Explaining Artificial Intelligence (AI) decisions is a major challenge nowadays in AI, in particular when applied to sensitive scenarios like medicine and law. However, the need to explain the rationale behind decisions is a main issues also for human-based deliberation as it is important to justify why a certain decision has been taken. Resident medical doctors for instance are required not only to provide a (possibly correct) diagnosis, but also to explain how they reached a certain conclusion. Developing new tools to aid residents to train their explanation skills is therefore a central objective of AI in education. In this paper, we follow this direction, and we present, to the best of our knowledge, the first multilingual dataset for Medical Question Answering where correct and incorrect diagnoses for a clinical case are enriched with a natural language explanation written by doctors. These explanations have been manually annotated with argument components (i.e., premise, claim) and argument relations (i.e., attack, support). The Multilingual CasiMedicos-arg dataset consists of 558 clinical cases (English, Spanish, French, Italian) with explanations, where we annotated 5021 claims, 2313 premises, 2431 support relations, and 1106 attack relations. We conclude by showing how competitive baselines perform over this challenging dataset for the argument mining task.

This paper proposes a novel approach to evaluate Counter Narrative (CN) generation using a Large Language Model (LLM) as an evaluator. We show that traditional automatic metrics correlate poorly with human judgements and fail to capture the nuanced relationship between generated CNs and human perception. To alleviate this, we introduce a model ranking pipeline based on pairwise comparisons of generated CNs from different models, organized in a tournament-style format. The proposed evaluation method achieves a high correlation with human preference, with a ρ score of 0.88. As an additional contribution, we leverage LLMs as zero-shot CN generators and provide a comparative analysis of chat, instruct, and base models, exploring their respective strengths and limitations. Through meticulous evaluation, including fine-tuning experiments, we elucidate the differences in performance and responsiveness to domain-specific data. We conclude that chat-aligned models in zero-shot are the best option for carrying out the task, provided they do not refuse to generate an answer due to security concerns.

The development of Large Language Models (LLMs) has brought impressive performances on mitigation strategies against misinformation, such as counterargument generation. However, LLMs are still seriously hindered by outdated knowledge and by their tendency to generate hallucinated content. In order to circumvent these issues, we propose a new task, namely, Critical Questions Generation, consisting of processing an argumentative text to generate the critical questions (CQs) raised by it.In argumentation theory CQs are tools designed to lay bare the blind spots of an argument by pointing at the information it could be missing.Thus, instead of trying to deploy LLMs to produce knowledgeable and relevant counterarguments, we use them to question arguments, without requiring any external knowledge.Research on CQs Generation using LLMs requires a reference dataset for large scale experimentation. Thus, in this work we investigate two complementary methods to create such a resource: (i) instantiating CQs templates as defined by Walton’s argumentation theory and (ii), using LLMs as CQs generators. By doing so, we contribute with a procedure to establish what is a valid CQ and conclude that, while LLMs are reasonable CQ generators, they still have a wide margin for improvement in this task.

Lemmatization is a natural language processing (NLP) task that consists of producing, from a given inflected word, its canonical form or lemma. Lemmatization is one of the basic tasks that facilitate downstream NLP applications, and is of particular importance for high-inflected languages. Given that the process to obtain a lemma from an inflected word can be explained by looking at its morphosyntactic category, including fine-grained morphosyntactic information to train contextual lemmatizers has become common practice, without considering whether that is the optimum in terms of downstream performance. In order to address this issue, in this article we empirically investigate the role of morphological information to develop contextual lemmatizers in six languages within a varied spectrum of morphological complexity: Basque, Turkish, Russian, Czech, Spanish, and English. Furthermore, and unlike the vast majority of previous work, we also evaluate lemmatizers in out-of-domain settings, which constitutes, after all, their most common application use. The results of our study are rather surprising. It turns out that providing lemmatizers with fine-grained morphological features during training is not that beneficial, not even for agglutinative languages. In fact, modern contextual word representations seem to implicitly encode enough morphological information to obtain competitive contextual lemmatizers without seeing any explicit morphological signal. Moreover, our experiments suggest that the best lemmatizers out-of-domain are those using simple UPOS tags or those trained without morphology and, lastly, that current evaluation practices for lemmatization are not adequate to clearly discriminate between models.

In this paper we introduce TextBI, a multimodal generic dashboard designed to present multidimensional text annotations on large volumes of multilingual social media data. This tool focuses on four core dimensions: spatial, temporal, thematic, and personal, and also supports additional enrichment data such as sentiment and engagement. Multiple visualization modes are offered, including frequency, movement, and association. This dashboard addresses the challenge of facilitating the interpretation of NLP annotations by visualizing them in a user-friendly, interactive interface catering to two categories of users: (1) domain stakeholders and (2) NLP researchers. We conducted experiments within the domain of tourism leveraging data from X (formerly Twitter) and incorporating requirements from tourism offices. Our approach, TextBI, represents a significant advancement in the field of visualizing NLP annotations by integrating and blending features from a variety of Business Intelligence, Geographical Information Systems and NLP tools. A demonstration video is also provided https://youtu.be/x714RKvo9Cg

Recent research on sequence labelling has been exploring different strategies to mitigate the lack of manually annotated data for the large majority of the world languages. Among others, the most successful approaches have been based on (i) the crosslingual transfer capabilities of multilingual pre-trained language models (model-transfer), (ii) data translation and label projection (data-transfer) and (iii), prompt-based learning by reusing the mask objective to exploit the few-shot capabilities of pre-trained language models (few-shot). Previous work seems to conclude that model-transfer outperform data-transfer methods and that few-shot techniques based on prompting are superior to updating the model’s weights via fine-tuning. In this paper we empirically demonstrate that, for Argument Mining, a sequence labelling task which requires the detection of long and complex discourse structures, previous insights on crosslingual transfer or few-shot learning do not apply. Contrary to previous work, we show that for Argument Mining data-transfer obtains better results than model-transfer and that fine-tuning outperforms few-shot methods. Regarding the former, the domain of the dataset used for data-transfer seems to be a deciding factor, while, for few-shot, the type of task (length and complexity of the sequence spans) and sampling method proves to be crucial.

Counter Narratives (CNs) are non-negative textual responses to Hate Speech (HS) aiming at defusing online hatred and mitigating its spreading across media. Despite the recent increase in HS content posted online, research on automatic CN generation has been relatively scarce and predominantly focused on English. In this paper, we present CONAN-EUS, a new Basque and Spanish dataset for CN generation developed by means of Machine Translation (MT) and professional post-edition. Being a parallel corpus, also with respect to the original English CONAN, it allows to perform novel research on multilingual and crosslingual automatic generation of CNs. Our experiments on CN generation with mT5, a multilingual encoder-decoder model, shows that generation greatly benefits from training on post-edited data, as opposed to relying on silver MT data only. These results are confirmed by their correlation with a qualitative manual evaluation, demonstrating that manually revised training data remains crucial for the quality of the generated CNs. Furthermore, multilingual data augmentation improves results over monolingual settings for structurally similar languages such as English and Spanish, while being detrimental for Basque, a language isolate. Similar findings occur in zero-shot crosslingual evaluations, where model transfer (fine-tuning in English and generating in a different target language) outperforms fine-tuning mT5 on machine translated data for Spanish but not for Basque. This provides an interesting insight into the asymmetry in the multilinguality of generative models, a challenging topic which is still open to research. Data and code will be made publicly available upon publication.

Modern contextual lemmatizers often rely on automatically induced Shortest Edit Scripts (SES), namely, the number of edit operations to transform a word form into its lemma. In fact, different methods of computing SES have been proposed as an integral component in the architecture of several state-of-the-art contextual lemmatizers currently available. However, previous work has not investigated the direct impact of SES in the final lemmatization performance. In this paper we address this issue by focusing on lemmatization as a token classification task where the only input that the model receives is the word-label pairs in context, where the labels correspond to previously induced SES. Thus, by modifying in our lemmatization system only the SES labels that the model needs to learn, we may then objectively conclude which SES representation produces the best lemmatization results. We experiment with seven languages of different morphological complexity, namely, English, Spanish, Basque, Russian, Czech, Turkish and Polish, using multilingual and language-specific pre-trained masked language encoder-only models as a backbone to build our lemmatizers. Comprehensive experimental results, both in- and out-of-domain, indicate that computing the casing and edit operations separately is beneficial overall, but much more clearly for languages with high-inflected morphology. Notably, multilingual pre-trained language models consistently outperform their language-specific counterparts in every evaluation setting.

Research on language technology for the development of medical applications is currently a hot topic in Natural Language Understanding and Generation. Thus, a number of large language models (LLMs) have recently been adapted to the medical domain, so that they can be used as a tool for mediating in human-AI interaction. While these LLMs display competitive performance on automated medical texts benchmarks, they have been pre-trained and evaluated with a focus on a single language (English mostly). This is particularly true of text-to-text models, which typically require large amounts of domain-specific pre-training data, often not easily accessible for many languages. In this paper, we address these shortcomings by compiling, to the best of our knowledge, the largest multilingual corpus for the medical domain in four languages, namely English, French, Italian and Spanish. This new corpus has been used to train Medical mT5, the first open-source text-to-text multilingual model for the medical domain. Additionally, we present two new evaluation benchmarks for all four languages with the aim of facilitating multilingual research in this domain. A comprehensive evaluation shows that Medical mT5 outperforms both encoders and similarly sized text-to-text models for the Spanish, French, and Italian benchmarks, while being competitive with current state-of-the-art LLMs in English.

Large language models are very resource intensive, both financially and environmentally, and require an amount of training data which is simply unobtainable for the majority of NLP practitioners. Previous work has researched the scaling laws of such models, but optimal ratios of model parameters, dataset size, and computation costs focused on the large scale. In contrast, we analyze the effect those variables have on the performance of language models in constrained settings, by building three lightweight BERT models (16M/51M/124M parameters) trained over a set of small corpora (5M/25M/125M words).We experiment on four languages of different linguistic characteristics (Basque, Spanish, Swahili and Finnish), and evaluate the models on MLM and several NLU tasks. We conclude that the power laws for parameters, data and compute for low-resource settings differ from the optimal scaling laws previously inferred, and data requirements should be higher. Our insights are consistent across all the languages we study, as well as across the MLM and downstream tasks. Furthermore, we experimentally establish when the cost of using a Transformer-based approach is worth taking, instead of favouring other computationally lighter solutions.

In the absence of readily available labeled data for a given sequence labeling task and language, annotation projection has been proposed as one of the possible strategies to automatically generate annotated data. Annotation projection has often been formulated as the task of transporting, on parallel corpora, the labels pertaining to a given span in the source language into its corresponding span in the target language. In this paper we present T-Projection, a novel approach for annotation projection that leverages large pretrained text2text language models and state-of-the-art machine translation technology. T-Projection decomposes the label projection task into two subtasks: (i) A candidate generation step, in which a set of projection candidates using a multilingual T5 model is generated and, (ii) a candidate selection step, in which the generated candidates are ranked based on translation probabilities. We conducted experiments on intrinsic and extrinsic tasks in 5 Indo-European and 8 low-resource African languages. We demostrate that T-projection outperforms previous annotation projection methods by a wide margin. We believe that T-Projection can help to automatically alleviate the lack of high-quality training data for sequence labeling tasks. Code and data are publicly available.

The lack of wide coverage datasets annotated with everyday metaphorical expressions for languages other than English is striking. This means that most research on supervised metaphor detection has been published only for that language. In order to address this issue, this work presents the first corpus annotated with naturally occurring metaphors in Spanish large enough to develop systems to perform metaphor detection. The presented dataset, CoMeta, includes texts from various domains, namely, news, political discourse, Wikipedia and reviews. In order to label CoMeta, we apply the MIPVU method, the guidelines most commonly used to systematically annotate metaphor on real data. We use our newly created dataset to provide competitive baselines by fine-tuning several multilingual and monolingual state-of-the-art large language models. Furthermore, by leveraging the existing VUAM English data in addition to CoMeta, we present the, to the best of our knowledge, first cross-lingual experiments on supervised metaphor detection. Finally, we perform a detailed error analysis that explores the seemingly high transfer of everyday metaphor across these two languages and datasets.

The influence of fake news in the perception of reality has become a mainstream topic in the last years due to the fast propagation of misleading information. In order to help in the fight against misinformation, automated solutions to fact-checking are being actively developed within the research community. In this context, the task of Automated Claim Verification is defined as assessing the truthfulness of a claim by finding evidence about its veracity. In this work we empirically demonstrate that enriching a BERT model with explicit semantic information such as Semantic Role Labelling helps to improve results in claim verification as proposed by the FEVER benchmark. Furthermore, we perform a number of explainability tests that suggest that the semantically-enriched model is better at handling complex cases, such as those including passive forms or multiple propositions.

The vast majority of non-English corpora are derived from automatically filtered versions of CommonCrawl. While prior work has identified major issues on the quality of these datasets (Kreutzer et al., 2021), it is not clear how this impacts downstream performance. Taking representation learning in Basque as a case study, we explore tailored crawling (manually identifying and scraping websites with high-quality content) as an alternative to filtering CommonCrawl. Our new corpus, called EusCrawl, is similar in size to the Basque portion of popular multilingual corpora like CC100 and mC4, yet it has a much higher quality according to native annotators. For instance, 66% of documents are rated as high-quality for EusCrawl, in contrast with <33% for both mC4 and CC100. Nevertheless, we obtain similar results on downstream NLU tasks regardless of the corpus used for pre-training. Our work suggests that NLU performance in low-resource languages is not primarily constrained by the quality of the data, and other factors like corpus size and domain coverage can play a more important role.

Zero-resource cross-lingual transfer approaches aim to apply supervised modelsfrom a source language to unlabelled target languages. In this paper we performan in-depth study of the two main techniques employed so far for cross-lingualzero-resource sequence labelling, based either on data or model transfer.Although previous research has proposed translation and annotation projection(data-based cross-lingual transfer) as an effective technique for cross-lingualsequence labelling, in this paper we experimentally demonstrate that highcapacity multilingual language models applied in a zero-shot (model-basedcross-lingual transfer) setting consistently outperform data-basedcross-lingual transfer approaches. A detailed analysis of our results suggeststhat this might be due to important differences in language use. Morespecifically, machine translation often generates a textual signal which isdifferent to what the models are exposed to when using gold standard data,which affects both the fine-tuning and evaluation processes. Our results alsoindicate that data-based cross-lingual transfer approaches remain a competitiveoption when high-capacity multilingual language models are not available.

Natural Language Understanding (NLU) technology has improved significantly over the last few years and multitask benchmarks such as GLUE are key to evaluate this improvement in a robust and general way. These benchmarks take into account a wide and diverse set of NLU tasks that require some form of language understanding, beyond the detection of superficial, textual clues. However, they are costly to develop and language-dependent, and therefore they are only available for a small number of languages. In this paper, we present BasqueGLUE, the first NLU benchmark for Basque, a less-resourced language, which has been elaborated from previously existing datasets and following similar criteria to those used for the construction of GLUE and SuperGLUE. We also report the evaluation of two state-of-the-art language models for Basque on BasqueGLUE, thus providing a strong baseline to compare upon. BasqueGLUE is freely available under an open license.

Parliamentary transcripts provide a valuable resource to understand the reality and know about the most important facts that occur over time in our societies. Furthermore, the political debates captured in these transcripts facilitate research on political discourse from a computational social science perspective. In this paper we release the first version of a newly compiled corpus from Basque parliamentary transcripts. The corpus is characterized by heavy Basque-Spanish code-switching, and represents an interesting resource to study political discourse in contrasting languages such as Basque and Spanish. We enrich the corpus with metadata related to relevant attributes of the speakers and speeches (language, gender, party...) and process the text to obtain named entities and lemmas. The obtained metadata is then used to perform a detailed corpus analysis which provides interesting insights about the language use of the Basque political representatives across time, parties and gender.

In this paper, we introduce the first SemEval shared task on Structured Sentiment Analysis, for which participants are required to predict all sentiment graphs in a text, where a single sentiment graph is composed of a sentiment holder, target, expression and polarity. This new shared task includes two subtracks (monolingual and cross-lingual) with seven datasets available in five languages, namely Norwegian, Catalan, Basque, Spanish and English. Participants submitted their predictions on a held-out test set and were evaluated on Sentiment Graph F1 . Overall, the task received over 200 submissions from 32 participating teams. We present the results of the 15 teams that provided system descriptions and our own expanded analysis of the test predictions.

The growing interest in employing counter narratives for hatred intervention brings with it a focus on dataset creation and automation strategies. In this scenario, learning to recognize counter narrative types from natural text is expected to be useful for applications such as hate speech countering, where operators from non-governmental organizations are supposed to answer to hate with several and diverse arguments that can be mined from online sources. This paper presents the first multilingual work on counter narrative type classification, evaluating SoTA pre-trained language models in monolingual, multilingual and cross-lingual settings. When considering a fine-grained annotation of counter narrative classes, we report strong baseline classification results for the majority of the counter narrative types, especially if we translate every language to English before cross-lingual prediction. This suggests that knowledge about counter narratives can be successfully transferred across languages.

In the last few years, several methods have been proposed to build meta-embeddings. The general aim was to obtain new representations integrating complementary knowledge from different source pre-trained embeddings thereby improving their overall quality. However, previous meta-embeddings have been evaluated using a variety of methods and datasets, which makes it difficult to draw meaningful conclusions regarding the merits of each approach. In this paper we propose a unified common framework, including both intrinsic and extrinsic tasks, for a fair and objective meta-embeddings evaluation. Furthermore, we present a new method to generate meta-embeddings, outperforming previous work on a large number of intrinsic evaluation benchmarks. Our evaluation framework also allows us to conclude that previous extrinsic evaluations of meta-embeddings have been overestimated.

Stance detection aims to determine the attitude of a given text with respect to a specific topic or claim. While stance detection has been fairly well researched in the last years, most the work has been focused on English. This is mainly due to the relative lack of annotated data in other languages. The TW-10 referendum Dataset released at IberEval 2018 is a previous effort to provide multilingual stance-annotated data in Catalan and Spanish. Unfortunately, the TW-10 Catalan subset is extremely imbalanced. This paper addresses these issues by presenting a new multilingual dataset for stance detection in Twitter for the Catalan and Spanish languages, with the aim of facilitating research on stance detection in multilingual and cross-lingual settings. The dataset is annotated with stance towards one topic, namely, the ndependence of Catalonia. We also provide a semi-automatic method to annotate the dataset based on a categorization of Twitter users. We experiment on the new corpus with a number of supervised approaches, including linear classifiers and deep learning methods. Comparison of our new corpus with the with the TW-1O dataset shows both the benefits and potential of a well balanced corpus for multilingual and cross-lingual research on stance detection. Finally, we establish new state-of-the-art results on the TW-10 dataset, both for Catalan and Spanish.

Word embeddings and pre-trained language models allow to build rich representations of text and have enabled improvements across most NLP tasks. Unfortunately they are very expensive to train, and many small companies and research groups tend to use models that have been pre-trained and made available by third parties, rather than building their own. This is suboptimal as, for many languages, the models have been trained on smaller (or lower quality) corpora. In addition, monolingual pre-trained models for non-English languages are not always available. At best, models for those languages are included in multilingual versions, where each language shares the quota of substrings and parameters with the rest of the languages. This is particularly true for smaller languages such as Basque. In this paper we show that a number of monolingual models (FastText word embeddings, FLAIR and BERT language models) trained with larger Basque corpora produce much better results than publicly available versions in downstream NLP tasks, including topic classification, sentiment classification, PoS tagging and NER. This work sets a new state-of-the-art in those tasks for Basque. All benchmarks and models used in this work are publicly available.

In this paper we describe our participation to the Hyperpartisan News Detection shared task at SemEval 2019. Motivated by the late arrival of Doris Martin, we test a previously developed document classification system which consists of a combination of clustering features implemented on top of some simple shallow local features. We show how leveraging distributional features obtained from large in-domain unlabeled data helps to easily and quickly develop a reasonably good performing system for detecting hyperpartisan news. The system and models generated for this task are publicly available.

IXA pipeline is a modular set of Natural Language Processing tools (or pipes) which provide easy access to NLP technology. It offers robust and efficient linguistic annotation to both researchers and non-NLP experts with the aim of lowering the barriers of using NLP technology either for research purposes or for small industrial developers and SMEs. IXA pipeline can be used “as is” or exploit its modularity to pick and change different components. Given its open-source nature, it can also be modified and extended for it to work with other languages. This paper describes the general data-centric architecture of IXA pipeline and presents competitive results in several NLP annotations for English and Spanish.

In this paper we focus on the creation of general-purpose (as opposed to domain-specific) polarity lexicons in five languages: French, Italian, Dutch, English and Spanish using WordNet propagation. WordNet propagation is a commonly used method to generate these lexicons as it gives high coverage of general purpose language and the semantically rich WordNets where concepts are organised in synonym , antonym and hyperonym/hyponym structures seem to be well suited to the identification of positive and negative words. However, WordNets of different languages may vary in many ways such as the way they are compiled, the number of synsets, number of synonyms and number of semantic relations they include. In this study we investigate whether this variability translates into differences of performance when these WordNets are used for polarity propagation. Although many variants of the propagation method are developed for English, little is known about how they perform with WordNets of other languages. We implemented a propagation algorithm and designed a method to obtain seed lists similar with respect to quality and size, for each of the five languages. We evaluated the results against gold standards also developed according to a common method in order to achieve as less variance as possible between the different languages.

Subtitling and audiovisual translation have been recognized as areas that could greatly benefit from the introduction of Statistical Machine Translation (SMT) followed by post-editing, in order to increase efficiency of subtitle production process. The FP7 European project SUMAT (An Online Service for SUbtitling by MAchine Translation: http://www.sumat-project.eu) aims to develop an online subtitle translation service for nine European languages, combined into 14 different language pairs, in order to semi-automate the subtitle translation processes of both freelance translators and subtitling companies on a large scale. In this paper we discuss the data collection and parallel corpus compilation for training SMT systems, which includes several procedures such as data partition, conversion, formatting, normalization and alignment. We discuss in detail each data pre-processing step using various approaches. Apart from the quantity (around 1 million subtitles per language pair), the SUMAT corpus has a number of very important characteristics. First of all, high quality both in terms of translation and in terms of high-precision alignment of parallel documents and their contents has been achieved. Secondly, the contents are provided in one consistent format and encoding. Finally, additional information such as type of content in terms of genres and domain is available.

This paper presents Q-WordNet, a lexical resource consisting of WordNet senses automatically annotated by positive and negative polarity. Polarity classification amounts to decide whether a text (sense, sentence, etc.) may be associated to positive or negative connotations. Polarity classification is becoming important within the fields of Opinion Mining and Sentiment Analysis for determining opinions about commercial products, on companies reputation management, brand monitoring, or to track attitudes by mining online forums, blogs, etc. Inspired by work on classification of word senses by polarity (e.g., SentiWordNet), and taking WordNet as a starting point, we build Q-WordNet. Instead of applying external tools such as supervised classifiers to annotated WordNet synsets by polarity, we try to effectively maximize the linguistic information contained in WordNet, thereby taking advantage of the human effort put by lexicographers and annotators. The resulting resource is a subset of WordNet senses classified as positive or negative. In this approach, neutral polarity is seen as the absence of positive or negative polarity. The evaluation of Q-WordNet shows an improvement with respect to previous approaches. We believe that Q-WordNet can be used as a starting point for data-driven approaches in sentiment analysis.