Hasil untuk "Greek philology and language"

Klaus-Dietrich Fischer

Koena Ronny Mabokela, Tim Schlippe, Mpho Raborife et al.

Sentiment analysis is a helpful task to automatically analyse opinions and emotions on various topics in areas such as AI for Social Good, AI in Education or marketing. While many of the sentiment analysis systems are developed for English, many African languages are classified as low-resource languages due to the lack of digital language resources like text labelled with corresponding sentiment classes. One reason for that is that manually labelling text data is time-consuming and expensive. Consequently, automatic and rapid processes are needed to reduce the manual effort as much as possible making the labelling process as efficient as possible. In this paper, we present and analyze an automatic language-independent sentiment labelling method that leverages information from sentiment-bearing emojis and words. Our experiments are conducted with tweets in the languages English, Sepedi and Setswana from SAfriSenti, a multilingual sentiment corpus for South African languages. We show that our sentiment labelling approach is able to label the English tweets with an accuracy of 66%, the Sepedi tweets with 69%, and the Setswana tweets with 63%, so that on average only 34% of the automatically generated labels remain to be corrected.

Monika Miazek-Męczyńska

The article contains a translation into Polish and an analysis of Ovid’s elegy Amores II 12, which deals with the theme of the similarity between love and war — a recurring motif in his oeuvre. The poet finds justification for his own romantic conquests in tradition, as he refers to a number of legendary kidnappings of women that resulted in wars. With typical self-irony, however, he emphasizes that his own victories are more praiseworthy than those won by mythical heroes, as his triumphs were individual and bloodless.

Michail I. Marinis

Since 1940, numerous eff orts have been made to either verify or refute the hypothesis of a rhythm typology, yet no defi nitive conclusions have been reached. In this paper, I discuss the limitations of the reliability of data collection and processing methods, as well as the indices that dominate the attempts to measure the phenomenon, highlighting the obstacles to creating a rhythm typology. To highlight the issues under discussion, I conduct a test application of the frameworks from international literature on two varieties of the Greek language, the Amaliada variety and Cypriot Greek, based on the analysis of 192 intonational phrases, which were systematically and randomly selected from recordings of unscripted natural speech by two female speakers for each linguistic system. The analysis demonstrates such variability among speakers of the same dialect that it calls into question the validity of the rhythm measurement practices used to date. I propose the key pillars upon which rhythm research should be based in order to draw reliable conclusions and obtain cross-linguistically and inter-study comparable results, aiming to reach a defi nitive confirmation or refutation of a rhythm typology.

Christiane Schulz

Candida M. Greco, Lucio La Cava, Andrea Tagarelli

Verbs form the backbone of language, providing the structure and meaning to sentences. Yet, their intricate semantic nuances pose a longstanding challenge. Understanding verb relations through the concept of lexical entailment is crucial for comprehending sentence meanings and grasping verb dynamics. This work investigates the capabilities of eight Large Language Models in recognizing lexical entailment relations among verbs through differently devised prompting strategies and zero-/few-shot settings over verb pairs from two lexical databases, namely WordNet and HyperLex. Our findings unveil that the models can tackle the lexical entailment recognition task with moderately good performance, although at varying degree of effectiveness and under different conditions. Also, utilizing few-shot prompting can enhance the models' performance. However, perfectly solving the task arises as an unmet challenge for all examined LLMs, which raises an emergence for further research developments on this topic.

Vasileios Saketos, Despina-Athanasia Pantazi, Manolis Koubarakis

We develop four versions of GreekLegalRoBERTa, which are four large language models trained on Greek legal and nonlegal text. We show that our models surpass the performance of GreekLegalBERT, Greek- LegalBERT-v2, and GreekBERT in two tasks involving Greek legal documents: named entity recognition and multi-class legal topic classification. We view our work as a contribution to the study of domain-specific NLP tasks in low-resource languages, like Greek, using modern NLP techniques and methodologies.

Xudong Lu, Qi Liu, Yuhui Xu et al.

A pivotal advancement in the progress of large language models (LLMs) is the emergence of the Mixture-of-Experts (MoE) LLMs. Compared to traditional LLMs, MoE LLMs can achieve higher performance with fewer parameters, but it is still hard to deploy them due to their immense parameter sizes. Different from previous weight pruning methods that rely on specifically designed hardware, this paper mainly aims to enhance the deployment efficiency of MoE LLMs by introducing plug-and-play expert-level sparsification techniques. Specifically, we propose, for the first time to our best knowledge, post-training approaches for task-agnostic and task-specific expert pruning and skipping of MoE LLMs, tailored to improve deployment efficiency while maintaining model performance across a wide range of tasks. Extensive experiments show that our proposed methods can simultaneously reduce model sizes and increase the inference speed, while maintaining satisfactory performance. Data and code will be available at https://github.com/Lucky-Lance/Expert_Sparsity.

Yongchao Chen, Rujul Gandhi, Yang Zhang et al.

Temporal Logic (TL) can be used to rigorously specify complex high-level specification for systems in many engineering applications. The translation between natural language (NL) and TL has been under-explored due to the lack of dataset and generalizable model across different application domains. In this paper, we propose an accurate and generalizable transformation framework of English instructions from NL to TL, exploring the use of Large Language Models (LLMs) at multiple stages. Our contributions are twofold. First, we develop a framework to create a dataset of NL-TL pairs combining LLMs and human annotation. We publish a dataset with 28K NL-TL pairs. Then, we finetune T5 models on the lifted versions (i.e., the specific Atomic Propositions (AP) are hidden) of the NL and TL. The enhanced generalizability originates from two aspects: 1) Usage of lifted NL-TL characterizes common logical structures, without constraints of specific domains. 2) Application of LLMs in dataset creation largely enhances corpus richness. We test the generalization of trained models on five varied domains. To achieve full NL-TL transformation, we either combine the lifted model with AP recognition task or do the further finetuning on each specific domain. During the further finetuning, our model achieves higher accuracy (>95%) using only <10% training data, compared with the baseline sequence to sequence (Seq2Seq) model.

Ishita Dasgupta, Christine Kaeser-Chen, Kenneth Marino et al.

Reasoning in a complex and ambiguous environment is a key goal for Reinforcement Learning (RL) agents. While some sophisticated RL agents can successfully solve difficult tasks, they require a large amount of training data and often struggle to generalize to new unseen environments and new tasks. On the other hand, Large Scale Language Models (LSLMs) have exhibited strong reasoning ability and the ability to to adapt to new tasks through in-context learning. However, LSLMs do not inherently have the ability to interrogate or intervene on the environment. In this work, we investigate how to combine these complementary abilities in a single system consisting of three parts: a Planner, an Actor, and a Reporter. The Planner is a pre-trained language model that can issue commands to a simple embodied agent (the Actor), while the Reporter communicates with the Planner to inform its next command. We present a set of tasks that require reasoning, test this system's ability to generalize zero-shot and investigate failure cases, and demonstrate how components of this system can be trained with reinforcement-learning to improve performance.

Heinz-Jürgen Schulz-Koppe

Bhavya Bhavya, Jinjun Xiong, Chengxiang Zhai

We propose a novel application of prompting Pre-trained Language Models (PLMs) to generate analogies and study how to design effective prompts for two task settings: generating a source concept analogous to a given target concept (aka Analogous Concept Generation or ACG), and generating an explanation of the similarity between a given pair of target concept and source concept (aka Analogous Explanation Generation or AEG). We found that it is feasible to prompt InstructGPT to generate meaningful analogies and the best prompts tend to be precise imperative statements especially with a low temperature setting. We also systematically analyzed the sensitivity of the InstructGPT model to prompt design, temperature, and injected spelling errors, and found that the model is particularly sensitive to certain variations (e.g., questions vs. imperative statements). Further, we conducted human evaluation on 1.4k of the generated analogies and found that the quality of generations varies substantially by model size. The largest InstructGPT model can achieve human-level performance at generating meaningful analogies for a given target while there is still room for improvement on the AEG task.

Samuel Belkadi, Lifeng Han, Yuping Wu et al.

The practice of fine-tuning Pre-trained Language Models (PLMs) from general or domain-specific data to a specific task with limited resources, has gained popularity within the field of natural language processing (NLP). In this work, we re-visit this assumption and carry out an investigation in clinical NLP, specifically Named Entity Recognition on drugs and their related attributes. We compare Transformer models that are trained from scratch to fine-tuned BERT-based LLMs namely BERT, BioBERT, and ClinicalBERT. Furthermore, we examine the impact of an additional CRF layer on such models to encourage contextual learning. We use n2c2-2018 shared task data for model development and evaluations. The experimental outcomes show that 1) CRF layers improved all language models; 2) referring to BIO-strict span level evaluation using macro-average F1 score, although the fine-tuned LLMs achieved 0.83+ scores, the TransformerCRF model trained from scratch achieved 0.78+, demonstrating comparable performances with much lower cost - e.g. with 39.80\% less training parameters; 3) referring to BIO-strict span-level evaluation using weighted-average F1 score, ClinicalBERT-CRF, BERT-CRF, and TransformerCRF exhibited lower score differences, with 97.59\%/97.44\%/96.84\% respectively. 4) applying efficient training by down-sampling for better data distribution further reduced the training cost and need for data, while maintaining similar scores - i.e. around 0.02 points lower compared to using the full dataset. Our models will be hosted at \url{https://github.com/HECTA-UoM/TransformerCRF}

Ankur Bapna, Isaac Caswell, Julia Kreutzer et al.

In this paper we share findings from our effort to build practical machine translation (MT) systems capable of translating across over one thousand languages. We describe results in three research domains: (i) Building clean, web-mined datasets for 1500+ languages by leveraging semi-supervised pre-training for language identification and developing data-driven filtering techniques; (ii) Developing practical MT models for under-served languages by leveraging massively multilingual models trained with supervised parallel data for over 100 high-resource languages and monolingual datasets for an additional 1000+ languages; and (iii) Studying the limitations of evaluation metrics for these languages and conducting qualitative analysis of the outputs from our MT models, highlighting several frequent error modes of these types of models. We hope that our work provides useful insights to practitioners working towards building MT systems for currently understudied languages, and highlights research directions that can complement the weaknesses of massively multilingual models in data-sparse settings.

Miloš Tomasco, Markéta Kulhánková

De Martinis, Livia

La stele conserva cinque provvedimenti per Eraclide di Salamina di Cipro, che nel 330-329 fornì ad Atene 3.000 medimni di grano al prezzo vantaggioso di 5 dracme e nel 328-327 donò alla città 3.000 dracme per l’acquisto di cereali. L’insieme di questi decreti è utile per datare due delle principali crisi alimentari che l’Attica affrontò nella seconda metà del IV secolo; arricchisce la nostra conoscenza delle relazioni tra Atene e Salamina di Cipro; permette di approfondire l’iter deliberativo della democrazia ateniese di IV secolo; contribuisce ad argomentare l’esistenza ad Atene di un archivio pubblico per la conservazione dei documenti.

Matina Paraskeva

Antreas Kordopatis, the main character in Thanasis Valtinos' novel Synaxari Antrea Kordopati, Vivlio Proto: Ameriki (1972 [1964]), emerged as an eminent literary figure in Greek post-war literature, especially due to his oscillation between fiction and reality. The aim of this paper is to examine the construction of Kordopatis' character as well as the methods and literary devices that are used for it. Valtinos' blurring of the lines between the real elements of Kordopatis' story and the fictional ones manages to achieve a twofold effect; firstly, he constructs a fluid literary persona that is constantly transforming to conquer its dream, and secondly, he subverts the reader's reception.

Mithun Das, Somnath Banerjee, Punyajoy Saha

Online hatred is a growing concern on many social media platforms. To address this issue, different social media platforms have introduced moderation policies for such content. They also employ moderators who can check the posts violating moderation policies and take appropriate action. Academicians in the abusive language research domain also perform various studies to detect such content better. Although there is extensive research in abusive language detection in English, there is a lacuna in abusive language detection in low resource languages like Hindi, Urdu etc. In this FIRE 2021 shared task - "HASOC- Abusive and Threatening language detection in Urdu" the organizers propose an abusive language detection dataset in Urdu along with threatening language detection. In this paper, we explored several machine learning models such as XGboost, LGBM, m-BERT based models for abusive and threatening content detection in Urdu based on the shared task. We observed the Transformer model specifically trained on abusive language dataset in Arabic helps in getting the best performance. Our model came First for both abusive and threatening content detection with an F1scoreof 0.88 and 0.54, respectively.

Ross Gruetzemacher, David Paradice

AI is widely thought to be poised to transform business, yet current perceptions of the scope of this transformation may be myopic. Recent progress in natural language processing involving transformer language models (TLMs) offers a potential avenue for AI-driven business and societal transformation that is beyond the scope of what most currently foresee. We review this recent progress as well as recent literature utilizing text mining in top IS journals to develop an outline for how future IS research can benefit from these new techniques. Our review of existing IS literature reveals that suboptimal text mining techniques are prevalent and that the more advanced TLMs could be applied to enhance and increase IS research involving text data, and to enable new IS research topics, thus creating more value for the research community. This is possible because these techniques make it easier to develop very powerful custom systems and their performance is superior to existing methods for a wide range of tasks and applications. Further, multilingual language models make possible higher quality text analytics for research in multiple languages. We also identify new avenues for IS research, like language user interfaces, that may offer even greater potential for future IS research.

Angelina McMillan-Major, Salomey Osei, Juan Diego Rodriguez et al.

Developing documentation guidelines and easy-to-use templates for datasets and models is a challenging task, especially given the variety of backgrounds, skills, and incentives of the people involved in the building of natural language processing (NLP) tools. Nevertheless, the adoption of standard documentation practices across the field of NLP promotes more accessible and detailed descriptions of NLP datasets and models, while supporting researchers and developers in reflecting on their work. To help with the standardization of documentation, we present two case studies of efforts that aim to develop reusable documentation templates -- the HuggingFace data card, a general purpose card for datasets in NLP, and the GEM benchmark data and model cards with a focus on natural language generation. We describe our process for developing these templates, including the identification of relevant stakeholder groups, the definition of a set of guiding principles, the use of existing templates as our foundation, and iterative revisions based on feedback.