Search

The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-19390-8_24, [EN] The amount of digitized legacy documents has been rising over the last years due mainly to the increasing number of on-line digital libraries publishing this kind of documents. The vast majority of them remain waiting to be transcribed to provide historians and other researchers new ways of indexing, consulting and querying them. However, the performance accuracy of state-of-the-art Handwritten Text Recognition techniques decreases dramatically when they are applied to these historical documents. This is mainly due to the typical paper degradation problems. Therefore, robust pre-processing techniques is an important step for helping further recognition steps. This paper proposes to take existing binarization techniques, in order to retain their advantages, and modify them in such a way that some of the original grayscale information is preserved and be considered by the subsequent recognizer. Results are reported with the publicly available ESPOSALLES database.

The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-19390-8_24, [EN] The amount of digitized legacy documents has been rising over the last years due mainly to the increasing number of on-line digital libraries publishing this kind of documents. The vast majority of them remain waiting to be transcribed to provide historians and other researchers new ways of indexing, consulting and querying them. However, the performance accuracy of state-of-the-art Handwritten Text Recognition techniques decreases dramatically when they are applied to these historical documents. This is mainly due to the typical paper degradation problems. Therefore, robust pre-processing techniques is an important step for helping further recognition steps. This paper proposes to take existing binarization techniques, in order to retain their advantages, and modify them in such a way that some of the original grayscale information is preserved and be considered by the subsequent recognizer. Results are reported with the publicly available ESPOSALLES database.

The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-19390-8_24, [EN] The amount of digitized legacy documents has been rising over the last years due mainly to the increasing number of on-line digital libraries publishing this kind of documents. The vast majority of them remain waiting to be transcribed to provide historians and other researchers new ways of indexing, consulting and querying them. However, the performance accuracy of state-of-the-art Handwritten Text Recognition techniques decreases dramatically when they are applied to these historical documents. This is mainly due to the typical paper degradation problems. Therefore, robust pre-processing techniques is an important step for helping further recognition steps. This paper proposes to take existing binarization techniques, in order to retain their advantages, and modify them in such a way that some of the original grayscale information is preserved and be considered by the subsequent recognizer. Results are reported with the publicly available ESPOSALLES database.

The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-18117-2_21, In this paper we consider the detection of opinion spam as a stylistic classi cation task because, given a particular domain, the deceptive and truthful opinions are similar in content but di ffer in the way opinions are written (style). Particularly, we propose using character ngrams as features since they have shown to capture lexical content as well as stylistic information. We evaluated our approach on a standard corpus composed of 1600 hotel reviews, considering positive and negative reviews. We compared the results obtained with character n-grams against the ones with word n-grams. Moreover, we evaluated the e ffectiveness of character n-grams decreasing the training set size in order to simulate real training conditions. The results obtained show that character n-grams are good features for the detection of opinion spam; they seem to be able to capture better than word n-grams the content of deceptive opinions and the writing style of the deceiver. In particular, results show an improvement of 2:3% and 2:1% over the word-based representations in the detection of positive and negative deceptive opinions respectively. Furthermore, character n-grams allow to obtain a good performance also with a very small training corpus. Using only 25% of the training set, a Na ve Bayes classi er showed F1 values up to 0.80 for both opinion polarities.

The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-21413-9_15, Consistency is an inconsistency are ubiquitous term in data engineering. Its relevance to quality is obvious, since consistency is a commonplace dimension of data quality. However, connotations are vague or ambiguous. In this paper, we address semantic consistency, transaction consistency, replication consistency, eventual consistency and the new notion of partial consistency in databases. We characterize their distinguishing properties, and also address their differences, interactions and interdependencies. Partial consistency is an entry door to living with inconsistency, which is an ineludible necessity in the age of big data.

The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-18117-2_21, In this paper we consider the detection of opinion spam as a stylistic classi cation task because, given a particular domain, the deceptive and truthful opinions are similar in content but di ffer in the way opinions are written (style). Particularly, we propose using character ngrams as features since they have shown to capture lexical content as well as stylistic information. We evaluated our approach on a standard corpus composed of 1600 hotel reviews, considering positive and negative reviews. We compared the results obtained with character n-grams against the ones with word n-grams. Moreover, we evaluated the e ffectiveness of character n-grams decreasing the training set size in order to simulate real training conditions. The results obtained show that character n-grams are good features for the detection of opinion spam; they seem to be able to capture better than word n-grams the content of deceptive opinions and the writing style of the deceiver. In particular, results show an improvement of 2:3% and 2:1% over the word-based representations in the detection of positive and negative deceptive opinions respectively. Furthermore, character n-grams allow to obtain a good performance also with a very small training corpus. Using only 25% of the training set, a Na ve Bayes classi er showed F1 values up to 0.80 for both opinion polarities.

© Springer International Publishing Switzerland 2015 C.P. Kitsos et al. (eds.), Theory and Practice of Risk Assessment, Springer Proceedings in Mathematics & Statistics 136, DOI 10.1007/978-3-319-18029-8_26, Trade credit refers to providing goods and services on a deferred payment basis. Commercial credit management is a matter of great importance for most small and medium enterprises (SMEs), since it represents a significant portion of their assets. Commercial lending involves assuming some credit risk due to exposure to default. Thus, the management of trade credit and payment delays is strongly related to the liquidation and bankruptcy of enterprises. In this paper we study the relationship between trade credit management and the level of risk in SMEs. Despite its relevance for most SMEs, this problem has not been sufficiently analyzed in the existing literature. After a brief review of existing literature, we use a large database of enterprises to analyze data and propose a multivariate decision-tree model which aims at explaining the level of risk as a function of several variables, both of financial and non-financial nature. Decision trees replace the equation in parametric regression models with a set of rules. This feature is an important aid for the decision process of risk experts, as it allows them to reduce time and then the economic cost of their decisions.

The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-19390-8_38, People use social media to express their opinions. Often linguistic devices such as irony are used. From the sentiment analysis perspective such utterances represent a challenge being a polarity reversor (usually from positive to negative). This paper presents an approach to address irony detection from a machine learning perspective. Our model considers structural features as well as, for the first time, sentiment analysis features such as the overall sentiment of a tweet and a score of its polarity. The approach has been evaluated over a set classifiers such as: Naïve Bayes, Decision Tree, Maximum Entropy, Support Vector Machine, and for the first time in irony detection task: Multilayer Perceptron. The results obtained showed the ability of our model to distinguish between potentially ironic and non-ironic sentences.

The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-14078-0_7, [EN] In this paper, a mixed-integer mathematical programming model is proposed to address a production and routing problem related to inbound logistics processes in supply chains environments. This model is also enriched with sustainable issues related to routing decisions by introducing additional fuel consumption and pollutants emissions calculations into the objective function. For the solution methodology, a two-phase decoupled solution procedure based on exact algorithms for the production model and a tabu search algorithm for the routing model is adopted. Results of computational experiments performed with a realworld automotive supply chain confirm the efficiency of the proposed solution method in terms of total cost, fuel consumptions and CPU time.

The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-24027-5_49, This paper presents an overview of the PAN/CLEF evaluation lab. During the last decade, PAN has been established as the main forum of text mining research focusing on the identification of personal traits of authors left behind in texts unintentionally. PAN 2015 comprises three tasks: plagiarism detection, author identification and author profiling studying important variations of these problems. In plagiarism detection, community-driven corpus construction is introduced as a new way of developing evaluation resources with diversity. In author identification, cross-topic and cross-genre author verification (where the texts of known and unknown authorship do not match in topic and/or genre) is introduced. A new corpus was built for this challenging, yet realistic, task covering four languages. In author profiling, in addition to usual author demographics, such as gender and age, five personality traits are introduced (openness, conscientiousness, extraversion, agreeableness, and neuroticism) and a new corpus of Twitter messages covering four languages was developed. In total, 53 teams participated in all three tasks of PAN 2015 and, following the practice of previous editions, software submissions were required and evaluated within the TIRA experimentation framework.

The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-19390-8_49, In this paper, we present a clustering approach based on the combined use of a continuous vector space representation of sentences and the k-means algorithm. The principal motivation of this proposal is to split a big heterogeneous corpus into clusters of similar sentences. We use the word2vec toolkit for obtaining the representation of a given word as a continuous vector space. We provide empirical evidence for proving that the use of our technique can lead to better clusters, in terms of intra-cluster perplexity and F 1 score.

The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-19390-8_38, People use social media to express their opinions. Often linguistic devices such as irony are used. From the sentiment analysis perspective such utterances represent a challenge being a polarity reversor (usually from positive to negative). This paper presents an approach to address irony detection from a machine learning perspective. Our model considers structural features as well as, for the first time, sentiment analysis features such as the overall sentiment of a tweet and a score of its polarity. The approach has been evaluated over a set classifiers such as: Naïve Bayes, Decision Tree, Maximum Entropy, Support Vector Machine, and for the first time in irony detection task: Multilayer Perceptron. The results obtained showed the ability of our model to distinguish between potentially ironic and non-ironic sentences.

The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-24027-5_49, This paper presents an overview of the PAN/CLEF evaluation lab. During the last decade, PAN has been established as the main forum of text mining research focusing on the identification of personal traits of authors left behind in texts unintentionally. PAN 2015 comprises three tasks: plagiarism detection, author identification and author profiling studying important variations of these problems. In plagiarism detection, community-driven corpus construction is introduced as a new way of developing evaluation resources with diversity. In author identification, cross-topic and cross-genre author verification (where the texts of known and unknown authorship do not match in topic and/or genre) is introduced. A new corpus was built for this challenging, yet realistic, task covering four languages. In author profiling, in addition to usual author demographics, such as gender and age, five personality traits are introduced (openness, conscientiousness, extraversion, agreeableness, and neuroticism) and a new corpus of Twitter messages covering four languages was developed. In total, 53 teams participated in all three tasks of PAN 2015 and, following the practice of previous editions, software submissions were required and evaluated within the TIRA experimentation framework.

The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-19390-8_49, In this paper, we present a clustering approach based on the combined use of a continuous vector space representation of sentences and the k-means algorithm. The principal motivation of this proposal is to split a big heterogeneous corpus into clusters of similar sentences. We use the word2vec toolkit for obtaining the representation of a given word as a continuous vector space. We provide empirical evidence for proving that the use of our technique can lead to better clusters, in terms of intra-cluster perplexity and F 1 score.

© Springer International Publishing Switzerland 2015 C.P. Kitsos et al. (eds.), Theory and Practice of Risk Assessment, Springer Proceedings in Mathematics & Statistics 136, DOI 10.1007/978-3-319-18029-8_26, Trade credit refers to providing goods and services on a deferred payment basis. Commercial credit management is a matter of great importance for most small and medium enterprises (SMEs), since it represents a significant portion of their assets. Commercial lending involves assuming some credit risk due to exposure to default. Thus, the management of trade credit and payment delays is strongly related to the liquidation and bankruptcy of enterprises. In this paper we study the relationship between trade credit management and the level of risk in SMEs. Despite its relevance for most SMEs, this problem has not been sufficiently analyzed in the existing literature. After a brief review of existing literature, we use a large database of enterprises to analyze data and propose a multivariate decision-tree model which aims at explaining the level of risk as a function of several variables, both of financial and non-financial nature. Decision trees replace the equation in parametric regression models with a set of rules. This feature is an important aid for the decision process of risk experts, as it allows them to reduce time and then the economic cost of their decisions.

The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-19390-8_4, Social circles detection is a special case of community detection in social network that is currently attracting a growing interest in the research community. We propose in this paper an empirical evaluation of the multi-assignment clustering method using different feature representation models. We define different vectorial representations from both structural egonet information and user profile features. We study and compare the performance on the available labelled Facebook data from the Kaggle competition on learning social circles in networks. We compare our results with several different baselines.

The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-19390-8_38, People use social media to express their opinions. Often linguistic devices such as irony are used. From the sentiment analysis perspective such utterances represent a challenge being a polarity reversor (usually from positive to negative). This paper presents an approach to address irony detection from a machine learning perspective. Our model considers structural features as well as, for the first time, sentiment analysis features such as the overall sentiment of a tweet and a score of its polarity. The approach has been evaluated over a set classifiers such as: Naïve Bayes, Decision Tree, Maximum Entropy, Support Vector Machine, and for the first time in irony detection task: Multilayer Perceptron. The results obtained showed the ability of our model to distinguish between potentially ironic and non-ironic sentences.

The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-18117-2_21, In this paper we consider the detection of opinion spam as a stylistic classi cation task because, given a particular domain, the deceptive and truthful opinions are similar in content but di ffer in the way opinions are written (style). Particularly, we propose using character ngrams as features since they have shown to capture lexical content as well as stylistic information. We evaluated our approach on a standard corpus composed of 1600 hotel reviews, considering positive and negative reviews. We compared the results obtained with character n-grams against the ones with word n-grams. Moreover, we evaluated the e ffectiveness of character n-grams decreasing the training set size in order to simulate real training conditions. The results obtained show that character n-grams are good features for the detection of opinion spam; they seem to be able to capture better than word n-grams the content of deceptive opinions and the writing style of the deceiver. In particular, results show an improvement of 2:3% and 2:1% over the word-based representations in the detection of positive and negative deceptive opinions respectively. Furthermore, character n-grams allow to obtain a good performance also with a very small training corpus. Using only 25% of the training set, a Na ve Bayes classi er showed F1 values up to 0.80 for both opinion polarities.

The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-21413-9_15, Consistency is an inconsistency are ubiquitous term in data engineering. Its relevance to quality is obvious, since consistency is a commonplace dimension of data quality. However, connotations are vague or ambiguous. In this paper, we address semantic consistency, transaction consistency, replication consistency, eventual consistency and the new notion of partial consistency in databases. We characterize their distinguishing properties, and also address their differences, interactions and interdependencies. Partial consistency is an entry door to living with inconsistency, which is an ineludible necessity in the age of big data.

The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-14078-0_7, [EN] In this paper, a mixed-integer mathematical programming model is proposed to address a production and routing problem related to inbound logistics processes in supply chains environments. This model is also enriched with sustainable issues related to routing decisions by introducing additional fuel consumption and pollutants emissions calculations into the objective function. For the solution methodology, a two-phase decoupled solution procedure based on exact algorithms for the production model and a tabu search algorithm for the routing model is adopted. Results of computational experiments performed with a realworld automotive supply chain confirm the efficiency of the proposed solution method in terms of total cost, fuel consumptions and CPU time.

The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-13623-3_28, Over the past few years, online multimedia educational repositories have increased in number and popularity. The main aim of the transLectures project is to develop cost-effective solutions for producing accurate transcriptions and translations for large video lecture repositories, such as VideoLectures.NET or the Universitat Politècnica de València s repository, poliMedia. In this paper, we present the transLectures-UPV toolkit (TLK), which has been specifically designed to meet the requirements of the transLectures project, but can also be used as a conventional ASR toolkit. The main features of the current release include HMM training and decoding with speaker adaptation techniques (fCMLLR). TLK has been tested on the VideoLectures.NET and poliMedia repositories, yielding very competitive results. TLK has been released under the permissive open source Apache License v2.0 and can be directly downloaded from the transLectures website.

Standards for cryptographic protocols have long been attractive candidates for formal verification. It is important that such standards be correct, and cryptographic protocols are tricky to design and subject to non-intuitive attacks even when the underlying cryptosystems are secure. Thus a number of general-purpose cryptographic protocol analysis tools have been developed and applied to protocol standards. However, there is one class of standards, security application programming interfaces (security APIs), to which few of these tools have been applied. Instead, most work has concentrated on developing special-purpose tools and algorithms for specific classes of security APIs. However, there can be much advantage gained from having general-purpose tools that could be applied to a wide class of problems, including security APIs. One particular class of APIs that has proven difficult to analyze using general-purpose tools is that involving exclusive-or. In this paper we analyze the IBM 4758 Common Cryptographic Architecture (CCA) protocol using an advanced automated protocol verification tool with full exclusive-or capabilities, the Maude-NPA tool. This is the first time that API protocols have been satisfactorily specified and analyzed in the Maude-NPA, and the first time XOR-based APIs have been specified and analyzed using a general-purpose unbounded session cryptographic protocol verification tool that provides direct support for AC theories. We describe our results and indicate what further research needs to be done to make such protocol analysis generally effective.

The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-13623-3_5, Online multimedia repositories are growing rapidly. However, language barriers are often difficult to overcome for many of the current and potential users. In this paper we describe a TTS Spanish sys- tem and we apply it to the synthesis of transcribed and translated video lectures. A statistical parametric speech synthesis system, in which the acoustic mapping is performed with either HMM-based or DNN-based acoustic models, has been developed. To the best of our knowledge, this is the first time that a DNN-based TTS system has been implemented for the synthesis of Spanish. A comparative objective evaluation between both models has been carried out. Our results show that DNN-based systems can reconstruct speech waveforms more accurately.

The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-13623-3_5, Online multimedia repositories are growing rapidly. However, language barriers are often difficult to overcome for many of the current and potential users. In this paper we describe a TTS Spanish sys- tem and we apply it to the synthesis of transcribed and translated video lectures. A statistical parametric speech synthesis system, in which the acoustic mapping is performed with either HMM-based or DNN-based acoustic models, has been developed. To the best of our knowledge, this is the first time that a DNN-based TTS system has been implemented for the synthesis of Spanish. A comparative objective evaluation between both models has been carried out. Our results show that DNN-based systems can reconstruct speech waveforms more accurately.

The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-13623-3_28, Over the past few years, online multimedia educational repositories have increased in number and popularity. The main aim of the transLectures project is to develop cost-effective solutions for producing accurate transcriptions and translations for large video lecture repositories, such as VideoLectures.NET or the Universitat Politècnica de València s repository, poliMedia. In this paper, we present the transLectures-UPV toolkit (TLK), which has been specifically designed to meet the requirements of the transLectures project, but can also be used as a conventional ASR toolkit. The main features of the current release include HMM training and decoding with speaker adaptation techniques (fCMLLR). TLK has been tested on the VideoLectures.NET and poliMedia repositories, yielding very competitive results. TLK has been released under the permissive open source Apache License v2.0 and can be directly downloaded from the transLectures website.

Standards for cryptographic protocols have long been attractive candidates for formal verification. It is important that such standards be correct, and cryptographic protocols are tricky to design and subject to non-intuitive attacks even when the underlying cryptosystems are secure. Thus a number of general-purpose cryptographic protocol analysis tools have been developed and applied to protocol standards. However, there is one class of standards, security application programming interfaces (security APIs), to which few of these tools have been applied. Instead, most work has concentrated on developing special-purpose tools and algorithms for specific classes of security APIs. However, there can be much advantage gained from having general-purpose tools that could be applied to a wide class of problems, including security APIs. One particular class of APIs that has proven difficult to analyze using general-purpose tools is that involving exclusive-or. In this paper we analyze the IBM 4758 Common Cryptographic Architecture (CCA) protocol using an advanced automated protocol verification tool with full exclusive-or capabilities, the Maude-NPA tool. This is the first time that API protocols have been satisfactorily specified and analyzed in the Maude-NPA, and the first time XOR-based APIs have been specified and analyzed using a general-purpose unbounded session cryptographic protocol verification tool that provides direct support for AC theories. We describe our results and indicate what further research needs to be done to make such protocol analysis generally effective.

The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-13623-3_5, Online multimedia repositories are growing rapidly. However, language barriers are often difficult to overcome for many of the current and potential users. In this paper we describe a TTS Spanish sys- tem and we apply it to the synthesis of transcribed and translated video lectures. A statistical parametric speech synthesis system, in which the acoustic mapping is performed with either HMM-based or DNN-based acoustic models, has been developed. To the best of our knowledge, this is the first time that a DNN-based TTS system has been implemented for the synthesis of Spanish. A comparative objective evaluation between both models has been carried out. Our results show that DNN-based systems can reconstruct speech waveforms more accurately.

The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-13623-3_28, Over the past few years, online multimedia educational repositories have increased in number and popularity. The main aim of the transLectures project is to develop cost-effective solutions for producing accurate transcriptions and translations for large video lecture repositories, such as VideoLectures.NET or the Universitat Politècnica de València s repository, poliMedia. In this paper, we present the transLectures-UPV toolkit (TLK), which has been specifically designed to meet the requirements of the transLectures project, but can also be used as a conventional ASR toolkit. The main features of the current release include HMM training and decoding with speaker adaptation techniques (fCMLLR). TLK has been tested on the VideoLectures.NET and poliMedia repositories, yielding very competitive results. TLK has been released under the permissive open source Apache License v2.0 and can be directly downloaded from the transLectures website.