Search Results (102)

This study investigated the dynamic resolution of lexical–semantic ambiguity during sentence comprehension, focusing on how uncertainty evolves as contextual information accumulates. Using time-resolved eye-tracking and a novel entropy-based measure derived from group-level semantic choice distributions, we quantified semantic uncertainty at a fine-grained temporal resolution for ambiguous words. By parametrically manipulating the semantic bias strength of the sentence context, we examined how context guides disambiguation over time. The results showed that semantic uncertainty declined gradually over temporal segments and dropped sharply following the onset of ambiguous words, reflecting both incremental integration and syntactic anchoring. A stronger contextual bias led to faster reductions in uncertainty, with effects following a near-linear trend. These findings support dynamic semantic processing models that assume continuous, context-sensitive convergence toward intended meanings. In contrast, a pretrained Chinese BERT model (RoBERTa-wwm-ext) showed similar overall trends in uncertainty reduction but lacked sensitivity to contextual bias. This discrepancy suggests that, while language models can approximate human-level disambiguation broadly, they fail to capture fine-grained semantic modulation driven by context. These findings provide a novel empirical characterization of disambiguation dynamics and offer a new methodological approach to capturing real-time semantic uncertainty. The observed divergence between human and model performance may inform future improvements to language models and contributes to our understanding of possible architectural differences between human and artificial semantic systems. Full article

To address issues commonly observed during the inference phase of large language models—such as inconsistent labels, formatting errors, or semantic deviations—a series of targeted strategies has been proposed. First, a relation label refinement strategy based on semantic similarity and syntactic structure has been designed to calibrate the model’s outputs, thereby improving the accuracy and consistency of label prediction. Second, to meet the contextual modeling needs of different types of instance bags, a multi-level contextual augmentation strategy has been constructed. For multi-sentence instance bags, a graph-based retrieval enhancement mechanism is introduced, which integrates intra-bag entity co-occurrence networks with document-level sentence association graphs to strengthen the model’s understanding of cross-sentence semantic relations. For single-sentence instance bags, a semantic expansion strategy based on term frequency-inverse document frequency is employed to retrieve similar sentences. This enriches the training context under the premise of semantic consistency, alleviating the problem of insufficient contextual information. Notably, the proposed multi-granularity framework captures semantic symmetry between entities and relations across different levels of context, which is crucial for accurate and balanced relation understanding. The proposed methodology offers practical advancements for semantic analysis applications, particularly in knowledge graph development. Full article

This study is the first to scrutinize the rates of, and the lexical diversity in, adjective intensification in second language (L2) German. We additionally attend to the issue concerning whether sociodemographic variables (i.e., length of residence, age, and gender) and individual learner differences (i.e., L2 proficiency, intensity of exposure to the L2, and L2 socioaffect) can predict (a) the inter-individual variation in syntactic adjective intensification, and (b) the observed intra-individual variation based on a weighted measure of intensifier lexical diversity. We analyzed spoken data collected via virtual reality (VR) elicitation tasks from 40 learners of L2 German (first language [L1] English). We found that learners engaged in adjective intensification at similar rates as those reported in the literature, despite some cases of overshooting the target; learners also preferred markers of intensification consistent with the lexical choices of L1 German speakers. Sociodemographic variables did not predict different rates of adjective intensification; rather, individual learner differences such as those relating to L2 proficiency and L2 exposure correlated with more target-like use of intensifiers, though the correlations were weak. The diversity in adjective intensification was also only marginally related to demographic factors and individual learner differences. Our findings suggest that L2 learners indeed engage in similar intensification practices as do L1 speakers; however, systematically predicting more ‘successful’ adoption of target-like sociopragmatic norms among L2 learners remains challenging. Full article

Conventionalized or symbolic “emblematic” visual expressions are the types of “gesture” that most closely resemble lexical and grammatical elements seen in spoken languages or in sign languages in the visual modality. The relationship between conventionalization in the visual modality and in morphosyntax is a topic that remains only partially explored, with more research focused on iconic and indexical aspects of visual expression than on symbolic aspects. However, the culture-specific nature of symbolic gestures makes them an important phenomenon for the study of cultural variation at the intersection of modality and linguistic diversity. This study examines the relationship of a specific area of morphosyntax, negation and syntactic polarity, to an element of the visual modality, a practice of visual existential negation used by speakers of Imbabura Kichwa, a variety of Ecuadorian Highland Kichwa, a Quechuan language spoken in the Ecuadorian Andes. A data set of natural speech recordings will illustrate this open-handed rotating gesture that expresses negative existence: “there is none”. This gesture will be analyzed in terms of its form, meaning, and combination with spoken elements in discourse context, finding that in this variety of Kichwa, this practice is associated with a specific verb root meaning “to lack” or “to not exist”. This discussion will be framed in the wider context of the areal distribution of similar types of visual existential negation in other languages of Ecuador, reflecting the diversity of multimodal conventionalization across speech communities. Full article

Despite the growing number of bilinguals worldwide, research on how bilingualism influences grammatical development in children with learning disabilities remains limited. This may be due to challenges in assessing language in these children, given the heterogeneity of their disabilities, lack of appropriate tools, and variability in language background and exposure common in bilingual populations. This pilot study investigates grammatical abilities in bilingual versus monolingual children with Down syndrome using the LITMUS Sentence Repetition Task, specifically designed for bilingual populations. Sentence repetition tasks are widely used for assessing grammar in neurotypical children and children with language impairments and are part of many omnibus language assessments. Ten children with Down syndrome aged 5–8 were recruited: five bilingual, speakers of British English and various home languages, and five monolingual, age- and language-matched. Both groups produced a high proportion of ungrammatical repetitions, with more omissions of verbs than nouns, function words than content words, and significant difficulties producing complex structures such as relative clauses, wh-questions, and passives. However, qualitative analyses showed that bilingual children speaking morphologically rich home languages (e.g., Polish, Greek) appeared to have fewer difficulties with some function words (e.g., prepositions) and were able to produce complex structures like passives and wh-questions, unlike their monolingual peers. Although the small sample limits generalisability, two insights emerge: First, sentence repetition may be of limited use in assessing expressive grammar in children with Down syndrome due to frequent ungrammatical responses. Second, while both groups showed similar challenges, bilingualism—especially with richly inflected home languages—may support specific grammatical skills. These findings support existing evidence that bilingualism does not hinder grammatical development in children with Down syndrome and suggest that parents should not avoid dual-language input. Further research is needed to determine whether bilingualism confers specific benefits in grammatical morpheme use and complex syntactic constructions. Full article

Background/Objectives: Verbs are considered to be more abstract than nouns, as they represent actions, states, and events, which are less tangible, more flexible in their meaning and thus less univocally specified. It has been suggested that children acquire abstract concepts based on their linguistic contexts of use, making use of semantic and syntactic cues. By contrast, according to theories of embodied cognition, conceptual knowledge is based on physical and perceptual interaction with the world. The present study investigates whether the verbal and the visual modality produce similar or different results in the processes of construction and reactivation of novel verbs, corresponding to new compositional abstract concepts, in children of different ages. In Experiment 1, the acquisition of the concept was determined based on the quality of verbal explanation; in Experiment 2, participants were asked to decide whether a visual representation fitted the concept or not. Thus, response modality could be either explicit or implicit, and either congruent or incongruent with respect to learning modality. Methods: In Experiment 1, 100 children from grade 1 to 5 were asked to explain the meaning of verbs introduced via verbal or visual instances. In Experiment 2, 15 children aged 8 to 10 had to judge pictures as (not) being examples of previously verbally or visually presented novel verbs. Results: The results of Experiment 1 show more accurate explanations after verbal presentation across all grades. In Experiment 2, verbal presentation was no longer associated with more accurate matching responses, but rather with slower decision times. Conclusions: Modality congruence, explicitness and linguistic (semantic and syntactic) factors were all shown to play a role, which is discussed in a developmental perspective. Full article

In this article, we tested some specific claims made in the literature on relative distances among European languages and among Chinese dialects, suggesting that some language varieties within the Sinitic family traditionally called dialects are, in fact, more linguistically distant from one another than some European varieties that are traditionally called languages. More generally, we examined whether distances among varieties within and across European language families were larger than those within and across Sinitic language varieties. To this end, we computed lexico-phonetic as well as syntactic distance measures for comparable language materials in six Germanic, five Romance and six Slavic languages, as well as for six Mandarin and nine non-Mandarin (‘southern’) Chinese varieties. Lexico-phonetic distances were expressed as the length-normalized MPI-weighted Levenshtein distances computed on the 100 most frequently used nouns in the 32 language varieties. Syntactic distance was implemented as the (complement of) the Pearson correlation coefficient found for the PoS trigram frequencies established for a parallel corpus of the same four texts translated into each of the 32 languages. The lexico-phonetic distances proved to be relatively large and of approximately equal magnitude in the Germanic, Slavic and non-Mandarin Chinese language varieties. However, the lexico-phonetic distances among the Romance and Mandarin languages were considerably smaller, but of similar magnitude. Cantonese (Guangzhou dialect) was lexico-phonetically as distant from Standard Mandarin (Beijing dialect) as European language pairs such as Portuguese–Italian, Portuguese–Romanian and Dutch–German. Syntactically, however, the differences among the Sinitic varieties were about ten times smaller than the differences among the European languages, both within and across the families—which provides some justification for the Chinese tradition of calling the Sinitic varieties dialects of the same language. Full article

This article aims to increase our understanding of the syntax of manner modification by examining it from the perspective of the syntax of anaphoric dependencies. It is proposed that the two grammatical dependencies share certain abstract formal properties and are governed by the same type of principle governing the computational system of human language. Building on the so-called IDI constraint (Inability to Distinguish Indistinguishables), it is proposed that the Computational system of Human Language (C_HL) is unable to distinguish two predicates—for example, a verbal predicate and an adjectival one—if they are in a local domain. Specifically, an adjectival predicate (e.g., quick) cannot merge directly with a verbal predicate (e.g., walk). The C_HL can only deal with two predicates if their linguistic environment allows them to be distinguished as different occurrences. This formal distinctness can be achieved by means of various licensing strategies, including so-called protection, which is a formal strategy that turns the modifier (e.g., quick) into a more complex syntactic object (e.g., quick+-ly). It is shown that the various morpho-syntactic implementations of the protection strategy are quite similar for Rreflexivization and for Manner Modification: (grammaticalized) body nouns, doubling pronouns, and adpositional material can be used for making the dependent element (i.e., the anaphor; the manner modifier) more complex. It is further proposed that superficially bare manner modifiers (e.g., fast) are actually complex syntactic objects, where the complexity comes from the (hidden) presence of a silent element. Full article

This study investigates the cross-linguistic priming effect in the syntactic written output of late bilingual Levantine Arabic speakers who learn English as a second language. In particular, we examined priming sentence type (simple vs. complex sentences) and priming language condition (Levantine Arabic vs. English). Forty-nine bilinguals (Mean age = 33.3, SD = 8.5), who learned Levantine Arabic as their L1 and English as their L2, were primed with a short paragraph presented on the computer screen in either English or Levantine Arabic and asked to produce a written response in the counterpart language. Logistic regression analysis revealed a significant cross-linguistic priming effect, suggesting that the syntactic structure of the prime in the participants’ first language (Levantine Arabic) predicts the participants’ written output in the second language (English), and the reverse is also true. However, there was no significant effect of priming sentence type (simple vs. complex) on the likelihood of producing primed res ponses, indicating that both priming conditions yielded similar levels of priming. In contrast, there was a significant effect of the priming language condition, with participants significantly more likely to produce syntactically primed responses when the priming language was Arabic compared to English. In addition, there was a significant interaction between the priming language condition and priming sentence type: Arabic priming led to more simple sentence production in English, whereas English priming did not significantly affect sentence complexity in Arabic. These findings align with the shared syntax account but highlight the need to consider factors such as language dominance in bilingual syntactic processing. Full article

The cross-lingual text classification task remains a long-standing challenge that aims to train a classifier on high-resource source languages and apply it to classify texts in low-resource target languages, bridging linguistic gaps while maintaining accuracy. Most existing methods achieve exceptional performance by relying on multilingual pretrained language models to transfer knowledge across languages. However, little attention has been paid to factors beyond semantic similarity, which leads to the degradation of classification performance in the target languages. This study proposes a novel framework, a heterogeneous graph neural network with multi-view contrastive learning for cross-lingual text classification, which integrates a heterogeneous graph architecture with multi-view contrastive learning for the cross-lingual text classification task. This study constructs a heterogeneous graph to capture both syntactic and semantic knowledge by connecting document and word nodes using different types of edges, including Part-of-Speech tagging, dependency, similarity, and translation edges. A Graph Attention Network is applied to aggregate information from neighboring nodes. Furthermore, this study devises a multi-view contrastive learning strategy to enhance model performance by pulling positive examples closer together and pushing negative examples further apart. Extensive experiments show that the framework outperforms the previous state-of-the-art model, achieving improvements of 2.20% in accuracy and 1.96% in F1-score on the XGLUE and Amazon Review datasets, respectively. These findings demonstrate that the proposed model makes a positive impact on the cross-lingual text classification task overall. Full article

Password guessing is a crucial research direction in password security, considering vulnerabilities like password reuse and data breaches. While research has extensively explored intra-site password guessing, the complexities of cross-site attacks, where attackers use leaked data from one site to target another, remain less understood. This study investigates the impact of dataset feature similarity on cross-site password guessing performance, revealing that dataset differences significantly influence guessing success more than model variations. By analyzing eight password datasets and four guessing methods, we identified eight key features affecting guessing success, including general data features like length distribution and specific semantic features like PCFG grammar. Our research reveals that syntactic and statistical patterns in passwords, particularly PCFG features, are most effective for cross-site password guessing due to their strong generalization across datasets. The Spearman correlation coefficient of 0.754 between PCFG feature similarity and guessing success rate indicates a significant positive correlation, unlike the minimal impact of length distribution features (0.284). These findings highlight the importance of focusing on robust semantic features like PCFG for improving password guessing techniques and security strategies. Additionally, the study underscores the importance of dataset selection for attackers and suggests that defenders can enhance security by mitigating feature similarity with commonly leaked data. Full article

This paper investigates how verbal affixes that encode manner information (manner affixes) interact with verbs of different lexical aspect classes and transitivity values in West Greenlandic (Inuit–Yupik–Unangan: Greenland). Manner affixes remain an understudied and poorly understood grammatical category. The data presented and discussed here is primarily based on original fieldwork conducted in Copenhagen (Denmark) and Nuuk (Greenland). The findings show that manner affixes are interspersed among syntactic projections encoding event and argument structure, with a high degree of flexibility in terms of linear and hierarchical ordering, which correlate with differences in scope interpretation. However, this flexibility is limited by the productivity of the affixes involved, and manner affixes cannot intervene between the syntactic projections that encode the event core (the big VP in traditional generative terminology). Furthermore, manner affixes interact with verbs of different lexical aspect classes in ways similar to manner adverbs, highlighting the similarities between the two categories and the similarities between morphological structures (manner affixes) and syntactic structures (manner adverbs). Full article

As Large Language Models (LLMs) continue to advance, their capabilities in code clone detection have garnered significant attention. While much research has assessed LLM performance on human-generated code, the proliferation of LLM-generated code raises critical questions about their ability to detect clones across both human- and LLM-created codebases, as this capability remains largely unexplored. This paper addresses this gap by evaluating two versions of LLaMA3 on these distinct types of datasets. Additionally, we perform a deeper analysis beyond simple prompting, examining the nuanced relationship between code cloning and code similarity that LLMs infer. We further explore how fine-tuning impacts LLM performance in clone detection, offering new insights into the interplay between code clones and similarity in human versus AI-generated code. Our findings reveal that LLaMA models excel in detecting syntactic clones but face challenges with semantic clones. Notably, the models perform better on LLM-generated datasets for semantic clones, suggesting a potential bias. The fine-tuning technique enhances the ability of LLMs to comprehend code semantics, improving their performance in both code clone detection and code similarity assessment. Our results offer valuable insights into the effectiveness and characteristics of LLMs in clone detection and code similarity assessment, providing a foundation for future applications and guiding further research in this area. Full article

Background/Objectives: Developmental language disorders (DLD) are often associated with co-occurring neurodevelopmental difficulties, including attentional or social–emotional problems. Another nonverbal domain, i.e., visual cognition and its relationship to DLD, is virtually unexplored. However, learning visuospatial regularities—a scene-grammar—is crucial for navigating our daily environment. These regularities show certain similarities to the structure of language and there is preliminary evidence for a relationship between scene processing and language competence in preschoolers with and without DLD. This study compared implicit and explicit visuospatial knowledge of everyday indoor scenes in older children, aged 6 to 10 years, of both groups. Methods: We measured ‘dwell times’ on semantic and syntactic object—scene inconsistencies via eye-tracking and performance in an object-placement task, and their associations with children’s language, visual, and cognitive skills. Results: Visual attention towards object-scene inconsistencies was highly comparable between groups, but children with DLD scored lower in a visual perception test and higher language skills were associated with higher visuo-cognitive performance in both tasks. In the explicit scene-grammar measurement, this relationship only existed for children with DLD and disappeared when nonverbal cognitive performance was controlled. Conclusions: Our study suggests the existence of mild problems in visuospatial processing co-occurring with DLD, which is partly influenced by age and nonverbal cognitive ability. The acquisition of visual cognition and linguistic knowledge is an interactive, multimodal process where the perception of objects in scenes might affect how the words for these objects are learned and vice versa. A better understanding of this interplay could eventually have impact on the diagnosis and treatment of DLD. Full article

Background/Objectives: Narration is a sensitive tool for the assessment of language in children with high-functioning autism spectrum disorder (HF-ASD) since mild language deficits beyond the sentential level are not always noticeable through the administration of standardized language tests targeting the lexical or sentential level. This study investigated the narrative ability of monolingual Greek-speaking HF-ASD children in comparison to that of their typically developing (TD) peers and explored the associations between narrative variables, ADHD symptomatology, and memory skills in the participants on the autistic spectrum. Methods: The participants were 39 children aged 7 to 12 years, 19 with HF-ASD and 20 age-matched, vocabulary-matched, and cognitively matched TD peers. Results: The two groups were similar in most microstructural and macrostructural variables but differed significantly in syntactic complexity (p = 0.024; d = 0.754) and subordination (p < 0.001; d = −1.576) indices, implying that the HF-ASD group presented syntactic delay in comparison to their TD peers. The HF-ASD participants showed significantly higher heterogeneity in the amount of information generated for the story’s main character (p = 0.004; d = −0.093) in comparison to their TD peers. Significant associations were observed between verbal and visual memory, complex syntactic structures, and Theory of Mind-related internal state terms. ADHD symptomatology was negatively correlated with the generation of simple and coordinated clauses. Finally, complex syntax and delayed vSTM were correlated with retelling total scores, indicating that language ability and verbal memory compensate for narrative competence in HF-ASD children. Conclusions: The findings highlight the impact that language skills, memory ability, and ADHD symptomatology have on narrative competence in children with HF-ASD, as well as the importance of narrative use for assessing the language skills in populations with mild language impairment. Full article