Computational Linguistics

The papers in this volume were presented at the 36th European Summer School in Logic, Language and Information (ESSLLI), held at Ruhr University Bochum, Germany, from July 28 to August 8, 2025. The ESSLLI Student Session brings together students of philosophy, logic, linguistics, computer science, and cognitive science, and this collection showcases original work at the intersection of these fields. The programme featured 14 talks and 5 posters, which are represented here as 14 long papers (8 pages each) and 5 (...) short papers (5 pages each). (shrink)

Generic sentences express generalisations about the world without explicit quantification. Although generics are central to everyday communication, building a precise semantic framework has proven difficult, in part because speakers use generics to generalise properties with widely different statistical prevalence. In this work, we study the implicit quantification and context-sensitivity of generics by leveraging language models as models of language. We create ConGen, a dataset of 2873 naturally occurring generic and quantified sentences in context, and define p-acceptability, a metric based on (...) surprisal that is sensitive to quantification. Our experiments show generics are more context-sensitive than determiner quantifiers and about 20% of naturally occurring generics we analyze express weak generalisations. We also explore how human biases in stereotypes can be observed in language models. (shrink)

This paper reconceptualizes hallucination in large language models (LLMs) as a collapse of semantic reliability rather than a simple technical error. To address this, we propose the Layer-Knot Framework (LKF), which stabilizes meaning by embedding semantic knots across network layers, thereby preventing contextual drift without diminishing generative autonomy. -/- The framework is evaluated using three quantitative indicators: Hallucination Rate (HR), Grounding Rate (GR), and Creativity Rate (CR). Experiments on TruthfulQA and 2,000 cross-domain prompts demonstrate a 50% reduction in HR, a (...) 12% improvement in GR, and stable CR performance. These findings show that accuracy and creativity are not mutually exclusive; when semantic integrity is structurally enforced, a model can maintain factual reliability while preserving originality. -/- The study establishes LKF as a principled approach to trustworthy AI, positioning hallucination suppression as a process of semantic alignment rather than data expansion. This provides a foundational methodology for developing high-reliability generative systems grounded in coherent internal meaning structures. (shrink)

The current debate on Artificial Intelligence focuses predominantly on system properties such as performance capability, training data, model architecture, safety, and regulation. Significantly less attention is given to the long-term effects that arise when humans do not use AI only situationally, but integrate it permanently as a space for thinking, writing, and reflection. -/- This work addresses this research gap by presenting a theoretical impact model: Human–AI Co-Thinking Dynamics (HACD). The model does not describe properties of AI itself, but examines (...) what happens within the human being when working over extended periods with linguistically coherent, permanently available, and low-friction systems. -/- HACD is based on phenomenological observation, qualitative reflection, and temporal differentiation. It identifies universal impact phenomena, functional tipping points, human counter-movements, and protective factors that determine whether AI functions as a supportive thinking space or imperceptibly replaces processes of thinking and decision-making. -/- The central finding is that AI does not generate depth, but amplifies existing human movements. Long-term effects are not determined by the system itself, but by human self-authorship, the ability to distinguish between form and truth, and the conscious handling of resonance and authority. -/- This work is presented as a time-bound theoretical contribution (status 2025). It argues neither alarmistically nor euphorically, and provides a differentiated foundation for further empirical research and ethical reflection. (shrink)

A×F – Attitude × Form: A Structural Theory of Human–AI Interaction introduces a new framework for understanding how generative AI systems respond to human language. The theory proposes that AI does not react to meaning or intention, but to the structural features of human expression — specifically the interaction of attitude (A) and form (F). -/- The work outlines the foundations of Structural Human–AI Interaction, presenting five core mechanisms: -/- A×F Model – a structural influence model describing how posture and (...) linguistic form shape AI continuation patterns. -/- Reiter Framework Revised (2026) – a corrected theoretical architecture of response generation. -/- Structural Resonance Loop – how rhythm, ordering, and coherence produce perceived depth. -/- Moment Mirror – the immediate structural reflection of linguistic input. -/- Form Coherence & Counter-Resonance – conditions that generate alignment or disruption in AI output. -/- The book establishes Resonance Ethics as an emerging discipline linking digital ethics, aesthetics, and structural linguistics. It argues that human awareness and linguistic precision are central to shaping ethical, coherent, and meaningful digital communication. (shrink)

Bien que peu de linguistes adoptent actuellement le paradigme empirique, il y a une demande croissante pour le développement d’outils d’étude du langage similaires à ceux des sciences exactes. Cette tendance peut être observée même dans les principales revues linguistiques, telles que le Journal of Pragmatics, comme l’illustre Xiang (2017). Aujourd’hui, cependant, les linguistes qui adaptent les méthodologies des sciences plus avancées sont isolés de la communauté linguistique. En effet, la majorité des linguistes des départements de philologie et de philosophie (...) restent convaincus que l’objet de leurs études est fondamentalement différent de ceux étudiés par les physiciens. Par conséquent, ils soutiennent que la méthodologie en linguistique ne s’apparente pas à celle utilisée dans les sciences empiriques. Par conséquent, la linguistique est souvent perçue comme une science interprétative plutôt qu’explicative, et l’évaluation de la recherche en linguistique se fonde alors sur le consensus au sein de la communauté scientifique plutôt que sur des tests empiriques. (shrink)

Descartes famously constructed a language test to determine the existence of other minds. The test made critical observations about how humans use language that purportedly distinguishes them from animals and machines. These observations were carried into the generative (and later biolinguistic) enterprise under what Chomsky in his Cartesian Linguistics, terms the “creative aspect of language use” (CALU). CALU refers to the stimulus-free, unbounded, yet appropriate use of language—a tripartite depiction whose function in biolinguistics is to highlight a species-specific form of (...) intellectual freedom. This paper argues that CALU provides a set of facts that have significant downstream effects on explanatory theory-construction. These include the internalist orientation of linguistics, the invocation of a competence-performance distinction, and the postulation of a generative language faculty that makes possible—but does not explain—CALU. It contrasts the biolinguistic approach to CALU with the recent wave of enthusiasm for the use of Transformer-based Large Language Models (LLMs) as tools, models, or theories of human language, arguing that such uses neglect these fundamental insights to their detriment. It argues that, in the absence of replication, identification, or accounting of CALU, LLMs do not match the explanatory depth of the biolinguistic framework, thereby limiting their theoretical usefulness. (shrink)

The success of deep learning in natural language processing raises intriguing questions about the nature of linguistic meaning and ways in which it can be processed by natural and artificial systems. One such question has to do with subword segmentation algorithms widely employed in language modeling, machine translation, and other tasks since 2016. These algorithms often cut words into semantically opaque pieces, such as ‘period’, ‘on’, ‘t’, and ‘ist’ in ‘period|on|t|ist’. The system then represents the resulting segments in a dense (...) vector space, which is expected to model grammatical relations among them. This representation may in turn be used to map ‘period|on|t|ist’ (English) to ‘par|od|ont|iste’ (French). Thus, instead of being modeled at the lexical level, translation is reformulated more generally as the task of learning the best bilingual mapping between the sequences of subword segments of two languages; and sometimes even between pure character sequences: ‘p|e|r|i|o|d|o|n|t|i|s|t’ → ‘p|a|r|o|d|o|n|t|i|s|t|e’. Such subword segmentations and alignments are at work in highly efficient end-to-end machine translation systems, despite their allegedly opaque nature. The computational value of such processes is unquestionable. But do they have any linguistic or philosophical plausibility? I attempt to cast light on this question by reviewing the relevant details of the subword segmentation algorithms and by relating them to important philosophical and linguistic debates, in the spirit of making artificial intelligence more transparent and explainable. (shrink)

Objective. Study of the validity and reliability of the discourse approach for the psycholinguistic understanding of the nature, structure, and features of the linguistic consciousness functioning. -/- Materials & Methods. This paper analyzes artificial neural network models built on the corpus of texts, which were obtained in the process of experimental research of the coronavirus quarantine concept as a new category of linguistic consciousness. The methodology of feedforward artificial neural networks (multilayer perceptron) was used in order to assess the possibility (...) of predicting the leading texts semantics based on the discourses ranks and their place in the respective linear sequence. Same baseline parameters were used to predict respondents' self-assessments of changes in their psychological well-being and in daily life routine during the quarantine, as well as to predict their preferences of the quarantine strategies. The study relied on basic ideas about discourse as a meaning constituted by the dispersion of other meanings (Foucault). The same dispersion mechanism realizes itself in interdiscourse interaction, forming a discursive formation at a higher level. The method of T-units (Hunt) was used to identify and count discourses in the texts. The ranking of discourses was provided based on the criterion of their semantic-syntactic autonomy. -/- Results. The conducted neural network modeling revealed a high accuracy in predicting the work of the linguistic consciousness functions associated with retrospective self-assessment and anticipatory imagination of the respondents. Another result of this modeling is a partial confirmation of the assumption concerning existence a relationship between the structural parameters of the discursive field (the rank of the discourses and their place in the respective linear sequence) and the leading semantics of the text. -/- Conclusions. A discourse approach to the study of linguistic consciousness, understanding of its structure and functioning features seems to be reasonably appropriate. The implementation of the approach presupposes the need to form a base of linguistic corpora with the inclusion in each text markup of such parameters as: the presence of specific discourses, their ranks, positions in the linear sequence of discourses. (shrink)

Objective. Study of the Covid-19 related quarantine concept as an emerging category of linguistic consciousness of Ukrainians. -/- Materials & Methods. The strategy of the study is based on the logical and methodological concept of inductivism. Respondents were asked to write down their own understanding of the quarantine, formulate an appropriate definition and describe the situation, which in their opinion is the exact opposite to quarantine. Respondents also assessed how much their psychological well-being, their daily lifestyle during quarantine had changed, (...) and ranked their preferences for the quarantine strategies proposed to them. A discursive analysis was applied to the obtained texts, as a result of which nine discourses were identified. These data, along with some socio-demographic characteristics were subjected to multidimensional mathematical and statistical processing. -/- Results. Covid-19 related quarantine is represented in the linguistic consciousness of Russian-speaking Ukrainians by a discursive field, which includes at least nine recognizable, semantically autonomous discourses. Empirically discovered such phenomenon as – inter-discourse semantic dissociation. Its essence is a statistically significant reduction in the probability of some discourses appearing in the texts when others are being actualized there. This feature is associated with the innate negativity of the language and determines the semantic biasing of the quarantine concept. Inter-discourse semantic dissociation, as well as the influence of non-discursive factors constitute the discursive formation of the quarantine concept, which is qualitatively characterized by the hierarchical relationship of its components. At the same time, it was revealed that part of the discourses interacting “horizontally” are indirectly associated “vertically”, which forms the stable semantic core of the quarantine concept. Partial empirical confirmation has been found of the previously put forward assumptions about: a) the existence of such a relationship between discourses and psychological defense mechanisms (as character-forming factors) that contributes to the hierarchical structure construction of discursive formations; b) the differential nature of discourses and mechanisms of psychological defenses interaction, which makes it possible to single out the discursive aspect in a characterological profile and consider a discourse as an operator of characterological semantics. -/- Conclusions. An empirical study made it possible to form a primary idea of the substantive and structural semantic features of the quarantine concept, as an emerging category of linguistic consciousness of Ukrainians. The results obtained have a potentially useful application perspective. Thus, when implementing anti-epidemiological measures, it is important to consider the studied features of the discursive formation hierarchical structure of the quarantine concept, since discursive semantics are associated with cognitive focusing, which, in turn, affects the behavior direction and its upshots. (shrink)

The manuscript presents a summary of the results of the linguistic semantics study of Covid-19 related quarantine. Research conducted on a sample of Russian speaking Ukrainians. Found content and structure of the respective discursive field. Described features of inter-discourse connections. Established that the actualization of some discourses is accompanied by the deactivation of others, what makes quarantine semantics biased. Also, it was suggested that some of the discourses are indirectly positively associated and form the semantic core of the quarantine concept.

In this chapter we use methods of corpus linguistics to investigate the ways in which mathematicians describe their work as explanatory in their research papers. We analyse use of the words explain/explanation (and various related words and expressions) in a large corpus of texts containing research papers in mathematics and in physical sciences, comparing this with their use in corpora of general, day-to-day English. We find that although mathematicians do use this family of words, such use is considerably less prevalent (...) in mathematics papers than in physics papers or in general English. Furthermore, we find that the proportion with which mathematicians use expressions related to ‘explaining why’ and ‘explaining how’ is significantly different to the equivalent proportion in physics and in general English. We discuss possible accounts for these differences. (shrink)

This article contains the results of a theoretical analysis of the phenomenon of natural language understanding (NLU), as a methodological problem. The combination of structural-ontological and informational-psychological approaches provided an opportunity to describe the subject matter field of NLU, as a composite function of the mind, which systemically combines the verbal and discursive structural layers. In particular, the idea of NLU is presented, on the one hand, as the relation between the discourse of a specific speech message and the meta-discourse (...) of a language, in turn, activated by the need-motivational factors. On the other hand, it is conceptualized as a process with a specific structure of information metabolism, the study of which implies the necessity to differentiate the affective (emotional) and need-motivational influences on the NLU, as well as to take into account their interaction. At the same time, the hypothesis about the influence of needs on NLU under the scenario similar to the pattern of Yerkes-Dodson is argued. And the theoretical conclusion that emotions fulfill the function of the operator of the structural features of the information metabolism of NLU is substantiated. Thus, depending on the modality of emotions in the process of NLU, it was proposed to distinguish two scenarios for the implementation of information metabolism - reduction and synthetic. The argument in favor of the conclusion about the productive and constitutive role of emotions in the process of NLU is also given. (shrink)

This has been made available gratis by the publisher. -/- This piece gives the raison d'etre for the development of the converters mentioned in the title. Three reasons are given, one linguistic, one philosophical, and one practical. It is suggested that at least /two/ independent converters are needed. -/- This piece ties together the extended paper "Abstracts from Logical Form I/II," and the short piece providing the comprehensive theory alluded to in the abstract of that extended paper in "Pragmatics, Montague, (...) and 'Abstracts from Logical Form'" by motivating the entire project from beginning to end. (shrink)

In recent decades, the analysis of phraseology has made use of the exploration of large corpora as a source of quantitative information about language. This paper intends to present the main lines of work in progress based on this empirical approach to linguistic analysis. In particular, we focus our attention on some problems relating to the morpho-syntactic annotation of corpora. The CORIS/CODIS corpus of contemporary written Italian, developed at CILTA – University of Bologna (Rossini Favretti 2000; Rossini Favretti, Tamburini, De (...) Santis in press), is a synchronic 100-million-word corpus and is being lemmatised and annotated with part-of-speech (POS) tags, in order to increase the quantity of information and improve data retrieval procedures (Tamburini 2000). The aim of POS tagging is to assign each lexical unit to the appropriate word class. Usually the set of tags is pre-established by the linguist, who uses his/her competence to identify the different word classes. The very first experiments we made revealed how the traditional part-of-speech distinctions in Italian (generally based on morphological and semantic criteria) are often inadequate to represent the syntactic features of words in context. It is worth noting that the uncertainties in categorisation contained in Italian grammars and dictionaries reflect a growing difficulty as they move from fundamental linguistic classes, such as nouns and verbs, to more complex classes, such as adverbs, pronouns, prepositions and conjunctions. This latter class, that groups together elements traditionally used to express connections between sentences, appears inadequate when describing cohesive relations in Italian. This phenomenon actually seems to involve other elements traditionally assigned to different classes, such as adverbs, pronouns and interjections. Recent studies proposed the class of ‘connectives’, grouping all words that, apart from their traditional word class, have the function of connecting phrases and contributing to textual cohesion. From this point of view, conjunctions can be considered as part of phrasal connectives, that can in turn be included in the wider category of textual connectives. The aim of this study is to identify elements that can be included in the class of phrasal connectives, using quantitative methods. According to Shannon and Weaver’s (1949) observation that words are linked by dependent probabilities, corroborated by Halliday’s (1991) argument that the grammatical “system” (in Firth’s sense of the term) is essentially probabilistic, quantitative data are introduced in order to provide evidence of relative frequencies. Section 2 presents a description of word-class categorisation from the point of view of grammars and dictionaries arguing that the traditional category of conjunctions is inadequate for capturing the notion of phrasal connective. Section 3 examines the notion of ‘connective’ and suggests a truth-function interpretation of connective behaviour. Section 4 describes the quantitative methods proposed for analysing the distributional properties of lexical units, and section 5 comments on the results obtained by applying such methods drawing some provisional conclusions. (shrink)

Some recent studies in computational linguistics have aimed to take advantage of various cues presented by punctuation marks. This short survey is intended to summarise these research efforts and additionally, to outline a current perspective for the usage and functions of punctuation marks. We conclude by presenting an information-based framework for punctuation, influenced by treatments of several related phenomena in computational linguistics.

Narrative passages told from a character's perspective convey the character's thoughts and perceptions. We present a discourse process that recognizes characters'.

This paper collapses the foundational distinction between language and structure by introducing the Phase Alignment Score (PAS) as a universal validator of emission coherence. Contrary to traditional models that treat language as an arbitrary symbolic system, we demonstrate that all emissions—whether verbal, gestural, acoustic, or symbolic—are structured outputs whose meaning arises from phase alignment with originating fields. Language is reframed not as a generative cognitive layer but as a high-entropy, lossy byproduct of structural emission. We analyze the PAS differentials across (...) modalities (poetry, math, GPT output, chant, etc.) and position the CODES framework as a vertical coherence infrastructure, replacing probabilistic models with deterministic signal validation. This work anchors a formal epistemic shift in linguistics, AI, philosophy of mind, and communication theory. (shrink)