Hasil untuk "Computational linguistics. Natural language processing"

Ma Lina

Abstract The current evaluation of English teaching quality in colleges and universities faces the problems of information uncertainty and fuzziness. Traditional evaluation methods cannot accurately reflect the complex teaching effects, mainly due to the diversity of data and the fuzziness of evaluation dimensions. To address this issue, this paper proposes a college English teaching quality evaluation system that combines Fuzzy C-Means (FCM) and Takagi-Sugeno Fuzzy Inference System (TS-FIS). First, the FCM algorithm is utilized to fuzzify various teaching data and convert the evaluation dimensions into fuzzy membership degrees. Then, TS-FIS is used to infer this fuzzy information and generate comprehensive scores. Finally, a deep neural network (DNN) is employed to train historical data, dynamically adjusting the evaluation results. The findings demonstrate that the system achieves an evaluation accuracy of more than 91% when dealing with uncertainties in complex teaching environments, and the score fluctuation range is controlled within 5% during the dynamic adjustment process, which proves the effectiveness of the system in improving evaluation accuracy and adaptability. The method proposed in this paper provides an effective solution to the problem of evaluating English teaching quality in colleges and universities using fuzzy information.

Toheeb Aduramomi Jimoh, Tabea De Wille, Nikola S. Nikolov

Natural Language Processing (NLP) is becoming a dominant subset of artificial intelligence as the need to help machines understand human language looks indispensable. Several NLP applications are ubiquitous, partly due to the myriad of datasets being churned out daily through mediums like social networking sites. However, the growing development has not been evident in most African languages due to the persisting resource limitations, among other issues. Yorùbá language, a tonal and morphologically rich African language, suffers a similar fate, resulting in limited NLP usage. To encourage further research towards improving this situation, this systematic literature review aims to comprehensively analyse studies addressing NLP development for Yorùbá, identifying challenges, resources, techniques, and applications. A well-defined search string from a structured protocol was employed to search, select, and analyse 105 primary studies between 2014 and 2024 from reputable databases. The review highlights the scarcity of annotated corpora, the limited availability of pre-trained language models, and linguistic challenges like tonal complexity and diacritic dependency as significant obstacles. It also revealed the prominent techniques, including rule-based methods, among others. The findings reveal a growing body of multilingual and monolingual resources, even though the field is constrained by socio-cultural factors such as code-switching and the desertion of language for digital usage. This review synthesises existing research, providing a foundation for advancing NLP for Yorùbá and in African languages generally. It aims to guide future research by identifying gaps and opportunities, thereby contributing to the broader inclusion of Yorùbá and other under-resourced African languages in global NLP advancements.

Sophie Hao

Chesi's (forthcoming) target paper depicts a generative linguistics in crisis, foreboded by Piantadosi's (2023) declaration that "modern language models refute Chomsky's approach to language." In order to survive, Chesi warns, generativists must hold themselves to higher standards of formal and empirical rigor. This response argues that the crisis described by Chesi and Piantadosi actually has little to do with rigor, but is rather a reflection of generativists' limited social ambitions. Chesi ties the fate of generative linguistics to its intellectual merits, but the current success of language model research is social in nature as much as it is intellectual. In order to thrive, then, generativists must do more than heed Chesi's call for rigor; they must also expand their ambitions by giving outsiders a stake in their future success.

Yufei Xiang, Yiqun Shen, Yeqin Zhang et al.

Large Language Models (LLMs) possess extensive knowledge and commonsense reasoning capabilities, making them valuable for creating powerful agents. However, existing LLM agent frameworks have not fully utilized past experiences for improvement. This work introduces a new LLM-based agent framework called Retrospex, which addresses this challenge by analyzing past experiences in depth. Unlike previous approaches, Retrospex does not directly integrate experiences into the LLM's context. Instead, it combines the LLM's action likelihood with action values estimated by a Reinforcement Learning (RL) Critic, which is trained on past experiences through an offline ''retrospection'' process. Additionally, Retrospex employs a dynamic action rescoring mechanism that increases the importance of experience-based values for tasks that require more interaction with the environment. We evaluate Retrospex in ScienceWorld, ALFWorld and Webshop environments, demonstrating its advantages over strong, contemporary baselines.

Jean Blanchard MAYI YUL

Résumé : Analyser les travaux scientifiques est une tache aussi ardue que difficile qui demande beaucoup de munitie. Cet article fait une analyse bibliométrique des mémoires de licence (Bac+5) défendus au sein du Département des Sciences et techniques Documentaires de l'Université de Kinshasa de 2014 à 2018. Les travaux produits par des universités sont de plus en plus oubliés par les autorités. Jeune qu’il soit le Département des Sciences et techniques Documentaires est parmi les rares départements que l’on retrouve dans des universités et facultés congolaises et il organise des études sur les archives, la bibliothèque et l’Edition. Mots-clés : Analyse, bibliologie, bibliometrie, memoire, Sciences et Techniques documentaires.

Roberto Zamparelli

Thanks to independent advances in language and image generation, we could soon be in the position to have systems that communicate with us by combining language and images in their output, a skill that humans do not possess (we receive, but we do not produce images at high speed). This paper explores some of the implications of this idea: which kinds of data sets need to be developed to train such systems, in which cases language and images could be most usefully integrated and which issues could arise on the image generation and language+images integration side. Story and dialogue illustration could be relatively low-hanging fruits for this technology, and a looped combination of I2T LLMs and T2I diffusion models is likely to play a role in solving some of the issues that arise in the design of such systems.

Yanis Labrak, Adrien Bazoge, Beatrice Daille et al.

Subword tokenization has become the prevailing standard in the field of natural language processing (NLP) over recent years, primarily due to the widespread utilization of pre-trained language models. This shift began with Byte-Pair Encoding (BPE) and was later followed by the adoption of SentencePiece and WordPiece. While subword tokenization consistently outperforms character and word-level tokenization, the precise factors contributing to its success remain unclear. Key aspects such as the optimal segmentation granularity for diverse tasks and languages, the influence of data sources on tokenizers, and the role of morphological information in Indo-European languages remain insufficiently explored. This is particularly pertinent for biomedical terminology, characterized by specific rules governing morpheme combinations. Despite the agglutinative nature of biomedical terminology, existing language models do not explicitly incorporate this knowledge, leading to inconsistent tokenization strategies for common terms. In this paper, we seek to delve into the complexities of subword tokenization in French biomedical domain across a variety of NLP tasks and pinpoint areas where further enhancements can be made. We analyze classical tokenization algorithms, including BPE and SentencePiece, and introduce an original tokenization strategy that integrates morpheme-enriched word segmentation into existing tokenization methods.

Leonidas Gee, Andrea Zugarini, Novi Quadrianto

To reduce the inference cost of large language models, model compression is increasingly used to create smaller scalable models. However, little is known about their robustness to minority subgroups defined by the labels and attributes of a dataset. In this paper, we investigate the effects of 18 different compression methods and settings on the subgroup robustness of BERT language models. We show that worst-group performance does not depend on model size alone, but also on the compression method used. Additionally, we find that model compression does not always worsen the performance on minority subgroups. Altogether, our analysis serves to further research into the subgroup robustness of model compression.

Mehrdad Sabetzadeh, Chetan Arora

Natural Language Processing (NLP) is now a cornerstone of requirements automation. One compelling factor behind the growing adoption of NLP in Requirements Engineering (RE) is the prevalent use of natural language (NL) for specifying requirements in industry. NLP techniques are commonly used for automatically classifying requirements, extracting important information, e.g., domain models and glossary terms, and performing quality assurance tasks, such as ambiguity handling and completeness checking. With so many different NLP solution strategies available and the possibility of applying machine learning alongside, it can be challenging to choose the right strategy for a specific RE task and to evaluate the resulting solution in an empirically rigorous manner. In this chapter, we present guidelines for the selection of NLP techniques as well as for their evaluation in the context of RE. In particular, we discuss how to choose among different strategies such as traditional NLP, feature-based machine learning, and language-model-based methods. Our ultimate hope for this chapter is to serve as a stepping stone, assisting newcomers to NLP4RE in quickly initiating themselves into the NLP technologies most pertinent to the RE field.

Phillip Richter-Pechanski, Philipp Wiesenbach, Dominic M. Schwab et al.

Automatic extraction of medical information from clinical documents poses several challenges: high costs of required clinical expertise, limited interpretability of model predictions, restricted computational resources and privacy regulations. Recent advances in domain-adaptation and prompting methods showed promising results with minimal training data using lightweight masked language models, which are suited for well-established interpretability methods. We are first to present a systematic evaluation of these methods in a low-resource setting, by performing multi-class section classification on German doctor's letters. We conduct extensive class-wise evaluations supported by Shapley values, to validate the quality of our small training data set and to ensure the interpretability of model predictions. We demonstrate that a lightweight, domain-adapted pretrained model, prompted with just 20 shots, outperforms a traditional classification model by 30.5% accuracy. Our results serve as a process-oriented guideline for clinical information extraction projects working with low-resource.

Carlos NGWAPITSHI NGWAMASHI

Résumé : L’étude menée par nous qui se solde par la présentation des résultats sous format d’un article porte sur « le magistrat congolais face au blanchiment d’argent sale ». Il répond à la question de savoir si le magistrat congolais peut-être classé parmi les usagers du blanchiment d’argent sale ? Après analyse, il s’est dégagé une opinion. Il y a lieu de faire la part des choses, dans la mesure où la corruption étant un interdit en droit positif congolais, ce qui renvoi à ce que tout juge ou magistrat selon le cas, qui recourt à cette pratique, tombe sous le coup du blanchiment d’argent sale que nous qualifions de « blanchiment d’opportunité ». Cependant, il y a lieu de préciser qu’après une observation de la situation, l’appareil judiciaire congolais est bourré d’un mal, qu’est la corruption voire même la concussion, raison pour laquelle depuis un certain temps, soit de 2010 à nos jours, il y a une abondance des procès en procédure de prise à partie devant la Cour de Cassation pour dol ou déni de justice. Mots-clés : Magistrat, blanchiment, argent sale

Andi Febriana Tamrin, Miselin Adveni, Basri Basri

This study analyses the types of neurotic needs experienced by Griffin through three kinds of neurotic conditions, which indicate that he has a neurotic disorder. This study uses psychoanalysis social by Karen Horney's theory about the types of neurotic needs, namely the neurotic need for power, the neurotic need to exploit others, the neurotic need for self-sufficiency, and independence. This study aimed to determine the types of neurotic conditions experienced by Griffin. This research method uses descriptive qualitative. The data Source of this research is the novel The Invisible Man by H.G. Wells, published in 1897 but using the 2016 version, which consists of 250 pages and 28 chapters. Meanwhile, the instrument in this study is note-taking. The data analysis technique of this research uses the theory of Miles and Huberman, namely, data reduction, data presentation, and drawing conclusions and verification. This study found that Griffin experienced three types of neurotic needs: the neurotic need for power, the neurotic need to exploit others, the neurotic need for self-sufficiency, and independence, which proves that he has a neurotic disorder or mental disorder. Social, cultural, and childhood life are the factors that influenced Griffin in a way to experience some types of neurotic needs.

Mohammed AGUIDI

Résumé : Cet article présente une étude scientifique sur la linguistique et la didactique. Les deux domaines sont considérés comme un pilier essentiel en classe du français langue étrangère. La présente étude concerne précisément la compréhension orale, étant une compétence primordiale de la communication orale, car l'apprenant est naturellement exposé à l'écoute de la langue avant de la produire. Sur la base de cette logique, mener une enquête auprès d'un groupe d'élèves du secondaire qualifiant marocain en vue d’identifier les erreurs liées à une telle compétence et leur origine, reste la première étape didactique pour concevoir des dispositifs pédagogiques dans les futurs projets de recherche sur le même sujet. Cette recherche porte également sur l'analyse de certaines erreurs de compréhension orale recueillies à partir de l'enquête déjà citée ; cette analyse est basée sur des cadres contextuel, épistémologique et théorique qui régissent la compréhension orale et l'analyse de l'erreur. Mots-clés : didactique, FLE, erreur, compétence grammaticale, compréhension orale.

Tobias Bornheim, Niklas Grieger, Patrick Gustav Blaneck et al.

The growing body of political texts opens up new opportunities for rich insights into political dynamics and ideologies but also increases the workload for manual analysis. Automated speaker attribution, which detects who said what to whom in a speech event and is closely related to semantic role labeling, is an important processing step for computational text analysis. We study the potential of the large language model family Llama 2 to automate speaker attribution in German parliamentary debates from 2017-2021. We fine-tune Llama 2 with QLoRA, an efficient training strategy, and observe our approach to achieve competitive performance in the GermEval 2023 Shared Task On Speaker Attribution in German News Articles and Parliamentary Debates. Our results shed light on the capabilities of large language models in automating speaker attribution, revealing a promising avenue for computational analysis of political discourse and the development of semantic role labeling systems.

A. Seza Doğruöz, Sunayana Sitaram, Barbara E. Bullock et al.

The analysis of data in which multiple languages are represented has gained popularity among computational linguists in recent years. So far, much of this research focuses mainly on the improvement of computational methods and largely ignores linguistic and social aspects of C-S discussed across a wide range of languages within the long-established literature in linguistics. To fill this gap, we offer a survey of code-switching (C-S) covering the literature in linguistics with a reflection on the key issues in language technologies. From the linguistic perspective, we provide an overview of structural and functional patterns of C-S focusing on the literature from European and Indian contexts as highly multilingual areas. From the language technologies perspective, we discuss how massive language models fail to represent diverse C-S types due to lack of appropriate training data, lack of robust evaluation benchmarks for C-S (across multilingual situations and types of C-S) and lack of end-to-end systems that cover sociolinguistic aspects of C-S as well. Our survey will be a step towards an outcome of mutual benefit for computational scientists and linguists with a shared interest in multilingualism and C-S.