In this paper, we present the two strategies employed for the WMT24 Shared Task on Translation into Low-Resource Languages of Spain. We participated in the language pairs of Spanish-to-Aragonese, Spanish-to-Aranese, and Spanish-to-Asturian, developing neural-based translation systems and moving away from rule-based approaches for these language directions. To create these models, two distinct strategies were employed. The first strategy involved a thorough cleaning process and curation of the limited provided data, followed by fine-tuning the multilingual NLLB-200-600M model (Constrained Submission). The other strategy involved training a transformer from scratch using a vast amount of synthetic data (Open Submission). Both approaches relied on generated synthetic data and resulted in high ChrF and BLEU scores. However, given the characteristics of the task, the strategy used in the Constrained Submission resulted in higher scores that surpassed the baselines across the three translation directions, whereas the strategy employed in the Open Submission yielded slightly lower scores than the highest baseline.

The development of language technologies (LTs) such as machine translation, text analytics, and dialogue systems is essential in the current digital society, culture and economy. These LTs, widely supported in languages in high demand worldwide, such as English, are also necessary for smaller and less economically powerful languages, as they are a driving force in the democratization of the communities that use them due to their great social and cultural impact. As an example, dialogue systems allow us to communicate with machines in our own language; machine translation increases access to contents in different languages, thus facilitating intercultural relations; and text-to-speech and speech-to-text systems broaden different categories of users’ access to technology. In the case of Galician (co-official language, together with Spanish, in the autonomous region of Galicia, located in northwestern Spain), incorporating the language into state-of-the-art AI applications can not only significantly favor its prestige (a decisive factor in language normalization), but also guarantee citizens’ language rights, reduce social inequality, and narrow the digital divide. This is the main motivation behind the Nós Project (Proxecto Nós), which aims to have a significant contribution to the development of LTs in Galician (currently considered a low-resource language) by providing openly licensed resources, tools, and demonstrators in the area of intelligent technologies.

This article describes some unsupervised strategies submitted to SemEval 2020 Task 3, a task which consists of considering the effect of context to compute word similarity. More precisely, given two words in context, the system must predict the degree of similarity of those words considering the context in which they occur, and the system score is compared against human prediction. We compare one approach based on pre-trained BERT models with other strategy relying on static word embeddings and syntactic dependencies. The BERT-based method clearly outperformed the dependency-based strategy.

This article describes the strategy submitted by the CiTIUS-COLE team to SemEval 2019 Task 5, a task which consists of binary classi- fication where the system predicting whether a tweet in English or in Spanish is hateful against women or immigrants or not. The proposed strategy relies on combining linguis- tic features to improve the classifier’s perfor- mance. More precisely, the method combines textual and lexical features, embedding words with the bag of words in Term Frequency- Inverse Document Frequency (TF-IDF) repre- sentation. The system performance reaches about 81% F1 when it is applied to the training dataset, but its F1 drops to 36% on the official test dataset for the English and 64% for the Spanish language concerning the hate speech class

This article describes a compositional distributional method to generate contextualized senses of words and identify their appropriate translations in the target language using monolingual corpora. Word translation is modeled in the same way as contextualization of word meaning, but in a bilingual vector space. The contextualization of meaning is carried out by means of distributional composition within a structured vector space with syntactic dependencies, and the bilingual space is created by means of transfer rules and a bilingual dictionary. A phrase in the source language, consisting of a head and a dependent, is translated into the target language by selecting both the nearest neighbor of the head given the dependent, and the nearest neighbor of the dependent given the head. This process is expanded to larger phrases by means of incremental composition. Experiments were performed on English and Spanish monolingual corpora in order to translate phrasal verbs in context. A new bilingual data set to evaluate strategies aimed at translating phrasal verbs in restricted syntactic domains has been created and released.

This article describes a dependency-based strategy that uses compositional distributional semantics and cross-lingual word embeddings to translate multiword expressions (MWEs). Our unsupervised approach performs translation as a process of word contextualization by taking into account lexico-syntactic contexts and selectional preferences. This strategy is suited to translate phraseological combinations and phrases whose constituent words are lexically restricted by each other. Several experiments in adjective-noun and verb-object compounds show that mutual contextualization (co-compositionality) clearly outperforms other compositional methods. The paper also contributes with a new freely available dataset of English-Spanish MWEs used to validate the proposed compositional strategy.

The objective of this work is to quantify, with a simple and robust measure, the distance between historical varieties of a language. The measure will be inferred from text corpora corresponding to historical periods. Different approaches have been proposed for similar aims: Language Identification, Phylogenetics, Historical Linguistics or Dialectology. In our approach, we used a perplexity-based measure to calculate language distance between all the historical periods of a specific language: European Portuguese. Perplexity has also proven to be a robust metric to calculate distance between languages. However, this measure has not been tested yet to identify diachronic periods within the historical evolution of a specific language. For this purpose, a historical Portuguese corpus has been constructed from different open sources containing texts with close original spelling. The results of our experiments show that Portuguese keeps an important degree of homogeneity over time. We anticipate this metric to be a starting point to be applied to other languages.

This article describes the unsupervised strategy submitted by the CitiusNLP team to the SemEval 2018 Task 10, a task which consists of predict whether a word is a discriminative attribute between two other words. Our strategy relies on the correspondence between discriminative attributes and relevant contexts of a word. More precisely, the method uses transparent distributional models to extract salient contexts of words which are identified as discriminative attributes. The system performance reaches about 70% accuracy when it is applied on the development dataset, but its accuracy goes down (63%) on the official test dataset.

This article describes MetaRomance, a rule-based cross-lingual parser for Romance languages submitted to CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies. The system is an almost delexicalized parser which does not need training data to analyze Romance languages. It contains linguistically motivated rules based on PoS-tag patterns. The rules included in MetaRomance were developed in about 12 hours by one expert with no prior knowledge in Universal Dependencies, and can be easily extended using a transparent formalism. In this paper we compare the performance of MetaRomance with other supervised systems participating in the competition, paying special attention to the parsing of different treebanks of the same language. We also compare our system with a delexicalized parser for Romance languages, and take advantage of the harmonized annotation of Universal Dependencies to propose a language ranking based on the syntactic distance each variety has from Romance languages.

This article describes the distributional strategy submitted by the Citius team to the SemEval 2017 Task 2. Even though the team participated in two subtasks, namely monolingual and cross-lingual word similarity, the article is mainly focused on the cross-lingual subtask. Our method uses comparable corpora and syntactic dependencies to extract count-based and transparent bilingual distributional contexts. The evaluation of the results show that our method is competitive with other cross-lingual strategies, even those using aligned and parallel texts.

This article describes a semantic system which is based on distributional models obtained from a chronologically structured language resource, namely Google Books Syntactic Ngrams. The models were created using dependency-based contexts and a strategy for reducing the vector space, which consists in selecting the more informative and relevant word contexts. The system allowslinguists to analize meaning change of Spanish words in the written language across time.

This article describes the system submitted by the Citius_Ixa_Imaxin team to the VarDial 2017 (DSL and GDI tasks). The strategy underlying our system is based on a language distance computed by means of model perplexity. The best model configuration we have tested is a voting system making use of several n-grams models of both words and characters, even if word unigrams turned out to be a very competitive model with reasonable results in the tasks we have participated. An error analysis has been performed in which we identified many test examples with no linguistic evidences to distinguish among the variants.

This article describes a method to build semantic representations of composite expressions in a compositional way by using WordNet relations to represent the meaning of words. The meaning of a target word is modelled as a vector in which its semantically related words are assigned weights according to both the type of the relationship and the distance to the target word. Word vectors are compositionally combined by syntactic dependencies. Each syntactic dependency triggers two complementary compositional functions: the named head function and dependent function. The experiments show that the proposed compositional method outperforms the state-of-the-art for both intransitive subject-verb and transitive subject-verb-object constructions.

Little attention has been paid to distributional compositional methods which employ syntactically structured vector models. As word vectors belonging to different syntactic categories have incompatible syntactic distributions, no trivial compositional operation can be applied to combine them into a new compositional vector. In this article, we generalize the method described by Erk and Padó (2009) by proposing a dependency-base framework that contextualize not only lemmas but also selectional preferences. The main contribution of the article is to expand their model to a fully compositional framework in which syntactic dependencies are put at the core of semantic composition. We claim that semantic composition is mainly driven by syntactic dependencies. Each syntactic dependency generates two new compositional vectors representing the contextualized sense of the two related lemmas. The sequential application of the compositional operations associated to the dependencies results in as many contextualized vectors as lemmas the composite expression contains. At the end of the semantic process, we do not obtain a single compositional vector representing the semantic denotation of the whole composite expression, but one contextualized vector for each lemma of the whole expression. Our method avoids the troublesome high-order tensor representations by defining lemmas and selectional restrictions as first-order tensors (i.e. standard vectors). A corpus-based experiment is performed to both evaluate the quality of the compositional vectors built with our strategy, and to compare them to other approaches on distributional compositional semantics. The experiments show that our dependency-based compositional method performs as (or even better than) the state-of-the-art.

This article describes the systems submitted by the Citius_Ixa_Imaxin team to the Discriminating Similar Languages Shared Task 2016. The systems are based on two different strategies: classification with ranked dictionaries and Naive Bayes classifiers. The results of the evaluation show that ranking dictionaries are more sound and stable across different domains while basic bayesian models perform reasonably well on in-domain datasets, but their performance drops when they are applied on out-of-domain texts.

We introduce TweetMT, a parallel corpus of tweets in four language pairs that combine five languages (Spanish from/to Basque, Catalan, Galician and Portuguese), all of which have an official status in the Iberian Peninsula. The corpus has been created by combining automatic collection and crowdsourcing approaches, and it is publicly available. It is intended for the development and testing of microtext machine translation systems. In this paper we describe the methodology followed to build the corpus, and present the results of the shared task in which it was tested.

In this paper we introduce TweetNorm_es, an annotated corpus of tweets in Spanish language, which we make publicly available under the terms of the CC-BY license. This corpus is intended for development and testing of microtext normalization systems. It was created for Tweet-Norm, a tweet normalization workshop and shared task, and is the result of a joint annotation effort from different research groups. In this paper we describe the methodology defined to build the corpus as well as the guidelines followed in the annotation process. We also present a brief overview of the Tweet-Norm shared task, as the first evaluation environment where the corpus was used.

This paper presents three corpora with coreferential annotation of person entities for Portuguese, Galician and Spanish. They contain coreference links between several types of pronouns (including elliptical, possessive, indefinite, demonstrative, relative and personal clitic and non-clitic pronouns) and nominal phrases (including proper nouns). Some statistics have been computed, showing distributional aspects of coreference both in journalistic and in encyclopedic texts. Furthermore, the paper shows the importance of coreference resolution for a task such as Information Extraction, by evaluating the output of an Open Information Extraction system on the annotated corpora. The corpora are freely distributed in two formats: (i) the SemEval-2010 and (ii) the brat rapid annotation tool, so they can be enlarged and improved collaboratively.

This paper describes a specific semantic property underlying binary dependencies: co-composition. We propose a more general definition than that given by Pustejovsky, what we call “optional co-composition”. The aim of the paper is to explore the benefits of optional cocomposition in two disambiguation tasks: both word sense and structural disambiguation. Concerning the second task, some experiments were performed on large corpora.