Spanish Corpus Research Articles

Analyzing assisted reproductive treatment representations in Italy and Spain through newspapers.

With the increase in infertility cases recorded over the last 20 years, there is a considerable demand for assisted reproductive treatments (ART). However, there is significant variation in the availability of such treatments across different countries. Legislation on assisted reproduction is influenced by various cultural expressions, making it seemingly impossible to create a single representation adaptable to different contexts. This work investigates the cultural representations of ART in Italy and Spain. We collected 1,735 articles from two Italian and Spanish newspapers, with all the articles containing the respective translation of ART from 2013 to 2022. The two corpora were analyzed using the Emotional Text Mining (ETM) methodology. The analysis produced 3 clusters in the Italian corpus and 5 clusters in the Spanish corpus. From the Italian results, a view of ART emerged that is linked to ethical limitations and the ideal of the traditional family. In contrast, the Spanish results depict ART in terms of community, rights, public health, and birth seen in itself. In conclusion, this study highlights the strong differences between Italian and Spanish cultures regarding ART. The results could be used to improve clinical practices and legislation surrounding ART.

Spoken Spanish PoS tagging: gold standard dataset

AbstractThe development of a benchmark for part-of-speech (PoS) tagging of spoken dialectal European Spanish is presented, which will serve as the foundation for a future treebank. The benchmark is constructed using transcriptions of the Corpus Oral y Sonoro del Español Rural (COSER;“Audible corpus of spoken rural Spanish”) and follows the Universal Dependencies project guidelines. We describe the methodology used to create a gold standard, which serves to evaluate different state-of-the-art PoS taggers (spaCy, Stanza NLP, and UDPipe), originally trained on written data and to fine-tune and evaluate a model for spoken Spanish. It is shown that the accuracy of these taggers drops from 0.98$$-$$ - 0.99 to 0.94$$-$$ - 0.95 when tested on spoken data. Of these three taggers, the spaCy’s trf (transformers) and Stanza NLP models performed the best. Finally, the spaCy trf model is fine-tuned using our gold standard, which resulted in an accuracy of 0.98 for coarse-grained tags (UPOS) and 0.97 for fine-grained tags (FEATS). Our benchmark will enable the development of more accurate PoS taggers for spoken Spanish and facilitate the construction of a treebank for European Spanish varieties.

El derecho informático y la influencia en los sistemas de información: un análisis bibliográfico bajo la perspectiva jurídica y tecnológica en Ecuador

This research focused on computer law and information systems in Ecuador. The aim was to analyze the legal and technological perspectives of computer laws and their influence on information systems in the Ecuadorian context. A PRISMA review protocol was established to obtain the bibliography, and advanced techniques such as Word2Vec and cosine similarity analyses were applied to two different linguistic corpora (Spanish and English). Hierarchical dendrograms provided a visual representation, highlighting groups of articles and the complexity of the relationship between computer law and information systems. The comparison between the corpora showed similarities and differences, such as the more marked connection between two of the articles in the Spanish corpus. The study revealed a significant connection between computer law and information systems, underscoring common themes such as cybercrime, data protection, and intellectual property. Links supported by Ecuadorian legislation were identified in areas such as software protection and e-commerce. However, the need to effectively implement the laws and broader international cooperation to address challenges such as cybercrime is emphasized. The study demonstrated disparities and connections between Ecuador's computer law and information systems. The need to adopt an interdisciplinary approach for future research is underlined.

Applying machine learning to assess emotional reactions to video game content streamed on Spanish Twitch channels

This research explores for the first time the application of machine learning to detect emotional responses in video game streaming channels, specifically on Twitch, the most widely used platform for broadcasting content. Analyzing sentiment in gaming contexts is difficult due to the brevity of messages, the lack of context, and the use of informal language, which is exacerbated in the gaming environment by slang, abbreviations, memes, and jargon. First, a novel Spanish corpus was created from chat messages on Spanish video game Twitch channels, manually labeled for polarity and emotions. It is noteworthy as the first Spanish corpus for analyzing social responses on Twitch. Secondly, machine learning algorithms were used to classify polarity and emotions offering promising evaluations. The methodology followed in this work consists of three main steps: (1) Extracting Twitch chat messages from Spanish streamers’ channels related to gaming events and gameplays; (2) Processing and selecting the messages to form the corpus and manually annotating polarity and emotions; and (3) Applying machine learning models to detect polarity and emotions in the created corpus. The results have shown that a Bidirectional Encoder Representation from Transformers (BERT) based model excels with 78% accuracy in polarity detection, while deep learning and Random Forest models reach around 70%. For emotion detection, the BERT model performs best with 68%, followed by deep learning with 55%. It is worth noting that emotion detection is more challenging due to the subjective interpretation of emotions in the complex communicative context of video gaming on platforms such as Twitch. The use of supervised learning techniques, together with the rigorous corpus labeling process and the subsequent corpus pre-processing methodology, has helped to mitigate these challenges, and the algorithms have performed well. The main limitations of the research involve category and video game representation balance. Finally, it is important to stress that the integration of machine learning in video games and on Twitch is innovative, by allowing the identification of viewers’ emotions on streamers’ channels. This innovation could bring benefits such as a better understanding of audience sentiment, improving content and audience retention, providing personalized recommendations and detecting toxic behavior in chats.

Automatic Translation between Mixtec to Spanish Languages Using Neural Networks

This paper introduces a novel method for collecting and translating texts from the Mixtec to the Spanish language. The method comprises four primary steps. First, we collected a Mixtec–Spanish corpus that includes 4568 sentences from educational and religious domain texts. To enhance the parallel corpus, we generate synthetic data with GPT-3.5. Second, we cleaned the data with a semi-automatic approach followed by preprocessing and tokenization. In preprocessing, we removed stop words, duplicated sentences, special characters, and numbers and converted them to lowercase. Third, we performed semi-automatic alignment to find the correspondence of Mixtec–Spanish sentences to generate sentence-level aligned texts necessary for translation. Finally, we trained automatic translation models based on recurrent neural networks, bidirectional recurrent neural networks, and Transformers. Our system achieved a BLEU score of 95.66 for Mixtec-to-Spanish translation and 99.87 for Spanish-to-Mixtec translation. We also obtained a translation edit rate (TER) of 0.5 for Spanish-to-Mixtec and a TER of 16.5 for Mixtec-to-Spanish. Our research stands out as a pioneering effort in the field of automatic Mixtec-to-Spanish translation in Mexico, filling a gap identified in the current literature.

Pseudorelative clauses, infinitives, and gerunds with Spanish perception verbs: A comparative view

AbstractIn this paper, we provide a comparative analysis of three constructions that occur with perception verbs like ver (“see”) in Spanish: infinitives, gerunds, and so‐called pseudorelative clauses. We analyze several phenomena regarding the transparency status of the embedded inflected or uninflected clause, such as the availability of long (i.e., matrix) passive, short (i.e., embedded) passive, the occurrence of modal verbs, embedded negation, and left‐peripheral fronting. Our data from acceptability judgment tasks and a Spanish corpus led us to postulate that, albeit their surface similarities, the three examined constructions have different syntactic structures, reflected by their structural integration and the phasal versus nonphasal status of the embedded clause: We argue that gerunds are secondary predicates, while pseudorelatives and infinitives are complements of the perception verb. With respect to the latter two configurations, pseudorelatives are defective CPs (and thus weak phases) that allow (finite) raising‐to‐object, but not raising‐to‐subject. Infinitives, on the other hand, show interspeaker variation with respect to their structural size as voiceP or TP, accounting for variable acceptability judgments.

El léxico coloquial proveniente del lenguaje juvenil en la lengua de ficción española e italiana, versiones originales y meta

Abstract Youth lexicon has penetrated and become consolidated in the common colloquial register of adult speakers of any given language. This study uses a comparable bilingual corpus of original Spanish and Italian series, and a parallel trilingual corpus which includes the target Spanish and Italian versions of an analogous French series in order to investigate the use of such voices in national and foreign serial products of both cultures. The frequency of use per minute and the repertoire of terms inserted in the series of the two countries have been compared. The results show that the number of occurrences per minute in the Spanish original fictional language is much higher than in the Italian one, where this kind of words and expressions are often excluded. These data coincide with the number of occurrences per minute recorded in the Spanish and Italian target versions. Therefore, the parallelism between the original and target products of both languages shows that hybridization and domestication have been the predominant strategies in the translation for dubbing.

Design of an Automatic Tagging Algorithm for the Development of a Non-Literal Language Corpus in Spanish

Design of an Automatic Tagging Algorithm for the Development of a Non-Literal Language Corpus in Spanish

The effect of standardisation on collocations in Colombian and European Spanish translations of the work "Rootless"

The empirical study of syntactic, stylistic, and lexical patterns through corpora has frequently revealed a tendency towards standardisation, as Toury (1995/2012) defines it, in translated texts. In this vein, some studies have found that diatopy tends to become blurred in translations, particularly into transnational languages. In the case of Spanish, it has been stated that the enormous geographical richness of the language is not really reflected in translated Spanish. This paper argues that the translation of the work Rootless by Chris Howard into Colombian Spanish exhibits traits more typical of the European Spanish than of the Colombian Spanish variety. For this purpose, diatopic distribution of verb + noun (object) collocations extracted from a parallel corpus and a monolingual corpus of Rootless and its translations published in Colombian and European Spanish, is examined in a reference Spanish corpus.
 Keywords: parallel corpus; translated Spanish; Colombian Spanish; standardisation in translation; diatopic variation

Negation recognition in clinical natural language processing using a combination of the NegEx algorithm and a convolutional neural network

BackgroundImportant clinical information of patients is present in unstructured free-text fields of Electronic Health Records (EHRs). While this information can be extracted using clinical Natural Language Processing (cNLP), the recognition of negation modifiers represents an important challenge. A wide range of cNLP applications have been developed to detect the negation of medical entities in clinical free-text, however, effective solutions for languages other than English are scarce. This study aimed at developing a solution for negation recognition in Spanish EHRs based on a combination of a customized rule-based NegEx layer and a convolutional neural network (CNN).MethodsBased on our previous experience in real world evidence (RWE) studies using information embedded in EHRs, negation recognition was simplified into a binary problem (‘affirmative’ vs. ‘non-affirmative’ class). For the NegEx layer, negation rules were obtained from a publicly available Spanish corpus and enriched with custom ones, whereby the CNN binary classifier was trained on EHRs annotated for clinical named entities (cNEs) and negation markers by medical doctors.ResultsThe proposed negation recognition pipeline obtained precision, recall, and F1-score of 0.93, 0.94, and 0.94 for the ‘affirmative’ class, and 0.86, 0.84, and 0.85 for the ‘non-affirmative’ class, respectively. To validate the generalization capabilities of our methodology, we applied the negation recognition pipeline on EHRs (6,710 cNEs) from a different data source distribution than the training corpus and obtained consistent performance metrics for the ‘affirmative’ and ‘non-affirmative’ class (0.95, 0.97, and 0.96; and 0.90, 0.83, and 0.86 for precision, recall, and F1-score, respectively). Lastly, we evaluated the pipeline against two publicly available Spanish negation corpora, the IULA and NUBes, obtaining state-of-the-art metrics (1.00, 0.99, and 0.99; and 1.00, 0.93, and 0.96 for precision, recall, and F1-score, respectively).ConclusionNegation recognition is a source of low precision in the retrieval of cNEs from EHRs’ free-text. Combining a customized rule-based NegEx layer with a CNN binary classifier outperformed many other current approaches. RWE studies highly benefit from the correct recognition of negation as it reduces false positive detections of cNE which otherwise would undoubtedly reduce the credibility of cNLP systems.

Unpacking the Art of Customer Complaint Handling in Spanish and British Telecom Emails: A Cross-Cultural Webcare Study With a Human Touch

In spite of the rise of new media in a B2C context, companies still prefer to handle complaints privately. As such, many complaints are handled via email resulting in a professional communication genre of its own. In this study we performed a cross-cultural genre analysis to understand the specific discourse structure of the moves within response mails to complaints, on the one hand, and the importance of the communicative function of Conversational Human Voice within this genre, on the other. With this aim, we collected authentic organizational email replies to complaints from telecom companies active in the UK and Spain (36 and 44 emails respectively). The results indicate that the British and Spanish data sets show a similar discourse structure in terms of move frequency. The submoves that are prototypical for all data sets are Greeting, Explanation, Conclusion, and the closing submoves Sign-off and Signature. The data sets differ mainly in their frequency for the interpersonal submoves Empathy, Gratitude, and Apology, which are more prevalent in the English corpus, and the more business-oriented moves, such as Contact reason, Marketing, and Future contact, which are mainly present in the Spanish corpus. This suggests that organizational email replies to complaints are a rather conventionalized genre, with some linguacultures putting more effort in company-customer interactions by using more interpersonal submoves. Regarding the cross-cultural analysis of the expression of Conversational Human Voice we observed an influence of the respective linguacultures in the sense that the Spanish data are less personal and less invitational than the English mails, although they present more empathetic intensifiers. Furthermore, both data sets show only a limited extent of informal language. We evaluate these findings in the light of previous work.

Metaphor repositories: the case of the mental health metaphor dictionary

Abstract In recent years, there has been an emergence of online metaphor repositories. The purpose of this article is 2-fold. First, we present a review and comparison of the existing online databases of conceptual metaphors, showing that although there are a good number of domain-independent conceptual metaphor repositories based on English texts, repositories that are field-specific and/or in other languages are still scarce. Accordingly, the second goal of this article is to present the first metaphor repository specific to the mental health field, named The Mental Health Metaphor Dictionary. This repository is based on a Spanish corpus of first-person accounts published on social media (blogs and Twitter) by people suffering from severe mental disorders. We present the structure and the building process of the repository, and more significantly, we demonstrate its usefulness for a wide range of groups: professionals working in the field of mental health, public health communicators, family members or friends of people diagnosed with a mental disorder, the affected people themselves, and researchers of conceptual metaphors and discourse analysis in mental health.

Analysis of the Semantic Shift in Diachronic Word Embeddings for Spanish Before and After COVID-19

Words can shift their meaning across time. This study shows the results obtained by the exploratory analysis of the semantic shifting on Spanish vocabulary using Diachronic Word Embeddings. Diachronic data consists of a 2018 Spanish corpus, before the COVID-19 outbreak, and a second corpus with documents from 2021. This paper addresses the construction of the diachronic Spanish word embeddings model, as well as the results obtained by the analysis using a non-supervised distance vector technique. The results allowed us to identify topics with the most semantic shift between those periods.

Language contact phenomena in multiword units: The code-switching–calquing continuum

Aims and objectives: Code-switching and calquing are two widespread language contact phenomena in bilingual speech. While both phenomena have been discussed extensively in research on language contact in the past decades, only very few studies systematically investigate code-switching and calquing of and within multiword units or constructions. In our contribution, we aim at developing a more differentiated account of code-switching and calquing of and within multiword units and constructions, bringing together recent usage-based psycholinguistic and Construction Grammar theories and modeling with cognitively oriented approaches to language contact and bilingualism. Design: We analyze and discuss corpus data from the Corpus of Spanish in Southern Arizona (CESA) from first-, second-, and third-generation bilingual Spanish–English speakers in Arizona. Data and analysis: The corpus analysis focuses on code-switching and calquing of and within N Prep N, NN(N), and Adj N/N Adj patterns (N = noun, Prep = preposition, Adj = adjective). Findings/conclusions: The analysis highlights the importance of both lexically specific multiword units and partially and fully schematic constructions in code-switching and calquing as well as a continuum between constructions situated closer to the lexical or to the syntactic pole. Originality: Whereas multiword sequences have been found to play an important role in (mostly first language [L1]) acquisition, use, and processing, the role of multiword units and constructions in bilingual speech has been much less studied so far. Significance/implications: The study shows that both lexically specific constructions or multiword units as well as partially or fully schematic constructions play a central role in code-switching and calquing. The study argues that code-switching and calquing may ultimately be viewed as a continuum, since the speakers rely on similar, highly frequent, and productive constructions and their interlingual correspondences for both phenomena.

Analytics-driven complaint prioritisation via deep learning and multicriteria decision-making

Complaint analysis is an essential business analytics application because complaints have a strong influence on customer satisfaction (CSAT). However, the process of categorising and prioritising complaints manually can be extremely time consuming for large companies. In this paper, we propose a framework for automatic complaint labelling and prioritisation using text analytics and operational research techniques. The labelling step of the training set is performed using a simple weighting approach from the multiple-criteria decision-making (MCDM) literature, while transformer-based deep learning (DL) techniques are used for text classification. We define two priority classes, namely, urgent complaints and other claims, and develop a system for automatic complaint categorisation. Our experimental results show that excellent predictive performance can be achieved with state-of-the-art text classification models. In particular, BETO, a bidirectional encoder representations from transformers (BERT) model trained on a large Spanish corpus, reaches an accuracy (ACCU) and area under the curve (AUC) of 92.1% and 0.9785, respectively. This positive result translates into a successful complaint prioritisation scheme, which improves CSAT and reduces the churn rate.

Indirect translation and its influence on term variation

Abstract Term variation occurs when different designations are used to name the same concept. In institutional settings, such as the European Union, term variants multiply, partly as a result of the different languages and directions involved. Indirect translation is a recurrent practice in these multilingual contexts since it limits the number of language combinations, besides reducing costs and the need for translators. This paper describes how indirect translation via English has an influence on Spanish term variation in the European Union. We analyzed the EUR-Lex and Europarl English and Spanish corpora in Sketch Engine. The focus was on concepts related to Sustainable Development Goal 13: Climate Action, which are specifically addressed in these institutional corpora as a result of a long-standing environmental awareness. Our analysis indicates that indirect translation seems to have a subtle effect on term variants, since their proliferation seems to be mitigated when indirect translation is used.

Syllable‐final /s/ as an index of language, gender, and ethnicity in a contact variety of Mexican Spanish

AbstractThis study of syllable‐final /s/ reduction in a 55‐speaker corpus of Spanish in Juchitán, México, a contact variety, uses both language contact and social processes to explain its results. Contact with the indigenous Isthmus Zapotec language leads to decreased rates of syllable‐final /s/ retention, creating a locally salient n+1‐order index between “Zapotecness” and /s/ reduction that influences the indexical field for syllable‐final /s/ reduction. Zapotec identity is associated with tradition and femininity. Therefore, in this new indexical field, syllable‐final /s/ reduction comes to directly index Zapotec language dominance and indirectly index both femininity and tradition. This leads feminine and elderly speakers to reduce /s/ more frequently than “less feminine” and young speakers, even though the opposite pattern is usually found in other varieties. The results show, therefore, that language contact can influence the indexical field typically linked to socially meaningful variation and thereby cause unexpected patterns of variation to emerge.

Building a pedagogic spellchecker for L2 learners of Spanish

AbstractIn 2016, Lawley proposed an easy-to-build spellchecker specifically designed to help second language (L2) learners in their writing process by facilitating self-correction. The aim was to overcome the disadvantages to L2 learners posed by generic spellcheckers (GSC), such as that embedded in Microsoft Word. Drawbacks include autocorrection, misdiagnoses, and overlooked errors. With the aim of imparting explicit L2 spelling knowledge, this correcting tool does not merely suggest possible alternatives to the detected error but also provides explanations of any relevant spelling patterns. Following Lawley’s (2016) recommendations, the present study developed a prototype computer-based pedagogic spellchecker (PSC) to aid L2 learners in self-correcting their written production in Spanish. First, a corpus was used to identify frequent spelling errors of Spanish as a foreign language (SFL) learners. Handcrafted feedback was then designed to tackle the commonest misspellings. To subsequently evaluate this PSC’s efficacy in error detection and correction, another learner Spanish corpus was used. Sixty compositions were analysed to determine the PSC’s capacity for error recognition and feedback provision in comparison with that of a GSC. Results indicate that the PSC detected over 90% of the misspellings, significantly outperforming the GSC in error detection. Both provided adequate feedback on two out of three detected errors, but the pedagogic nature of the former has the added advantage of facilitating self-learning (Blázquez-Carretero & Woore, 2021). These findings suggest that it is feasible to develop spellcheckers that provide synchronous feedback, allowing SFL learners to confidently self-correct their writing while saving time and effort on the teacher’s part.

The role of the input frequency in L1 Spanish phonological acquisition. A corpus-based study

This study presents the phonological system exhibited by children (n=59) aged 3;0 to 6;0 and focuses on the role of input frequency. Using a spontaneous child speech corpus of Spanish (CHIEDE) as a data source, as well as computational processing techniques -including an automatic phonological transcriber-, data relating to the phonological level was retrieved. This resulted in a phonological inventory of Spanish-speaking children, ordered by frequency of use, which may serve as a model for research on typical and atypical child language development. Additionally, a study was carried out on the stability of the participants’ phonological systems by calculating the variability that the different age groups displayed, and outcomes were compared with other similar corpora. Results obtained from the comparison of the phonological inventory of children and adults show that there is a relationship between frequency of use in adult speech and the order of acquisition of phonemes.

Interference, explicitation, implicitation and normalization in third code Spanish: Evidence from discourse markers

AbstractThird code research has documented the distinctiveness of translated language and singled out recurrent tendencies framing them as translation universals. This paper aims to identify the interaction between interference, explicitation, implicitation and normalization and their potential relationship(s) with other variables, such as register. The focus of the study is on Spanish discourse markers (DMs) translated from English. This study uses interference, explicitation, implicitation and normalization as methodological tools to unveil these patterns. Evidence comes from a bilingual parallel corpus (P-ACTRES 2.0), a corpus of translated Spanish (CETRI), and a reference corpus of contemporary Spanish (CORPES XXI). We select the input DMs according to two criteria: first, we focus on DMs showing cross-linguistic formal correspondence, indicating the possibility of grammatical interference; second, we consider different procedural meanings for the DMs to anticipate potential regularity distortions. Results indicate that DM underuse in the target texts generally co-occurs with explicitation. Register is an important variable: implicitation is more frequent in non-fiction and, together with normalization, affects the majority of DMs. Evidence also points to the DMs' semantics influencing implicitation and explicitation.