog system consists of deciding the next
system response considering the user’s actions and the dialog history, which is the fundamental
responsibility related to dialog management. A statistical dialog management technique is proposed
in this work to reduce the effort and time required to design the dialog manager. This technique
allows not only an easy adaptation to new domains, but also to deal with the different subtasks for
which the dialog system has been designed. The practical application of the proposed technique
to develop a dialog system for a travel-planning domain shows that the use of task-specific dialog
models increases the quality and number of successful interactions with the system in comparison
with developing a single dialog model for the complete domain.