ABSTRACT Humans can learn complex and dexterous manipulation tasks by observing videos, imitating and exploring. Multiple end‐effectors manipulation of free micron‐sized deformable cells is one of the challenging tasks in robotic micromanipulation. We propose an imitation‐enhanced reinforcement learning method inspired by the human learning process that enables robots to learn cell micromanipulation skills from videos. Firstly, for the microscopic robot micromanipulation videos, a multi‐task observation (MTO) network is designed to identify the two end‐effectors and the manipulated objects to obtain the spatiotemporal trajectories. The spatiotemporal constraints of the robot's actions are obtained by the task‐parameterised hidden Markov model (THMM). To simultaneously address the safety and dexterity of robot micromanipulation, an imitation learning optimisation‐based soft actor‐critic (ILOSAC) algorithm is proposed in which the robot can perform skill learning by demonstration and exploration. The proposed method is capable of performing complex cell manipulation tasks in a realistic physical environment. Experiments indicated that compared with current methods and manual remote manipulation, the proposed framework achieved a shorter operation time and less deformation of cells, which is expected to facilitate the development of robot skill learning.
Computational linguistics. Natural language processing, Computer software
Résumé : Le premier sens de la théologie est de parler de Dieu. D’autant plus qu’il s’est révélé Lui-même en vue de nous parler. Dans cette optique, pour nous parler, Il a utilisé deux vecteurs principaux : l’oralité et la scribalité. Cette dernière qui, autrement appelée, l’écriture, a joué un rôle prépondérant pour la transmission de la pensée de Dieu à l’humanité. A cet effet, si nous considérons que l’écriture et la lecture sont les paradigmes de la bibliologie, nous devons, à ce titre, reconnaitre que la bibliologie et la théologie sont intimement liées. C’est ainsi que l’heuristique menée par Bob Bobutaka, quant à ce sujet, l’a conduit à la construction du schème appelé « bibliologie théologique ».
Mots-clés : Bibliologie, théologie, schème, Construction, Bobutaka.
Arts in general, Computational linguistics. Natural language processing
This research reveals international legal discourse main peculiarities. The issue discussed includes international legal discourse distinction from related types of discourse – legal and diplomatic ones. International legal discourse was formed on the overlap of diplomatic and legal discourses. Thus, international legal discourse in English has such significant peculiarities as assimilation, institutionalization, prolixity, ambiguity, use of Latinisms and French loanwords, impersonalization, excessive solemnity and politeness, use of words associated with legal discourse including archaisms as well as legal terms, etc. Therefore, international legal discourse is an autonomous type of discourse that gradually changes and reveals perspectives for the future research.
Discourse analysis, Computational linguistics. Natural language processing
Md. Abdur Rahman, Nur Mohammad Fahad, Mohaimenul Azam Khan Raiaan
et al.
Abstract Skin cancer, a severe health threat, can spread rapidly if undetected. Therefore, early detection can lead to an advanced and efficient diagnosis, thus reducing mortality. Unsupervised classification techniques analyse extensive skin image datasets, identifying patterns and anomalies without prior labelling, facilitating early detection and effective diagnosis and potentially saving lives. In this study, the authors aim to explore the potential of unsupervised learning methods in classifying different types of skin lesions in dermatoscopic images. The authors aim to bridge the gap in dermatological research by introducing innovative techniques that enhance image quality and improve feature extraction. To achieve this, enhanced super‐resolution generative adversarial networks (ESRGAN) was fine‐tuned to strengthen the resolution of skin lesion images, making critical features more visible. The authors extracted histogram features to capture essential colour characteristics and used the Davies–Bouldin index and silhouette score to determine optimal clusters. Fine‐tuned k‐means clustering with Euclidean distance in the histogram feature space achieved 87.77% and 90.5% test accuracies on the ISIC2019 and HAM10000 datasets, respectively. The unsupervised approach effectively categorises skin lesions, indicating that unsupervised learning can significantly advance dermatology by enabling early detection and classification without extensive manual annotation.
Computational linguistics. Natural language processing, Computer software
We introduce CSAR, an algorithm for inducing morphemes from emergent language corpora of parallel utterances and meanings. It is a greedy algorithm that (1) weights morphemes based on mutual information between forms and meanings, (2) selects the highest-weighted pair, (3) removes it from the corpus, and (4) repeats the process to induce further morphemes (i.e., Count, Select, Ablate, Repeat). The effectiveness of CSAR is first validated on procedurally generated datasets and compared against baselines for related tasks. Second, we validate CSAR's performance on human language data to show that the algorithm makes reasonable predictions in adjacent domains. Finally, we analyze a handful of emergent languages, quantifying linguistic characteristics like degree of synonymy and polysemy.
Chain-of-Thought (CoT) prompting is a widely used method to improve the reasoning capability of Large Language Models (LLMs). More recently, CoT has been leveraged in Knowledge Distillation (KD) to transfer reasoning capability from a larger LLM to a smaller one. This paper examines the role of CoT in distilling the reasoning capability from larger LLMs to smaller LLMs using white-box KD, analysing its effectiveness in improving the performance of the distilled models for various natural language reasoning and understanding tasks. We conduct white-box KD experiments using LLMs from the Qwen and Llama2 families, employing CoT data from the CoT-Collection dataset. The distilled models are then evaluated on natural language reasoning and understanding tasks from the BIG-Bench-Hard (BBH) benchmark, which presents complex challenges for smaller LLMs. Experimental results demonstrate the role of CoT in improving white-box KD effectiveness, enabling the distilled models to achieve better average performance in natural language reasoning and understanding tasks from BBH.
Language Models (LMs) have revolutionized natural language processing, enabling high-quality text generation through prompting and in-context learning. However, models often struggle with long-context summarization due to positional biases, leading to suboptimal extraction of critical information. There are techniques to improve this with fine-tuning, pipelining, or using complex techniques, which have their own challenges. To solve these challenges, we propose QA-prompting - a simple prompting method for summarization that utilizes question-answering as an intermediate step prior to summary generation. Our method extracts key information and enriches the context of text to mitigate positional biases and improve summarization in a single LM call per task without requiring fine-tuning or pipelining. Experiments on multiple datasets belonging to different domains using ten state-of-the-art pre-trained models demonstrate that QA-prompting outperforms baseline and other state-of-the-art methods, achieving up to 29% improvement in ROUGE scores. This provides an effective and scalable solution for summarization and highlights the importance of domain-specific question selection for optimal performance.
Résumé : La conceptualité configurative du prénom Khaled dans « Mémoires de la Chair » de l’écrivaine Algérienne Ahlam Mostaghanemi s’impose, ici, comme une représentation singulière, qui déploie son propre regard critique et croise les champs de plusieurs disciplines telles que la sociologie et la psychologie sociale. Son processus prend corps lorsque le personnage est placé constamment en position d’observateur qui perçoit une vérité au-delà des limites de la vie individuelle.
Mots-clés : Prénom, Le moi, Conceptualité, Configurativité, Mouvance
Arts in general, Computational linguistics. Natural language processing
Hallucination, the generation of factually incorrect content, is a growing challenge in Large Language Models (LLMs). Existing detection and mitigation methods are often isolated and insufficient for domain-specific needs, lacking a standardized pipeline. This paper introduces THaMES (Tool for Hallucination Mitigations and EvaluationS), an integrated framework and library addressing this gap. THaMES offers an end-to-end solution for evaluating and mitigating hallucinations in LLMs, featuring automated test set generation, multifaceted benchmarking, and adaptable mitigation strategies. It automates test set creation from any corpus, ensuring high data quality, diversity, and cost-efficiency through techniques like batch processing, weighted sampling, and counterfactual validation. THaMES assesses a model's ability to detect and reduce hallucinations across various tasks, including text generation and binary classification, applying optimal mitigation strategies like In-Context Learning (ICL), Retrieval Augmented Generation (RAG), and Parameter-Efficient Fine-tuning (PEFT). Evaluations of state-of-the-art LLMs using a knowledge base of academic papers, political news, and Wikipedia reveal that commercial models like GPT-4o benefit more from RAG than ICL, while open-weight models like Llama-3.1-8B-Instruct and Mistral-Nemo gain more from ICL. Additionally, PEFT significantly enhances the performance of Llama-3.1-8B-Instruct in both evaluation tasks.
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.
Computational approach to politeness is the task of automatically predicting and generating politeness in text. This is a pivotal task for conversational analysis, given the ubiquity and challenges of politeness in interactions. The computational approach to politeness has witnessed great interest from the conversational analysis community. This article is a compilation of past works in computational politeness in natural language processing. We view four milestones in the research so far, viz. supervised and weakly-supervised feature extraction to identify and induce politeness in a given text, incorporation of context beyond the target text, study of politeness across different social factors, and study the relationship between politeness and various sociolinguistic cues. In this article, we describe the datasets, approaches, trends, and issues in computational politeness research. We also discuss representative performance values and provide pointers to future works, as given in the prior works. In terms of resources to understand the state-of-the-art, this survey presents several valuable illustrations, most prominently, a table summarizing the past papers along different dimensions, such as the types of features, annotation techniques, and datasets used.
Sushma Anand Akoju, Robert Vacareanu, Haris Riaz
et al.
We introduce a synthetic dataset called Sentences Involving Complex Compositional Knowledge (SICCK) and a novel analysis that investigates the performance of Natural Language Inference (NLI) models to understand compositionality in logic. We produce 1,304 sentence pairs by modifying 15 examples from the SICK dataset (Marelli et al., 2014). To this end, we modify the original texts using a set of phrases - modifiers that correspond to universal quantifiers, existential quantifiers, negation, and other concept modifiers in Natural Logic (NL) (MacCartney, 2009). We use these phrases to modify the subject, verb, and object parts of the premise and hypothesis. Lastly, we annotate these modified texts with the corresponding entailment labels following NL rules. We conduct a preliminary verification of how well the change in the structural and semantic composition is captured by neural NLI models, in both zero-shot and fine-tuned scenarios. We found that the performance of NLI models under the zero-shot setting is poor, especially for modified sentences with negation and existential quantifiers. After fine-tuning this dataset, we observe that models continue to perform poorly over negation, existential and universal modifiers.
We present a grammar inference system that leverages linguistic knowledge recorded in the form of annotations in interlinear glossed text (IGT) and in a meta-grammar engineering system (the LinGO Grammar Matrix customization system) to automatically produce machine-readable HPSG grammars. Building on prior work to handle the inference of lexical classes, stems, affixes and position classes, and preliminary work on inferring case systems and word order, we introduce an integrated grammar inference system that covers a wide range of fundamental linguistic phenomena. System development was guided by 27 geneologically and geographically diverse languages, and we test the system's cross-linguistic generalizability on an additional 5 held-out languages, using datasets provided by field linguists. Our system out-performs three baseline systems in increasing coverage while limiting ambiguity and producing richer semantic representations, while also producing richer representations than previous work in grammar inference.
Computational linguistics. Natural language processing
Microaggressions are subtle manifestations of bias (Breitfeller et al. 2019). These demonstrations of bias can often be classified as a subset of abusive language. However, not much focus has been placed on the recognition of these instances. As a result, limited data is available on the topic, and only in English. Being able to detect microaggressions without the need for labeled data would be advantageous since it would allow content moderation also for languages lacking annotated data. In this study, we introduce an unsupervised method to detect microaggressions in natural language expressions. The algorithm relies on pre-trained word-embeddings, leveraging the bias encoded in the model in order to detect microaggressions in unseen textual instances. We test the method on a dataset of racial and gender-based microaggressions, reporting promising results. We further run the algorithm on out-of-domain unseen data with the purpose of bootstrapping corpora of microaggressions “in the wild”, perform a pilot experiment with prompt-based learning, and discuss the benefits and drawbacks of our proposed method.1
Social Sciences, Computational linguistics. Natural language processing
End-to-end sign language generation models do not accurately represent the prosody in sign language. A lack of temporal and spatial variations leads to poor-quality generated presentations that confuse human interpreters. In this paper, we aim to improve the prosody in generated sign languages by modeling intensification in a data-driven manner. We present different strategies grounded in linguistics of sign language that inform how intensity modifiers can be represented in gloss annotations. To employ our strategies, we first annotate a subset of the benchmark PHOENIX-14T, a German Sign Language dataset, with different levels of intensification. We then use a supervised intensity tagger to extend the annotated dataset and obtain labels for the remaining portion of it. This enhanced dataset is then used to train state-of-the-art transformer models for sign language generation. We find that our efforts in intensification modeling yield better results when evaluated with automatic metrics. Human evaluation also indicates a higher preference of the videos generated using our model.