Lluís-F. Hurtado

ELiRF: A SVM Approach for SA tasks in Twitter at SemEval-2015

This paper describes our participation at tasks 10 (sub-task B, Message Polarity Classification) and 11 task (Sentiment Analysis of Figurative Language in Twitter) of Semeval2015. We describe the Support Vector Machine system we used in this competition. We also present the relevant feature set that we take into account in our models. Finally, we show the results we obtained in this competition and some conclusions.

Language identification of multilingual posts from Twitter: a case study

This paper describes a method for handling multi-class and multi-label classification problems based on the support vector machine formalism. This method has been applied to the language identification problem in Twitter. The system evaluation was performed mainly on a Twitter data set developed in the TweetLID workshop. This data set contains bilingual tweets written in the most commonly used Iberian languages (i.e., Spanish, Portuguese, Catalan, Basque, and Galician) as well as the English language. We address the following problems: (1) social media texts. We propose a suitable tokenization that processes the peculiarities of Twitter; (2) multilingual tweets. Since a tweet can belong to more than one language, we need to use a multi-class and multi-label classifier; (3) similar languages. We study the main confusions among similar languages; and (4) unbalanced classes. We propose threshold-based strategy to favor classes with less data. We have also studied the use of Wikipedia and the addition of new tweets in order to increase the training data set. Additionally, we have tested our system on Bergsma corpus, a collection of tweets in nine languages, focusing on confusable languages using the Cyrillic, Arabic, and Devanagari alphabets. To our knowledge, we obtained the best results published on the TweetLID data set and results that are in line with the best results published on Bergsma data set.

DSIC-ELIRF at SemEval-2016 Task 4: Message Polarity Classification in Twitter using a Support Vector Machine Approach

This paper contains the description of our participation at task 4 (sub-task A, Message Polarity Classification) of SemEval-2016. Our proposed system consists mainly of three steps. Firstly, the preprocessing step includes the tokenization and identification of special elements including URLs, hashtags, user mentions and emoticons. The second step aims at selecting and extracting the feature set. Finally, a supervised approach, in particular a Support Vector Machine has been applied to tackle the classification problem.

Spoken dialog systems based on online generated stochastic finite-state transducers

In this paper, we present an approach for the development of spoken dialog systems based on the statistical modelization of the dialog manager. This work focuses on three points: the modelization of the dialog manager using Stochastic Finite-State Transducers, an unsupervised way to generate training corpora, and a mechanism to address the problem of coverage that is based on the online generation of synthetic dialogs. Our proposal has been developed and applied to a sport facilities booking task at the university. We present experimentation evaluating the system behavior on a set of dialogs that was acquired using the Wizard of Oz technique as well as experimentation with real users. The experimentation shows that the method proposed to increase the coverage of the Dialog System was useful to find new valid paths in the model to achieve the user goals, providing good results with real users.

Spanish sentiment analysis in Twitter at the TASS workshop

This paper describes a support vector machine-based approach to different tasks related to sentiment analysis in Twitter for Spanish. We focus on parameter optimization of the models and the combination of several models by means of voting techniques. We evaluate the proposed approach in all the tasks that were defined in the five editions of the TASS workshop, between 2012 and 2016. TASS has become a framework for sentiment analysis tasks that are focused on the Spanish language. We describe our participation in this competition and the results achieved, and then we provide an analysis of and comparison with the best approaches of the teams who participated in all the tasks defined in the TASS workshops. To our knowledge, our results exceed those published to date in the sentiment analysis tasks of the TASS workshops.

A Train-on-Target Strategy for Multilingual Spoken Language Understanding

There are two main strategies to adapt a Spoken Language Understanding system to deal with languages different from the original (source) language: test-on-source and train-on-target. In the train-on-target approach, a new understanding model is trained in the target language, which is the language in which the test utterances are pronounced. To do this, a segmented and semantically labeled training set for each new language is needed. In this work, we use several general-purpose translators to obtain the translation of the training set and we apply an alignment process to automatically segment the training sentences. We have applied this train-on-target approach to estimate the understanding module of a Spoken Dialog System for the DIHANA task, which consists of an information system about train timetables and fares in Spanish. We present an evaluation of our train-on-target multilingual approach for two target languages, French and English.

Adaptive Training for Robust Spoken Language Understanding

Spoken Language Understanding, as other areas of Language Technologies, suffers from a mismatching between the conditions of the training of the models and the real use of the systems. If the semantic models are estimated from the correct transcriptions of the training corpus, when the system interacts with real users, some recognition errors can not be recovered by the understanding system. To achieve an improvement in real environments we propose the use of the output sentences from the recognition process of the training corpus in order to adapt the models. To estimate these models, a labeled and segmented corpus is needed. We propose an algorithm for the automatic segmentation and labeling of the recognized sentences considering the correct segmented and labeled data as reference. Experiments with a spoken dialog corpus show that this approach outperforms the approach based on correct transcriptions.