Hasil untuk "Computational linguistics. Natural language processing"

Erfan Shayegani, Md. Abdullah Al Mamun, Yu Fu et al.

Large Language Models (LLMs) are swiftly advancing in architecture and capability, and as they integrate more deeply into complex systems, the urgency to scrutinize their security properties grows. This paper surveys research in the emerging interdisciplinary field of adversarial attacks on LLMs, a subfield of trustworthy ML, combining the perspectives of Natural Language Processing and Security. Prior work has shown that even safety-aligned LLMs (via instruction tuning and reinforcement learning through human feedback) can be susceptible to adversarial attacks, which exploit weaknesses and mislead AI systems, as evidenced by the prevalence of `jailbreak' attacks on models like ChatGPT and Bard. In this survey, we first provide an overview of large language models, describe their safety alignment, and categorize existing research based on various learning structures: textual-only attacks, multi-modal attacks, and additional attack methods specifically targeting complex systems, such as federated learning or multi-agent systems. We also offer comprehensive remarks on works that focus on the fundamental sources of vulnerabilities and potential defenses. To make this field more accessible to newcomers, we present a systematic review of existing works, a structured typology of adversarial attack concepts, and additional resources, including slides for presentations on related topics at the 62nd Annual Meeting of the Association for Computational Linguistics (ACL'24).

Yixing Lan, Xin Xu, Jiahang Liu et al.

ABSTRACT Reinforcement learning (RL) has been widely studied as an efficient class of machine learning methods for adaptive optimal control under uncertainties. In recent years, the applications of RL in optimised decision‐making and motion control of intelligent vehicles have received increasing attention. Due to the complex and dynamic operating environments of intelligent vehicles, it is necessary to improve the learning efficiency and generalisation ability of RL‐based decision and control algorithms under different conditions. This survey systematically examines the theoretical foundations, algorithmic advancements and practical challenges of applying RL to intelligent vehicle systems operating in complex and dynamic environments. The major algorithm frameworks of RL are first introduced, and the recent advances in RL‐based decision‐making and control of intelligent vehicles are overviewed. In addition to self‐learning decision and control approaches using state measurements, the developments of DRL methods for end‐to‐end driving control of intelligent vehicles are summarised. The open problems and directions for further research works are also discussed.

Min Zhu, Linchi Qu

Abstract To enhance the usefulness of regulatory monitoring in global maritime governance, the International Maritime Organization (IMO) has required member state audits based on the IMO Instruments Implementation Code (III Code). Still, the original manual classification of audit findings to regulatory clauses remains resource-intensive and subject to confusion arising from semantic ambiguity and a variety of textual sources. To assist with and automate the classification of textual audit findings into categories of regulatory clauses, this research offers a BERT language representation model. A comprehensive dataset of 961 findings were collected from the IMO Comprehensive Audit Summary Report that ultimately constitute more than 40 categories of non-conformance. The classification model described here achieved an overall classification accuracy of 72.0% and a macro F1 score of 0.69, which is superior to the appropriate conventional baselines, including TF-IDF + logistic regression, and an additional Bi-LSTM classification model. Other studies on the dataset provide some evidence for the effectiveness of cross-lingual pretraining (MLM or TLM), layer-wise semantic representation analysis and simulation of audit scenario data. Based on visualizing the behavioral responses of the audit findings, the relationship between asset levels, substitution strategies, and default monetary thresholds offered an original mode of interpretation of compliance agents.

I. Skrynnikova

In recent years, numerous studies have pointed to the ability of artificial intelligence (AI) to generate and analyze expressions of natural language. However, the question of whether AI is capable of actually interpreting human language, rather than imitating its understanding, remains open. Metaphors, being an integral part of human language, as both a common figure of speech and the predominant cognitive mechanism of human reasoning, pose a considerable challenge to AI systems. Based on an overview of the existing studies findings in computational linguistics and related fields, the paper identifies a number of problems associated with the interpretation of non-literal expressions of language by large language models (LLM). It reveals that there is still no clear understanding of the methods for training language models to automatically recognize and interpret metaphors that would bring it closer to the level of human “interpretive competencies”. The purpose of the study is to identify possible reasons that hinder the understanding of figurative language by artificial systems and to outline possible directions for solving this problem. The study suggests that the main barriers to AI’s human-like interpretation of figurative natural language are the absence of a physical body, the inability to reason by analogy and make inferences based on common sense, the latter being both the result and the cognitive process in extracting and processing information. The author concludes that further improvement of the AI systems creative skills should be at the top of the research agenda in the coming years.

Sophie McBride, Aitor Garcés-Manzanera

This paper explores the potential of JASP (Jeffreys’s Amazing Statistics Program, https://jasp-stats.org/) as a robust statistical tool in advancing Second Language Acquisition (SLA) research, with a specific emphasis on its application within the domain of L2 writing. Second language writing proficiency is a complex and multifaceted skill, demanding rigorous empirical investigation to uncover nuanced patterns and insights. JASP, known for its user-friendly interface and advanced statistical capabilities, emerges as a promising instrument for researchers seeking to unravel the intricacies of L2 writing development. The paper begins by providing an overview of the features embedded in JASP and continues to discuss some of the extant research within the field of SLA that implements JASP as a data analysis tool. Follows is a detailed description of the use of JASP in two L2 writing papers, in which the data analysis decisions are discussed. Furthermore, the discussion delves into the practical implications of utilizing JASP in L2 writing research, including its ability to accommodate small sample sizes, handle complex interactions, and facilitate transparent and reproducible analyses. The paper concludes by advocating for the widespread adoption of JASP in SLA research, positing that its integration holds the promise of advancing our understanding of the intricacies of L2 writing development and contributing to the refinement of pedagogical approaches in second language education.

Catia Cucchiarini, Helmer Strik

R. Willems, S. Frank, Annabel D. Nijhof et al.

Sayouba OUEDRAOGO & Lallé SOMMA

Résumé : Cette recherche s’inscrit dans le cadre des représentations sociolinguistiques. Elle vise à appréhender les perceptions des acteurs du système éducatif formel notamment les enseignants de français des lycées et collèges sur la dynamique de la langue française. Pour ce faire, nous avons mené des investigations à travers deux établissements d’enseignement post-primaires et secondaires de la ville de Ouagadougou afin de recueillir les données sur les représentations à l’égard du français. L’analyse et l’interprétation des données d’enquête nous ont permis de comprendre qu’une frange importante des enquêtés expriment des attitudes positives vis-à-vis du français. Ces opinions favorables sont motivées par les fonctions qu’assume cette langue au Burkina Faso. Mots-clés : représentation sociolinguistique, dynamique langagière, perception.

Syifa Aulia Khairunnisa

This research’s objective is to find the comparison of two television series, Wednesday (2022) and The Chilling Adventures of Sabrina (2018) of their setting in Gothic element using the theory of Fred Botting. Based on Botting’s theory, the setting in Gothic fiction was divided into two types, natural sublime and synthetic sublime. This research answered the question of what Gothic’s setting in the television series Wednesday (2022) and The Chilling Adventure of Sabrina (2018) and the comparison between the two television series regarding the Gothic’s setting. This research’s objective requires a deep understanding of the topic, so the qualitative descriptive method is applied in this research. Based on this reseach, it was found that there are nine Gothic setting in Wednesday (2022) and six in The Chilling Adventures of Sabrina (2018).  On that note, four similarities and seven differences was also found regarding the Gothic setting between the two television series. Based on the analysis, Wednesday (2022) has more Gothic setting compared to The Chilling Adventures of Sabrina (2018) both in natural and synthetic sublime, with with one more data on natural sublime and four more data on synthetic sublime.

A. Cybulska, P. Vossen

Elena Cabrio, D. Croce, Lucia C. Passaro et al.

Chenchen Ding, Vichet Chea, Masao Utiyama et al.

Shohini Bhattasali, P. Resnik

Context guides comprehenders’ expectations during language processing, and information-theoretic surprisal is commonly used as an index of cognitive processing effort. However, prior work using surprisal has considered only within-sentence context, using n-grams, neural language models, or syntactic structure as conditioning context. In this paper, we extend the surprisal approach to use broader topical context, investigating the influence of local and topical context on processing via an analysis of fMRI time courses collected during naturalistic listening. Lexical surprisal calculated from ngram and LSTM language models is used to capture effects of local context; to capture the effects of broader context a new metric based on topic models, topical surprisal, is introduced. We identify distinct patterns of neural activation for lexical surprisal and topical sur-prisal. These differing neuro-anatomical correlates suggest that local and broad contextual cues during sentence processing recruit different brain regions and that those regions of the language network functionally contribute to processing different dimensions of contextual information during comprehension. More generally, our approach adds to a growing literature using methods from computational linguistics to operationalize and test hypotheses about neuro-cognitive mechanisms in sentence processing.

Chaoxu Mu, Jiangwen Peng, Yufei Tang

Abstract A generalized policy‐iteration‐based solution to a class of discrete‐time multi‐player non‐zero‐sum games concerning the control constraints was proposed. Based on initial admissible control policies, the iterative value function of each player converges to the optimum approximately, which is structured by the iterative control policies satisfying the Nash equilibrium. Afterwards, the stability analysis is shown to illustrate that the iterative control policies can stabilize the system and minimize the performance index function of each player. Meanwhile, neural networks are implemented to approximate the iterative control policies and value functions with the impact of control constraints. Finally, two numerical simulations of the discrete‐time two‐player non‐zero‐sum games for linear and non‐linear systems are shown to illustrate the effectiveness of the proposed scheme.

Robert E. Mercer

Ted Pedersen

Juan Luis Gastaldi

The present paper intends to draw the conception of language implied in the technique of word embeddings that supported the recent development of deep neural network models in computational linguistics. After a preliminary presentation of the basic functioning of elementary artificial neural networks, we introduce the motivations and capabilities of word embeddings through one of its pioneering models, word2vec. To assess the remarkable results of the latter, we inspect the nature of its underlying mechanisms, which have been characterized as the implicit factorization of a word-context matrix. We then discuss the ordinary association of the “distributional hypothesis” with a “use theory of meaning,” often justifying the theoretical basis of word embeddings, and contrast them to the theory of meaning stemming from those mechanisms through the lens of matrix models (such as vector space models and distributional semantic models). Finally, we trace back the principles of their possible consistency through Harris’s original distributionalism up to the structuralist conception of language of Saussure and Hjelmslev. Other than giving access to the technical literature and state of the art in the field of natural language processing to non-specialist readers, the paper seeks to reveal the conceptual and philosophical stakes involved in the recent application of new neural network techniques to the computational treatment of language.

Mary Ellen Foster

In the increasingly popular and diverse research area of social robotics, the primary goal is to develop robot agents that exhibit socially intelligent behaviour while interacting in a face-to-face context with human partners. An important aspect of face-to-face social conversation is fluent, flexible linguistic interaction; face-to-face dialogue is both the basic form of human communication and the richest and most flexible, combining unrestricted verbal expression with meaningful non-verbal acts such as gestures and facial displays, along with instantaneous, continuous collaboration between the speaker and the listener. In practice, however, most developers of social robots tend not to use the full possibilities of the unrestricted verbal expression afforded by face-to-face conversation; instead, they generally tend to employ relatively simplistic processes for choosing the words for their robots to say. This contrasts with the work carried out Natural Language Generation (NLG), the field of computational linguistics devoted to the automated production of high-quality linguistic content; while this research area is also an active one, in general most effort in NLG is focused on producing high-quality written text. This article summarizes the state of the art in the two individual research areas of social robotics and natural language generation. It then discusses the reasons why so few current social robots make use of more sophisticated generation techniques. Finally, an approach is proposed to bringing some aspects of NLG into social robotics, concentrating on techniques and tools that are most appropriate to the needs of socially interactive robots. This article is part of the theme issue ‘From social brains to social robots: applying neurocognitive insights to human–robot interaction’.

D. Suryanarayana, Prathyusha Kanakam, S. M. Hussain et al.

Rubab Tabassum

Iftikar Jalib draws on Wittgenstein for the theoretical framework of<br />modern poetry. And language remains the main site of contestation. The primary objective in Jalib is to create linguistic structures which suit the demands of modern poetry. Human alienation, disenchantment with modern human conditions and the oppression of a consumerist culture are the major thematic concerns in his poetry. And he argues that the traditional linguistic structures are incapacitated to accommodate the complexity of contemporary human experiences. New forms of linguistic structures need to emerge to produce, in the words of T.S.Eliot, the objective correlative for human sufferings. Jalib tends to create the objective correlative in the forms mediated through his peculiar complex linguistic structures.