Hasil untuk "Japanese language and literature"

E. O. Novoselova

In the late 19th – early 20th centuries, Japanese Buddhism was going through difficult times. Institutional crisis, loss of governmental support, competition with Shinto and Christianity, persecution caused by both political and social factors contributed to the consolidation of Japanese sangha and establishment of close relations with supporters abroad. A significant role in this process was played by the so-called general journals (総合雑誌, sōgō zasshi) – multitopic periodicals comprised of articles on politics, science, society and culture, which functioned as a platform for free exchange of opinions, both open and anonymous. Buddhist-oriented journals thus attracted both religious activists and scholars of Buddhology to their pages, while simultaneously exchanging contacts with foreign periodicals and promoting cooperation. The result was an impressive “Buddhist network” of journals, where representatives of various Buddhist schools could discuss pressing issues together, the works of young Japanese Buddhologists were published, and articles by their Western colleagues reprinted. Letters from Buddhists from other countries, such as India, Siam, and Ceylon, as well as ones by European sympathizers, were also published. Many such periodicals had a relatively short lifespan, but at least 800 journals are known. These included intersectarian and individual schools’ bulletins, regional journals, such as People’s Teaching (国教, Kokkyō), and female-oriented journals, such as Buddhist Woman (佛教婦人, Bukkyō fujin). All of them served as means of building strong horizontal ties and supporting Japanese Buddhism. One of the important functions of the “Buddhist network” was to provide information support for missionary work by Japanese Buddhists and coverage of sangha’s participation in important international cultural events. Paradoxically, despite governmental pressure, Japanese Buddhism managed to spread significantly abroad. This article examines said missions and their coverage.

Shohei Hisada, Endo Sunao, Himi Yamato et al.

This study investigates the applicability of HealthBench, a large-scale, rubric-based medical benchmark, to the Japanese context. Although robust evaluation frameworks are essential for the safe development of medical LLMs, resources in Japanese are scarce and often consist of translated multiple-choice questions. Our research addresses this issue in two ways. First, we establish a performance baseline by applying a machine-translated version of HealthBench's 5,000 scenarios to evaluate two models: a high-performing multilingual model (GPT-4.1) and a Japanese-native open-source model (LLM-jp-3.1). Secondly, we use an LLM-as-a-Judge approach to systematically classify the benchmark's scenarios and rubric criteria. This allows us to identify 'contextual gaps' where the content is misaligned with Japan's clinical guidelines, healthcare systems or cultural norms. Our findings reveal a modest performance drop in GPT-4.1 due to rubric mismatches, as well as a significant failure in the Japanese-native model, which lacked the required clinical completeness. Furthermore, our classification shows that, despite most scenarios being applicable, a significant proportion of the rubric criteria require localisation. This work underscores the limitations of direct benchmark translation and highlights the urgent need for a context-aware, localised adaptation, a "J-HealthBench", to ensure the reliable and safe evaluation of medical LLMs in Japan.

Belén Agüera-Marco, Itziar Gonzalez-Dios

In this work, we present LengClaro2023, a dataset of legal-administrative texts in Spanish. Based on the most frequently used procedures from the Spanish Social Security website, we have created for each text two simplified equivalents. The first version follows the recommendations provided by arText claro. The second version incorporates additional recommendations from plain language guidelines to explore further potential improvements in the system. The linguistic resource created in this work can be used for evaluating automatic text simplification (ATS) systems in Spanish.

Xiaoyu Luo, Yiyi Chen, Johannes Bjerva et al.

We present the first comprehensive study of Memorization in Multilingual Large Language Models (MLLMs), analyzing 95 languages using models across diverse model scales, architectures, and memorization definitions. As MLLMs are increasingly deployed, understanding their memorization behavior has become critical. Yet prior work has focused primarily on monolingual models, leaving multilingual memorization underexplored, despite the inherently long-tailed nature of training corpora. We find that the prevailing assumption, that memorization is highly correlated with training data availability, fails to fully explain memorization patterns in MLLMs. We hypothesize that the conventional focus on monolingual settings, effectively treating languages in isolation, may obscure the true patterns of memorization. To address this, we propose a novel graph-based correlation metric that incorporates language similarity to analyze cross-lingual memorization. Our analysis reveals that among similar languages, those with fewer training tokens tend to exhibit higher memorization, a trend that only emerges when cross-lingual relationships are explicitly modeled. These findings underscore the importance of a \textit{language-aware} perspective in evaluating and mitigating memorization vulnerabilities in MLLMs. This also constitutes empirical evidence that language similarity both explains Memorization in MLLMs and underpins Cross-lingual Transferability, with broad implications for multilingual NLP.

Gunjan Balde, Soumyadeep Roy, Mainack Mondal et al.

In this work, we show a fundamental limitation in vocabulary adaptation approaches that use Byte-Pair Encoding (BPE) tokenization scheme for fine-tuning pretrained language models (PLMs) to expert domains. Current approaches trivially append the target domain-specific vocabulary at the end of the PLM vocabulary. This approach leads to a lower priority score and causes sub-optimal tokenization in BPE that iteratively uses merge rules to tokenize a given text. To mitigate this issue, we propose AdaptBPE where the BPE tokenization initialization phase is modified to first perform the longest string matching on the added (target) vocabulary before tokenizing at the character level. We perform an extensive evaluation of AdaptBPE versus the standard BPE over various classification and summarization tasks; AdaptBPE improves by 3.57% (in terms of accuracy) and 1.87% (in terms of Rouge-L), respectively. AdaptBPE for MEDVOC works particularly well when reference summaries have high OOV concentration or are longer in length. We also conduct a human evaluation, revealing that AdaptBPE generates more relevant and more faithful summaries as compared to MEDVOC. We make our codebase publicly available at https://github.com/gb-kgp/adaptbpe.

Matīss Rikters, Sanita Reinsone

At the beginning of 2022, a simplistic word-guessing game took the world by storm and was further adapted to many languages beyond the original English version. In this paper, we examine the strategies of daily word-guessing game players that have evolved during a period of over two years. A survey gathered from 25% of frequent players reveals their strategies and motivations for continuing the daily journey. We also explore the capability of several popular open-access large language model systems and open-source models at comprehending and playing the game in two different languages. Results highlight the struggles of certain models to maintain correct guess length and generate repetitions, as well as hallucinations of non-existent words and inflections.

Andrea Busto-Castiñeira, Francisco J. González-Castaño, Silvia García-Méndez et al.

In recent years, the field of Natural Language Generation (NLG) has been boosted by the recent advances in deep learning technologies. Nonetheless, these new data-intensive methods introduce language-dependent disparities in NLG as the main training data sets are in English. Also, most neural NLG systems use decoder-only (causal) transformer language models, which work well for English, but were not designed with other languages in mind. In this work we depart from the hypothesis that they may introduce generation bias in target languages with less rigid word ordering, subject omission, or different attachment preferences for relative clauses, so that for these target languages other language generation strategies may be more desirable. This paper first compares causal and non-causal language modeling for English and Spanish, two languages with different grammatical structures and over 1.5 billion and 0.5 billion speakers, respectively. For this purpose, we define a novel metric of average causal and non-causal context-conditioned entropy of the grammatical category distribution for both languages as an information-theoretic a priori approach. The evaluation of natural text sources (such as training data) in both languages reveals lower average non-causal conditional entropy in Spanish and lower causal conditional entropy in English. According to this experiment, Spanish is more predictable than English given a non-causal context. Then, by applying a conditional relative entropy metric to text generation experiments, we obtain as insights that the best performance is respectively achieved with causal NLG in English, and with non-causal NLG in Spanish. These insights support further research in NLG in Spanish using bidirectional transformer language models.

Nicolas Audinet de Pieuchon, Adel Daoud, Connor Thomas Jerzak et al.

We investigate the potential of large language models (LLMs) to disentangle text variables--to remove the textual traces of an undesired forbidden variable in a task sometimes known as text distillation and closely related to the fairness in AI and causal inference literature. We employ a range of various LLM approaches in an attempt to disentangle text by identifying and removing information about a target variable while preserving other relevant signals. We show that in the strong test of removing sentiment, the statistical association between the processed text and sentiment is still detectable to machine learning classifiers post-LLM-disentanglement. Furthermore, we find that human annotators also struggle to disentangle sentiment while preserving other semantic content. This suggests there may be limited separability between concept variables in some text contexts, highlighting limitations of methods relying on text-level transformations and also raising questions about the robustness of disentanglement methods that achieve statistical independence in representation space.

Paloma Piot, Javier Parapar

Hate speech is a harmful form of online expression, often manifesting as derogatory posts. It is a significant risk in digital environments. With the rise of Large Language Models (LLMs), there is concern about their potential to replicate hate speech patterns, given their training on vast amounts of unmoderated internet data. Understanding how LLMs respond to hate speech is crucial for their responsible deployment. However, the behaviour of LLMs towards hate speech has been limited compared. This paper investigates the reactions of seven state-of-the-art LLMs (LLaMA 2, Vicuna, LLaMA 3, Mistral, GPT-3.5, GPT-4, and Gemini Pro) to hate speech. Through qualitative analysis, we aim to reveal the spectrum of responses these models produce, highlighting their capacity to handle hate speech inputs. We also discuss strategies to mitigate hate speech generation by LLMs, particularly through fine-tuning and guideline guardrailing. Finally, we explore the models' responses to hate speech framed in politically correct language.

W. J. T. Mollema

Is it sensical to ascribe psychological predicates to AI systems like chatbots based on large language models (LLMs)? People have intuitively started ascribing emotions or consciousness to social AI ('affective artificial agents'), with consequences that range from love to suicide. The philosophical question of whether such ascriptions are warranted is thus very relevant. This paper advances the argument that LLMs instantiate language users in Ludwig Wittgenstein's sense but that ascribing psychological predicates to these systems remains a functionalist temptation. Social AIs are not full-blown language users, but rather more like Italo Calvino's literature machines. The ideas of LLMs as Wittgensteinian language users and Calvino's literature-producing writing machine are combined. This sheds light on the misguided functionalist temptation inherent in moving from equating the two to the ascription of psychological predicates to social AI. Finally, the framework of mortal computation is used to show that social AIs lack the basic autopoiesis needed for narrative façons de parler and their role in the sensemaking of human (inter)action. Such psychological predicate ascriptions could make sense: the transition 'from quantity to quality' can take place, but its route lies somewhere between life and death, not between affective artifacts and emotion approximation by literature machines.

Yi-Cheng Lin, Tzu-Quan Lin, Chih-Kai Yang et al.

Speech Integrated Large Language Models (SILLMs) combine large language models with speech perception to perform diverse tasks, such as emotion recognition to speaker verification, demonstrating universal audio understanding capability. However, these models may amplify biases present in training data, potentially leading to biased access to information for marginalized groups. This work introduces a curated spoken bias evaluation toolkit and corresponding dataset. We evaluate gender bias in SILLMs across four semantic-related tasks: speech-to-text translation (STT), spoken coreference resolution (SCR), spoken sentence continuation (SSC), and spoken question answering (SQA). Our analysis reveals that bias levels are language-dependent and vary with different evaluation methods. Our findings emphasize the necessity of employing multiple approaches to comprehensively assess biases in SILLMs, providing insights for developing fairer SILLM systems.

Maryam Alimardani, Jesse Duret, Anne-Lise Jouen et al.

The aim of the current study was to investigate children's brain responses to robot-assisted language learning. EEG brain signals were collected from 41 Japanese children who learned French vocabularies in two groups; half of the children learned new words from a social robot that narrated a story in French using animations on a computer screen (Robot group) and the other half watched the same animated story on the screen but only with a voiceover narration and without the robot (Display group). To examine brain activation during the learning phase, we extracted EEG functional connectivity (FC) which is defined as the rhythmic synchronization of signals recorded from different brain areas. The results indicated significantly higher global synchronization of brain signals in the theta frequency band in the Robot group during the learning phase. Closer inspection of intra-hemispheric and inter-hemispheric connections revealed that children who learned a new language from the robot experienced a stronger theta-band EEG synchronization in inter-hemispheric connections, which has been previously associated with success in second language learning in the neuroscientific literature. Additionally, using a multiple linear regression analysis, it was found that theta-band FC and group assignment were significant predictors of children's language learning with the Robot group scoring higher in the post-interaction word recognition test. These findings provide novel neuroscientific evidence for the effectiveness of social robots as second language tutors for children.

Badr AlKhamissi, Siddharth Verma, Ping Yu et al.

In this paper, we conduct a thorough investigation into the reasoning capabilities of Large Language Models (LLMs), focusing specifically on the Open Pretrained Transformers (OPT) models as a representative of such models. Our study entails finetuning three different sizes of OPT on a carefully curated reasoning corpus, resulting in two sets of finetuned models: OPT-R, finetuned without explanations, and OPT-RE, finetuned with explanations. We then evaluate all models on 57 out-of-domain tasks drawn from the SUPER-NATURALINSTRUCTIONS benchmark, covering 26 distinct reasoning skills, utilizing three prompting techniques. Through a comprehensive grid of 27 configurations and 6,156 test evaluations, we investigate the dimensions of finetuning, prompting, and scale to understand the role of explanations on different reasoning skills. Our findings reveal that having explanations in the fewshot exemplar has no significant impact on the model's performance when the model is finetuned, while positively affecting the non-finetuned counterpart. Moreover, we observe a slight yet consistent increase in classification accuracy as we incorporate explanations during prompting and finetuning, respectively. Finally, we offer insights on which skills benefit the most from incorporating explanations during finetuning and prompting, such as Numerical (+20.4%) and Analogical (+13.9%) reasoning, as well as skills that exhibit negligible or negative effects.

Oliver Vinzelberg, Mark David Jenkins, Gordon Morison et al.

Summarisation of research results in plain language is crucial for promoting public understanding of research findings. The use of Natural Language Processing to generate lay summaries has the potential to relieve researchers' workload and bridge the gap between science and society. The aim of this narrative literature review is to describe and compare the different text summarisation approaches used to generate lay summaries. We searched the databases Web of Science, Google Scholar, IEEE Xplore, Association for Computing Machinery Digital Library and arXiv for articles published until 6 May 2022. We included original studies on automatic text summarisation methods to generate lay summaries. We screened 82 articles and included eight relevant papers published between 2020 and 2021, all using the same dataset. The results show that transformer-based methods such as Bidirectional Encoder Representations from Transformers (BERT) and Pre-training with Extracted Gap-sentences for Abstractive Summarization (PEGASUS) dominate the landscape of lay text summarisation, with all but one study using these methods. A combination of extractive and abstractive summarisation methods in a hybrid approach was found to be most effective. Furthermore, pre-processing approaches to input text (e.g. applying extractive summarisation) or determining which sections of a text to include, appear critical. Evaluation metrics such as Recall-Oriented Understudy for Gisting Evaluation (ROUGE) were used, which do not consider readability. To conclude, automatic lay text summarisation is under-explored. Future research should consider long document lay text summarisation, including clinical trial reports, and the development of evaluation metrics that consider readability of the lay summary.

Duong Tien Pham, Luan Thanh Nguyen

Every human has their own name, a fundamental aspect of their identity and cultural heritage. The name often conveys a wealth of information, including details about an individual's background, ethnicity, and, especially, their gender. By detecting gender through the analysis of names, researchers can unlock valuable insights into linguistic patterns and cultural norms, which can be applied to practical applications. Hence, this work presents a novel dataset for Japanese name gender detection comprising 64,139 full names in romaji, hiragana, and kanji forms, along with their biological genders. Moreover, we propose Gendec, a framework for gender detection from Japanese names that leverages diverse approaches, including traditional machine learning techniques or cutting-edge transfer learning models, to predict the gender associated with Japanese names accurately. Through a thorough investigation, the proposed framework is expected to be effective and serve potential applications in various domains.

Brendan Arkell Morley

G. F. Ishkineeva, F. F. Ishkineeva

Russian-Japanese relations present one of the most interesting cases of international relations with a perplexing historical background and a complex set of factors influencing contemporary  dynamics of Russian- Japanese interaction. The relations are claimed to have improved under Putin and Abe administrations, introduction of the Eight-Point Cooperation Plan and establishment of a unique post of a Minister for Cooperation with Russia. This article analyzed the specific period of Russian-Japanese relations between 2016 and 2019. Improved bilateral relations created a historical precedent that is important to understand in light of contemporary deteriorated relations between Japan and  Russia. However, Russian-Japanese  cooperation in this period is complicated by a complex historical legacy and other factors and is set to be locked in a Kurilian stumbling block. International relation theories traditionally applied to  analyze Russian-Japanese  relations fail to suggest the way out and the mechanisms to improve Russian-Japanese relations. The present article explores the theoretical apparatus traditionally applied to Russian-Japanese  relations and investigates  the potential of a functionalist approach to explain Russian-Japanese relations between 2016 and 2019. Functionalism describes the way to improve relations of countries with adversarial relations by moving away from high-politics issues and quid pro quo logic and focusing on the problem-solving approach. The spill-over effect occurs when cooperation established in one field expands to other areas. The article concludes by arguing that, in contemporary  Russian-Japanese cooperation, there is a hybrid spill-around effect.

Sadahisa Watanabe

l

Jussi T. S. Heikkila

The Journal of Economic Literature codes classification system (JEL) published by the American Economic Association (AEA) is the de facto standard classification system for research literature in economics. The JEL classification system is used to classify articles, dissertations, books, book reviews, and working papers in EconLit, a database maintained by the AEA. Over time, it has evolved and extended to a system with over 850 subclasses. This paper reviews the history and development of the JEL classification system, describes the current version, and provides a selective overview of its uses and applications in research. The JEL codes classification system has been adopted by several publishers, and their instructions are reviewed. There are interesting avenues for future research as the JEL classification system has been surprisingly little used in existing bibliometric and scientometric research as well as in library classification systems.

Young-Ho Kim, Sungdong Kim, Minsuk Chang et al.

Current natural language interaction for self-tracking tools largely depends on bespoke implementation optimized for a specific tracking theme and data format, which is neither generalizable nor scalable to a tremendous design space of self-tracking. However, training machine learning models in the context of self-tracking is challenging due to the wide variety of tracking topics and data formats. In this paper, we propose a novel NLP task for self-tracking that extracts close- and open-ended information from a retrospective activity log described as a plain text, and a domain-agnostic, GPT-3-based NLU framework that performs this task. The framework augments the prompt using synthetic samples to transform the task into 10-shot learning, to address a cold-start problem in bootstrapping a new tracking topic. Our preliminary evaluation suggests that our approach significantly outperforms the baseline QA models. Going further, we discuss future application domains toward which the NLP and HCI researchers can collaborate.