Search Results (22)

This paper evaluates multi-agent coordination strategies against single-agent retrieval-augmented generation (RAG) for open-source language models. Four coordination strategies (collaborative, sequential, competitive, hierarchical) were tested across Mistral 7B, Llama 3.1 8B, and Granite 3.2 8B using 100 domain-specific question–answer pairs (3100 total evaluations). Performance was assessed using Composite Performance Score (CPS) and Threshold-aware CPS (T-CPS), aggregating nine metrics spanning lexical, semantic, and linguistic dimensions. Under the tested conditions, all 28 multi-agent configurations showed degradation relative to single-agent baselines, ranging from −4.4% to −35.3%. Coordination overhead was identified as a primary contributing factor. Llama 3.1 8B tolerated Sequential and Hierarchical coordination with minimal degradation (−4.9% to −5.3%). Mistral 7B with shared context retrieval achieved comparable results. Granite 3.2 8B showed degradation of 14–35% across all strategies. Collaborative coordination exhibited the largest degradation across all models. Study limitations include evaluation on a single domain (agriculture), use of 7–8B parameter models, and homogeneous agent architectures. These findings suggest that single-agent RAG may be preferable for factual question-answering tasks in local deployment scenarios with computational constraints. Future research should explore larger models, heterogeneous agent teams, role-specific prompting, and advanced consensus mechanisms. Full article

Writers with decoding and/or spelling difficulties often produce short, lower-quality texts and experience less fluent writing, frequently interrupted by long pauses at the word level. Research suggests that from adolescence onward, such writers become increasingly aware of their difficulties, which influences behaviours such as avoiding difficult-to-spell words and pausing for lexical decisions. The objective of this study was to deepen the understanding of how adolescent students with decoding and spelling difficulties engage in the task of text composition. In this multiple case study, we qualitatively investigated argumentative texts and writing processes produced by three Swedish upper-secondary students with such difficulties. Data were collected through keystroke logging and analyses of texts and keystroke logs provided detailed insights into their individual writing approaches. The results generally align with previous findings but reveal notable differences depending on the severity of the difficulties. Two students with moderate challenges paused extensively to consider spelling, formulation, and word choice, while one student with more pronounced difficulties wrote rapidly and briefly to complete the task quickly. This nuanced analysis highlights the diversity of writing profiles among students with decoding and spelling difficulties and underscores the need for tailored support to help them produce higher-quality texts. Full article

This paper is concerned with the question of what adverbs in English are as a category. It argues that English adverbs are not positional variants of a single category together with adjectives but also do not constitute a separate lexical category on their own, as is commonly assumed. Instead, this paper advocates the position that adverbs can and should be assimilated with PPs and offers a comprehensive presentation of this view. In particular, it provides evidence that the morpheme -ly is not a suffix but a nominal root, which forms the basis of the analysis of adverbs as PPs. Furthermore, it shows that the PP analysis of adverbs is able to account for a variety of facts, including those that have been previously used as arguments for alternative analyses. Finally, this paper demonstrates that the PP analysis allows for a straightforward compositional semantics, using manner and degree adverbs as case studies, and provides an outlook into the cross-linguistic situation in the domain of adverbs from the perspective of their morphological structure. Full article

One aspect of clausal embedding that has not received any specific attention in the literature is the question of whether and how derivational morphology may affect clausal selection properties of the respective bases. In this paper, I will focus on the role of German preverbs for clausal embedding. I will show that any parameter of clausal embedding can be affected by a preverb, though sometimes in a non-compositional way. Preverbs may affect presuppositions and entailments of their base verb, their selectional behavior with respect to clause types, their status as control or raising predicate and their potential for restructuring. Furthermore, preverbs may license or block neg-raising. The first part of the paper is dedicated to the demonstration of these effects with no specific preverb in mind. The second part discusses three specific preverb patterns with zu- ‘to’, ein- ‘in’ and er-, showing their specific clausal complementation properties. Preverbs influence clausal complementation by their impact on the argument structure/realization (in the case of control and restructuring) and on the lexical aspect of the base (in the case of certain interrogative complements and neg-raising). Full article

Upper Kuskokwim (Athabaskan, Alaska) is a polysynthetic language with morphologically complex verbs involving pronominal affixes denoting clause arguments. One goal of this paper is to see how clauses in this kind of language are organized and operate in conversational discourse. This study is based on a dataset of transcribed conversations, arranged as sequences of elementary discourse units. The issues explored in this article include the structure of clauses, their functioning in discourse, the composition and expression of clause arguments and other participants, as well as an assessment of more and less typical clauses. I find that clauses are strongly aligned with elementary discourse units; that there is a preference for verb-centered, independent, and one-place clauses; and that lexically expressed arguments are rare. Overall, the clause is a viable notion for the description of Upper Kuskokwim conversational discourse. The specifics of clause structure and clause functioning in Upper Kuskokwim can be explained by a combination of general principles of discourse production and the typological features of the language. Full article

The search for environmental data typically involves lexical approaches, where query terms are matched with metadata records based on measures of term frequency. In contrast, dense retrieval approaches employ language models to comprehend the context and meaning of a query and provide relevant search results. However, for environmental data, this has not been researched and there are no corpora or evaluation datasets to fine-tune the models. This study demonstrates the adaptation of dense retrievers to the domain of climate-related scientific geodata. Four corpora containing text passages from various sources were used to train different dense retrievers. The domain-adapted dense retrievers are integrated into the search architecture of a standard metadata catalogue. To improve the search results further, we propose a spatial re-ranking stage after the initial retrieval phase to refine the results. The evaluation demonstrates superior performance compared to the baseline model commonly used in metadata catalogues (BM25). No clear trends in performance were discovered when comparing the results of the dense retrievers. Therefore, further investigation aspects are identified to finally enable a recommendation of the most suitable corpus composition. Full article

The purpose of this study was to investigate the effects of scaffolded English writing instruction using mind mapping tools on English narrative writing proficiency among Chinese middle-school EFL students. Specifically, we examined its effects on four subcomponents of narrative writing compositions: lexical complexity, grammatical complexity, accuracy, and fluency. Non-equivalent group pre-test–post-test design was employed in this study. The participants were 55 eighth-grade students in an English class. The data were collected through two writing tests administered before and after a two-month intervention. The results showed that students’ writing demonstrated significant improvements in lexical complexity, grammatical complexity, accuracy, and fluency. These findings suggest that scaffolded writing instruction with mind mapping can effectively enhance multiple dimensions of writing skills in adolescent EFL learners. This study provides insights into the application of using mind mapping to scaffold EFL learners’ narrative writing proficiency. Full article

In this paper, I focus on the puzzling ending of the apostolic letter in Acts 15 in which the addressees are told that if they hold to four “essential” prohibitions, they will “do well” (εὖ πράξετε, v. 29). The question as to how, exactly, can destabilise some understandings of the decree, with alternative translations creating different problems, and particularly so where theological commitments are at play. Following Danker’s call for greater attention to this phrase, I undertake a fresh, stratified survey of Greek usage across corpora ranging from the arguably less to the more proximate and bring this into dialogue with the senses given in various literary and social approaches to the decree involving epistolary rhetoric, reciprocity theory, and intertextuality. This reveals how purely linguistic data can stand in tension with compositional arguments in different ways and require a more complex arbitration between possibility, likelihood and coherence when both lexical- and discourse-level constraints are applied. Whilst not solving the problem of the decree outright, observing the impacts of different readings of εὖ πράξετε on the delicate balances involved presses some oblique but productive questions into the interpretive task. Full article

Sentiment analysis is a cornerstone of natural language processing. However, it presents formidable challenges due to the intricacies of lexical diversity, complex linguistic structures, and the subtleties of context dependence. This study introduces a bespoke and integrated approach to analyzing customer sentiment, with a particular emphasis on a case study in the Portuguese retail market. Capitalizing on the strengths of SentiLex-PT, a sentiment lexicon curated for the Portuguese language, and an array of sophisticated machine learning algorithms, this research constructs advanced models that encapsulate both lexical features and the subtleties of linguistic composition. A meticulous comparative analysis singles out multinomial logistic regression as the pre-eminent model for its applicability and accuracy within our case study. The findings of this analysis highlight the pivotal role that sentiment data play in strategic decision-making processes such as reputation management, strategic planning, and forecasting market trends within the retail sector. To the extent of our knowledge, this work is pioneering in its provision of a holistic sentiment analysis framework tailored to the Portuguese retail context, marking an advancement for both the academic field and industry application. Full article

This study examines the use of five tashbīh (simile) particles which appear in close frequency in pre-and early Islamic poetry and in the Qurʾan. The particles are ka-(as), ka-mā (such as), mithl (like), and derivatives of the roots ḥsb (deem) and shbh (looks like, similar to). As well as understanding classical Arabic techniques for composition of similes, the study examines aspects of the interrelationship between the Qurʾan and the poetry corpus, the single surviving Arabic text to which the scripture was exposed. It finds greater common structural and lexical similarities between poetry and the Qurʾan in its earlier period (during the Meccan Revelation, 610–622 CE) than later, following the migration of Prophet Muḥammad to Medina (622–632 CE), when other ways of using these particles developed. This suggests surveying these techniques in other texts possibly known to Medinian society, such as the Bible. The present study outlines the premise that qurʾanic composition moved from the influence of the Arabic prototype seen in the poetry in the earliest periods of Revelation to a different form in later periods (texts, possibly biblical). This premise can be further explored by future examination of the interrelationship between the Qurʾan, pre- and early Islamic poetry and the Bible. Full article

The automatic extraction of key entities in mechanics problems is an important means to automatically solve mechanics problems. Nevertheless, for standard Chinese, compared with the open domain, mechanics problems have a large number of specialized terms and composite entities, which leads to a low recognition capability. Although recent research demonstrates that external information and pre-trained language models can improve the performance of Chinese Named Entity Recognition (CNER), few efforts have been made to combine the two to explore high-performance algorithms for extracting mechanics entities. Therefore, this article proposes a Multi-Meta Information Embedding Enhanced Bidirectional Encoder Representation from Transformers (MMIEE-BERT) for recognizing entities in mechanics problems. The proposed method integrates lexical information and radical information into BERT layers directly by employing an information adapter layer (IAL). Firstly, according to the characteristics of Chinese, a Multi-Meta Information Embedding (MMIE) including character embedding, lexical embedding, and radical embedding is proposed to enhance Chinese sentence representation. Secondly, an information adapter layer (IAL) is proposed to fuse the above three embeddings into the lower layers of the BERT. Thirdly, a Bidirectional Long Short-Term Memory (BiLSTM) network and a Conditional Random Field (CRF) model are applied to semantically encode the output of MMIEE-BERT and obtain each character’s label. Finally, extensive experiments were carried out on the dataset built by our team and widely used datasets. The results demonstrate that the proposed method has more advantages than the existing models in the entity recognition of mechanics problems, and the precision, recall, and F1 score were improved. The proposed method is expected to provide an automatic means for extracting key information from mechanics problems. Full article

Numeral incorporation describes the merging of a numeral sign with a lexical sign to create a single sign with a compositional meaning, e.g., “three weeks.” As a phenomenon of simultaneous morphology, numeral incorporation is unique to sign languages. While researchers disagree on the exact morphological structure of the construction, it has, thus far, mainly been described as a synchronic, phonological phenomenon. Using the DGS corpus, a language resource on German Sign Language, we explore the possibility of numeral incorporation resulting from a language change process, specifically a grammaticalization process. Our dataset comprises tokens belonging to nine different signs that may occur in numeral incorporations. We find a cline of three constructions in the corpus, which shows a progression from free morpheme to cliticized morpheme to bound morpheme (affix). A comparison of the usage frequency of the three constructions in different age groups reveals that signers use more incorporations the younger they are. Following the apparent time approach, these observations are taken as indicators of diachronic language change. We describe to what extent the properties of numeral incorporation fit with the grammaticalization hypothesis and conclude that while the emergence of numeral incorporation is an instance of language change and shows some aspects seen in grammaticalization, the gradual change fails to exhibit some crucial aspects of grammaticalization and, thus, should not be regarded as an example thereof. Full article

We motivate a ‘rooted’ PP shell analysis of Arabic prepositional phrases, which takes into account the prepositional dual life, as a lexical root item and as a vocabulary word, projecting a lexical √P headed by the P root, and a functional pP headed by p, the syntactic case assigner. Moreover, PlaceP and PathP projections are motivated by differentiating locative and directional PPs, and AxPartPs represent the structure of adverbial spatial nouns (đ̣uruuf). It is shown that alternative analyses using a single source (or projection) of PPs are inadequate in dealing with prepositional polysemies, and their morpho-syntactic alternations or variations. A bifurcation analysis instead (distinguishing root syntax from category syntax) is motivated and implemented along the lines of distributive models of word formation, making use of the simplest composition operation Merge in both syntax and the lexicon. Full article

The performance of Chinese-named entity recognition (NER) has improved via word enhancement or new frameworks that incorporate various types of external data. However, for Chinese NER, syntactic composition (in sentence level) and inner regularity (in character-level) have rarely been studied. Chinese characters are highly sensitive to sentential syntactic data. The same Chinese character sequence can be decomposed into different combinations of words according to how they are used and placed in the context. In addition, the same type of entities usually have the same naming rules due to the specificity of the Chinese language structure. This paper presents a Kcr-FLAT to improve the performance of Chinese NER with enhanced semantic information. Specifically, we first extract different types of syntactic data, functionalize the syntactic information by a key-value memory network (KVMN), and fuse them by attention mechanism. Then the syntactic information and lexical information are integrated by a cross-transformer. Finally, we use an inner regularity perception module to capture the internal regularity of each entity for better entity type prediction. The experimental results show that with F1 scores as the evaluation index, the proposed model obtains 96.51%, 96.81%, and 70.12% accuracy rates on MSRA, resume, and Weibo datasets, respectively. Full article

Previous research and the BIA+ model support the hypothesis of language nonselective access during bilingual word recognition with language-ambiguous words like cognates organized in two distinct lexical representations. This paper adds to the existing literature by investigating how task demands and language proficiency influence cognate processing. Twenty-six Danish-English bilinguals with upper-intermediate to advanced L2 proficiencies performed four visual lexical decision tasks in which stimulus list composition (pure or mixed) and target language (L1 or L2) were varied. This study thus distinguishes itself from other studies by employing a within-subjects design to investigate a bilingual’s two languages. Significant cognate inhibition effects were found in the L2 mixed language condition while none of the other three tasks yielded significant results. Especially the absence of cognate facilitation effects in the L2 pure language condition was remarkable given the findings of previous literature. With reference to the BIA+ model’s assumptions of differing resting level activations for L1 and L2 lexical representations, the impact of L2 proficiency on cognate processing was tested in a post-hoc analysis dividing participants into two groups. This analysis revealed cognate facilitation effects for L2 upper-intermediate bilinguals in the L2 pure language condition while the results of the L1 tasks for both groups of bilinguals remained non-significant. The results therefore suggest that within-subject cognate processing is modulated by L2 proficiency in certain circumstances. Full article