Lucas C. Cordeiro, Matthew L. Daggitt, Julien Girard-Satabin
et al.
Neural network verification is a new and rapidly developing field of research. So far, the main priority has been establishing efficient verification algorithms and tools, while proper support from the programming language perspective has been considered secondary or unimportant. Yet, there is mounting evidence that insights from the programming language community may make a difference in the future development of this domain. In this paper, we formulate neural network verification challenges as programming language challenges and suggest possible future solutions.
Kleinberg and Mullainathan showed that language generation in the limit is always possible at the level of computability: given enough positive examples, a learner can eventually generate data indistinguishable from a target language. However, such existence results do not address feasibility. We study the sample complexity of language generation in the limit for several canonical classes of formal languages. Our results show that infeasibility already appears for context-free and regular languages, and persists even for strict subclasses such as locally threshold testable languages, as well as for incomparable classes such as non-erasing pattern languages, a well-studied class in the theory of language identification. Overall, our results establish a clear gap between the theoretical possibility of language generation in the limit and its computational feasibility.
Jesus Alvarez C, Daua D. Karajeanes, Ashley Celeste Prado
et al.
The digital exclusion of endangered languages remains a critical challenge in NLP, limiting both linguistic research and revitalization efforts. This study introduces the first computational investigation of Comanche, an Uto-Aztecan language on the verge of extinction, demonstrating how minimal-cost, community-informed NLP interventions can support language preservation. We present a manually curated dataset of 412 phrases, a synthetic data generation pipeline, and an empirical evaluation of GPT-4o and GPT-4o-mini for language identification. Our experiments reveal that while LLMs struggle with Comanche in zero-shot settings, few-shot prompting significantly improves performance, achieving near-perfect accuracy with just five examples. Our findings highlight the potential of targeted NLP methodologies in low-resource contexts and emphasize that visibility is the first step toward inclusion. By establishing a foundation for Comanche in NLP, we advocate for computational approaches that prioritize accessibility, cultural sensitivity, and community engagement.
Extinct and endangered languages have been preserved primarily through audio conservation and the collection and digitization of scripts and have been promoted through targeted language acquisition efforts. Another possibility would be to build conversational agents like chatbots or voice assistants that can master these languages. This would provide an artificial, active conversational partner which has knowledge of the vocabulary and grammar and allows one to learn with it in a different way. The chatbot, @llegra, with which one can communicate in the Rhaeto-Romanic idiom Vallader was developed in 2023 based on GPT-4. It can process and output text and has voice output. It was additionally equipped with a manually created knowledge base. After laying the conceptual groundwork, this paper presents the preparation and implementation of the project. In addition, it summarizes the tests that native speakers conducted with the chatbot. A critical discussion elaborates advantages and disadvantages. @llegra could be a new tool for teaching and learning Vallader in a memorable and entertaining way through dialog. It not only masters the idiom, but also has extensive knowledge about the Lower Engadine, that is, the area where Vallader is spoken. In conclusion, it is argued that conversational agents are an innovative approach to promoting and preserving languages.
The aim of this article is to analyse the role of biblical references in Al Berto’s (Alberto Raposo Pidwell Tavares’) last poetry volume, Horto de Incêndio, published in 1997. Previous research on this poetry has identified intertextuality, an interest in corporeality and the problem of the relationship between experience and text as dominant features of this work. Building upon these insights, I demonstrate that the numerous allusions to the Bible, especially evocations of the Apocalypse, in Horto de Incêndio are related to the author’s attempt to textualise the experience of illness and allow us to partially reconstruct his view of the ontology of the literary text.
Context-free languages can be characterized in several ways. This article studies projective linearisations of languages of simple dependency trees, i.e., dependency trees in which a node can govern at most one node with a given syntactic function. We prove that the projective linearisations of local languages of simple dependency trees coincide with the context-free languages. Simple dependency trees suggest alternative dual notions of locality and projectivity, which permits defining a dual language for each context-free language. We call this new class of languages anti-context-free. These languages are related to some linguistic constructions exhibiting the so-called cross-serial dependencies that were historically important for the development of computational linguistics. We propose that this duality could be a relevant linguistic phenomenon.
A problematic term and/or a disturbing reality
Often dubious or allergic, even downright negative, the reactions to the word “Francophone”, a term whose meaning is nevertheless clear, do not fail to raise questions. They are particularly strong in the literary field where more and more Francophone literatures are developing, the emergence, study and recognition of which always come up against resistance without equal in other linguistic areas resulting from European colonization. The explanation lies at the very heart of the History of France and of the Franco-French structures for apprehending the world – particularly through the place and the conception of the language and literature that signify it – what the author calls the French ideology. The effects of Parisian editorial centralism, unique in the world, are also studied, as well as the contrasting consequences of the political use made of the French language and its supposed universality. Diverse historical strata and contemporary contradictions are meticulously analysed, as well as the obstacles to considering and building a plural Franco-Francophone space. What the rejection of the word “Francophone” refers to is the realities that it designates and forces us to recognize fundamentally. They call into question a habitus.
Machine translation has seen rapid progress with the advent of Transformer-based models. These models have no explicit linguistic structure built into them, yet they may still implicitly learn structured relationships by attending to relevant tokens. We hypothesize that this structural learning could be made more robust by explicitly endowing Transformers with a structural bias, and we investigate two methods for building in such a bias. One method, the TP-Transformer, augments the traditional Transformer architecture to include an additional component to represent structure. The second method imbues structure at the data level by segmenting the data with morphological tokenization. We test these methods on translating from English into morphologically rich languages, Turkish and Inuktitut, and consider both automatic metrics and human evaluations. We find that each of these two approaches allows the network to achieve better performance, but this improvement is dependent on the size of the dataset. In sum, structural encoding methods make Transformers more sample-efficient, enabling them to perform better from smaller amounts of data.
Joachim Tilsted Kristensen, Robin Kaarsgaard, Michael Kirkedal Thomsen
Algorithms are ways of mapping problems to solutions. An algorithm is invertible precisely when this mapping is injective, such that the initial problem can be uniquely inferred from its solution. While invertible algorithms can be described in general-purpose languages, no guarantees are generally made by such languages as regards invertibility, so ensuring invertibility requires additional (and often non-trivial) proof. On the other hand, while reversible programming languages guarantee that their programs are invertible by restricting the permissible operations to those which are locally invertible, writing programs in the reversible style can be cumbersome, and may differ significantly from conventional implementations even when the implemented algorithm is, in fact, invertible. In this paper we introduce Jeopardy, a functional programming language that guarantees program invertibility without imposing local reversibility. In particular, Jeopardy allows the limited use of uninvertible -- and even nondeterministic! -- operations, provided that they are used in a way that can be statically determined to be invertible. To this end, we outline an \emph{implicitly available arguments analysis} and three further approaches that can give a partial static guarantee to the (generally difficult) problem of guaranteeing invertibility.
This paper puts forward a new division of the history of Germanic languages, taking into account the existence of three different historical periods (prehistoric, proto-historic, and literary) in the development from Common Germanic or Proto-Germanic to modern Germanic languages, analogously to the development of Romance or Romanic languages from Vulgar Latin (also called Proto-Romanic or Proto-Romance), in which three stages can be retraced: Vulgar Latin (prehistoric), Romance (proto-historic) and literary (historical). So far, only two stages have been considered in the linguistic history of Germanic languages, namely, the Common Germanic (not documented) and the literary Germanic languages (documented since the Middle Ages). Nevertheless, the history of both families of languages is similar in most aspects, so that the three aforementioned periods can be clearly recognized in both: a period of considerable linguistic unity, although poorly or not at all documented; a period of dissolution of this unity and fragmentation into several dialects not mutually intercomprehensible; and a period of full and intense literary production and official recognition of some of these dialects, now raised to the condition of culture languages. Due to this new historiographical division, the denomination Germance is proposed for the second of the three evolutionary stages of Germanic.
O objetivo deste trabalho é explorar as relações entre o gênero – enquanto espaço dinâmico de estruturação dos textos – e um dos níveis da arquitetura textual – os mecanismos que assinalam os modos de assumir (ou não) a responsabilidade enunciativa e as formas da modalização. Para tal, são observados dois gêneros de texto: as cartas de reclamação e as cartas-respostas institucionais publicadas na imprensa. Assim, partindo de um conjunto de textos publicados em Portugal – e adotando como eixo certos aspectos desenvolvidos no quadro do Interacionismo sócio-discursivo (cf. Bronckart, 1997) – procura-se pôr em relevo a estreita ligação entre os parâmetros genéricos e os mecanismos de construção textual.
Palavras-chave: gêneros de texto, responsabilidade enunciativa, tipos de discurso, cartas, imprensa.
La vie et l’oeuvre de l’auteur français Jean Genet ont toujours été une quête de l’oeuvre d’art absolue. Dans cette quête, trois figures majeures le guideront : le sculpteur Giacometti, le peintre Rembrandt et le funambule Abdellah Bentaga. À travers les oeuvres de ces artistes, Genet découvrira l’identité absolue. Qu’est-ce qui le mena vers cette découverte et quelles conséquences eurent-elles sur l’écrivain ? C’est ce rapport à l’Autre, analysé dans les quatre textes que Genet a écrit sur ces artistes, que nous nous proposons d’interroger dans cet article, notamment à travers le mythe de Narcisse.
Romanic languages, Language. Linguistic theory. Comparative grammar
contained in the linguistic atlases, we will bring back into discussion some aspects regarding the antiquity of the Romance element in the South Slavic languages and its territorial spread.
This paper attempts to connects the evolution of computer languages with the evolution of life, where the later has been dictated by \emph{theory of evolution of species}, and tries to give supportive evidence that the new languages are more robust than the previous, carry-over the mixed features of older languages, such that strong features gets added into them and weak features of older languages gets removed. In addition, an analysis of most prominent programming languages is presented, emphasizing on how the features of existing languages have influenced the development of new programming languages. At the end, it suggests a set of experimental languages, which may rule the world of programming languages in the time of new multi-core architectures. Index terms- Programming languages' evolution, classifications of languages, future languages, scripting-languages.
Armin Moin, Stephan Rössler, Marouane Sayih
et al.
In this paper, we illustrate how to enhance an existing state-of-the-art modeling language and tool for the Internet of Things (IoT), called ThingML, to support machine learning on the modeling level. To this aim, we extend the Domain-Specific Language (DSL) of ThingML, as well as its code generation framework. Our DSL allows one to define things, which are in charge of carrying out data analytics. Further, our code generators can automatically produce the complete implementation in Java and Python. The generated Python code is responsible for data analytics and employs APIs of machine learning libraries, such as Keras, Tensorflow and Scikit Learn. Our prototype is available as open source software on Github.
The article presents the innovative experience of professional training of teachers of Romanic languages (French and Italian) based on linguo-cultural approach. The stages of the development of linguoculturology are considered. A new approach to teaching foreign languages is proposed, which is implemented in modules of a linguo-culturological orientation and allows students to create professional and special competences through the prism of the national culture of Roman countries.
A partir do suporte teórico-metodológico da sociologia do discurso do Círculo de Bakhtin (BAKHTIN, 2016; VOLÓCHINOV, 2017), no que toca especialmente à questão da expressividade, em diálogo com a abordagem glotopolítica (GUESPIN, MARCELLESI, 1986), este texto busca tecer algumas reflexões em torno do objeto de estudo práticas de linguagem em placas de sinalização em espaços físicos escolar. Toma-se por base o contexto de internacionalização em um instituto federal tecnológico, com o intuito de compreender, por meio de uma lente discursivo-dialógica, quais os efeitos glotopolíticos implicados em práticas dessa natureza. Assume-se que essas práticas atuam como uma forma de intervenção política na paisagem linguística escolar (SPOLSKY, 2004), sendo fruto, portanto, de escolhas nada aleatórias, decisões tomadas aprioristicamente que, no caso do material analisado, dá a ver a opção por quais línguas privilegiar nas placas de sinalização nos ambientes dessa instituição, bem como a ordem de prioridade em que elas tendem a se inscrever nas placas em análise.