Hasil untuk "Language and Literature"

H. Scarborough, Wanda Dobrich

R. Jakobson, M. Halle

Okarisma Mailani, Irna Nuraeni, Sarah Agnia Syakila et al.

Humans need communication to help survival, one of which is by using language as a means of communication. Language is the most effective communication tool in conveying messages, thoughts, feelings, goals to others and allows for creating cooperation between humans. So that the role of language becomes very dominant in various human daily activities. The purpose of this study is to describe matters relating to language as a means of communication and communication in everyday life. The method used in this research is the literature review method, the data are collected from relevant literature data. The result of this research and discussion is to explain about language as a communication tool which discusses the function of language as a human communication tool which includes five basic functions, namely the function of expression, the function of information, the function of exploration, the function of persuasion, and the function of entertainment. And explain about communication in everyday life which discusses why we communicate and the language used when communicating in everyday life. As social beings, of course humans in their lives need communication to be able to establish relationships with other humans. Language is the most effective tool or medium for conveying thoughts, with human language being able to interact and talk about anything. For this reason, every human being communicates to get or convey information or messages

Alexander LeClair, S. Haque, Lingfei Wu et al.

Automatic source code summarization is the task of generating natural language descriptions for source code. Automatic code summarization is a rapidly expanding research area, especially as the community has taken greater advantage of advances in neural network and AI technologies. In general, source code summarization techniques use the source code as input and outputs a natural language description. Yet a strong consensus is developing that using structural information as input leads to improved performance. The first approaches to use structural information flattened the AST into a sequence. Recently, more complex approaches based on random AST paths or graph neural networks have improved on the models using flattened ASTs. However, the literature still does not describe the using a graph neural network together with source code sequence as separate inputs to a model. Therefore, in this paper, we present an approach that uses a graph-based neural architecture that better matches the default structure of the AST to generate these summaries. We evaluate our technique using a data set of 2.1 million Java method-comment pairs and show improvement over four baseline techniques, two from the software engineering literature, and two from machine learning literature.

Javier Virúes‐Ortega

Ken Hyland

J. Ptacek, T. L. Eberhardt

R. Ellis

This article examines a number of controversies relating to how corrective feedback (CF) has been viewed in SLA and language pedagogy. These controversies address (1) whether CF contributes to L2 acquisition, (2) which errors should be corrected, (3) who should do the correcting (the teacher or the learner him/herself), (4) which type of CF is the most effective, and (5) what is the best timing for CF (immediate or delayed). In discussing these controversies, both the pedagogic and SLA literature will be drawn on. The article will conclude with some general guidelines for conducting CF in language classrooms based on a sociocultural view of L2 acquisition and will suggest how these guidelines might be used for teacher development.

Ofelia García, A. Lin

S. Kidd, B. Eskenazi, A. Wyrobek

A. Fothergill, E. G. Maestas, J. Darlington

Buhong Wang, Jin Xiao, Ruochen Dong et al.

Satellite networks are essential to global connectivity yet face severe multidimensional cybersecurity threats. This systematic review conducts a holistic analysis of threats across the physical, network, and user layers. We propose the Sat-ATT&CK knowledge matrix to model satellite-specific attack chains. Corresponding defense technologies are organized within the core functions (Protect, Detect, Respond) of the National Institute of Standards and Technology (NIST) Cybersecurity Framework, establishing a structured threat–defense mapping. Furthermore, an exploratory case study on fine-tuning a large language model (SatSec) using the compiled literature corpus is presented. Finally, we identify key challenges and outline the future research directions toward a more resilient and intelligent security paradigm.

M. Svirsky, A. Robbins, K. Kirk et al.

Lingzhe Zhang, Tong Jia, Mengxi Jia et al.

As large language models (LLMs) grow increasingly sophisticated and pervasive, their application to various Artificial Intelligence for IT Operations (AIOps) tasks has garnered significant attention. However, a comprehensive understanding of the impact, potential, and limitations of LLMs in AIOps remains in its infancy. To address this gap, we conducted a detailed survey of LLM4AIOps, focusing on how LLMs can optimize processes and improve outcomes in this domain. We analyzed 183 research papers published between January 2020 and December 2024 to answer four key research questions (RQs). In RQ1, we examine the diverse failure data sources utilized, including advanced LLM-based processing techniques for legacy data and the incorporation of new data sources enabled by LLMs. RQ2 explores the evolution of AIOps tasks, highlighting the emergence of novel tasks and the publication trends across these tasks. RQ3 investigates the various LLM-based methods applied to address AIOps challenges. Finally, RQ4 reviews evaluation methodologies tailored to assess LLM-integrated AIOps approaches. Based on our findings, we discuss the state-of-the-art advancements and trends, identify gaps in existing research, and propose promising directions for future exploration.

Samin Mahdipour Aghabagher, Saeedeh Momtazi

Dialogue State Tracking (DST) is an essential element of conversational AI with the objective of deeply understanding the conversation context and leading it toward answering user requests. Due to high demands for open-domain and multi-turn chatbots, the traditional rule-based DST is not efficient enough, since it cannot provide the required adaptability and coherence for human-like experiences in complex conversations. This study proposes a hybrid DST model that utilizes rule-based methods along with language models, including BERT for slot filling and intent detection, XGBoost for intent validation, GPT for DST, and online agents for real-time answer generation. This model is uniquely designed to be evaluated on a comprehensive Persian multi-turn dialogue dataset and demonstrated significantly improved accuracy and coherence over existing methods in Persian-based chatbots. The results demonstrate how effectively a hybrid approach may improve DST capabilities, paving the way for conversational AI systems that are more customized, adaptable, and human-like.

Iwan Williams

Large Language Models (LLMs) such as GPT-4 produce compelling responses to a wide range of prompts. But their representational capacities are uncertain. Many LLMs have no direct contact with extra-linguistic reality: their inputs, outputs and training data consist solely of text, raising the questions (1) can LLMs represent anything and (2) if so, what? In this paper, I explore what it would take to answer these questions according to a structural-correspondence based account of representation, and make an initial survey of this evidence. I argue that the mere existence of structural correspondences between LLMs and worldly entities is insufficient to ground representation of those entities. However, if these structural correspondences play an appropriate role - they are exploited in a way that explains successful task performance - then they could ground real world contents. This requires overcoming a challenge: the text-boundedness of LLMs appears, on the face of it, to prevent them engaging in the right sorts of tasks.

E. Apter

Melusi Malinga, Isaac Lupanda, Mike Wa Nkongolo et al.

South Africa and the Democratic Republic of Congo (DRC) present a complex linguistic landscape with languages such as Zulu, Sepedi, Afrikaans, French, English, and Tshiluba (Ciluba), which creates unique challenges for AI-driven translation and sentiment analysis systems due to a lack of accurately labeled data. This study seeks to address these challenges by developing a multilingual lexicon designed for French and Tshiluba, now expanded to include translations in English, Afrikaans, Sepedi, and Zulu. The lexicon enhances cultural relevance in sentiment classification by integrating language-specific sentiment scores. A comprehensive testing corpus is created to support translation and sentiment analysis tasks, with machine learning models such as Random Forest, Support Vector Machine (SVM), Decision Trees, and Gaussian Naive Bayes (GNB) trained to predict sentiment across low resource languages (LRLs). Among them, the Random Forest model performed particularly well, capturing sentiment polarity and handling language-specific nuances effectively. Furthermore, Bidirectional Encoder Representations from Transformers (BERT), a Large Language Model (LLM), is applied to predict context-based sentiment with high accuracy, achieving 99% accuracy and 98% precision, outperforming other models. The BERT predictions were clarified using Explainable AI (XAI), improving transparency and fostering confidence in sentiment classification. Overall, findings demonstrate that the proposed lexicon and machine learning models significantly enhance translation and sentiment analysis for LRLs in South Africa and the DRC, laying a foundation for future AI models that support underrepresented languages, with applications across education, governance, and business in multilingual contexts.

Ara Yeroyan, Nikolay Karpov

In recent years, automatic speech recognition (ASR) systems have significantly improved, especially in languages with a vast amount of transcribed speech data. However, ASR systems tend to perform poorly for low-resource languages with fewer resources, such as minority and regional languages. This study introduces a novel pipeline designed to generate ASR training datasets from audiobooks, which typically feature a single transcript associated with hours-long audios. The common structure of these audiobooks poses a unique challenge due to the extensive length of audio segments, whereas optimal ASR training requires segments ranging from 4 to 15 seconds. To address this, we propose a method for effectively aligning audio with its corresponding text and segmenting it into lengths suitable for ASR training. Our approach simplifies data preparation for ASR systems in low-resource languages and demonstrates its application through a case study involving the Armenian language. Our method, which is "portable" to many low-resource languages, not only mitigates the issue of data scarcity but also enhances the performance of ASR models for underrepresented languages.

Mattia Setzu, Marta Marchiori Manerba, Pasquale Minervini et al.

Language Models (LMs) have been shown to inherit undesired biases that might hurt minorities and underrepresented groups if such systems were integrated into real-world applications without careful fairness auditing. This paper proposes FairBelief, an analytical approach to capture and assess beliefs, i.e., propositions that an LM may embed with different degrees of confidence and that covertly influence its predictions. With FairBelief, we leverage prompting to study the behavior of several state-of-the-art LMs across different previously neglected axes, such as model scale and likelihood, assessing predictions on a fairness dataset specifically designed to quantify LMs' outputs' hurtfulness. Finally, we conclude with an in-depth qualitative assessment of the beliefs emitted by the models. We apply FairBelief to English LMs, revealing that, although these architectures enable high performances on diverse natural language processing tasks, they show hurtful beliefs about specific genders. Interestingly, training procedure and dataset, model scale, and architecture induce beliefs of different degrees of hurtfulness.