Evaluating and Adapting Large Language Models to Represent Folktales in Low-Resource Languages

• URL: http://arxiv.org/abs/2411.05593v1
• Date: Fri, 08 Nov 2024 14:26:56 GMT
• Title: Evaluating and Adapting Large Language Models to Represent Folktales in Low-Resource Languages
• Authors: JA Meaney, Beatrice Alex, William Lamb,
• Abstract summary: Large language models (LLMs) claim to be able to represent low-resource langauges such as Irish and Gaelic. We present two classification tasks to explore how useful these representations are, and three adaptations to improve the performance of these models.
• Score: 3.1125246891252125
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Folktales are a rich resource of knowledge about the society and culture of a civilisation. Digital folklore research aims to use automated techniques to better understand these folktales, and it relies on abstract representations of the textual data. Although a number of large language models (LLMs) claim to be able to represent low-resource langauges such as Irish and Gaelic, we present two classification tasks to explore how useful these representations are, and three adaptations to improve the performance of these models. We find that adapting the models to work with longer sequences, and continuing pre-training on the domain of folktales improves classification performance, although these findings are tempered by the impressive performance of a baseline SVM with non-contextual features.

Related papers

• Overcoming Data Scarcity in Generative Language Modelling for Low-Resource Languages: A Systematic Review [0.7366405857677227]
  This paper focuses on strategies to address data scarcity in generative language modelling for low-resource languages (LRL)<n>We identify, categorise and evaluate technical approaches, including monolingual data augmentation, back-translation, multilingual training, and prompt engineering.<n>We conclude with recommendations for extending these methods to a wider range of LRLs and outline open challenges in building equitable generative language systems.
  arXiv  Detail & Related papers  (2025-05-07T16:04:45Z)
• Conversations in Galician: a Large Language Model for an Underrepresented Language [2.433983268807517]
  This paper introduces two novel resources designed to enhance Natural Language Processing (NLP) for the Galician language. We present a Galician adaptation of the Alpaca dataset, comprising 52,000 instructions and demonstrations. As a demonstration of the dataset utility, we fine-tuned LLaMA-7B to comprehend and respond in Galician, a language not originally supported by the model.
  arXiv  Detail & Related papers  (2023-11-07T08:52:28Z)
• Exploring Large Language Model for Graph Data Understanding in Online Job Recommendations [63.19448893196642]
  We present a novel framework that harnesses the rich contextual information and semantic representations provided by large language models to analyze behavior graphs. By leveraging this capability, our framework enables personalized and accurate job recommendations for individual users.
  arXiv  Detail & Related papers  (2023-07-10T11:29:41Z)
• Commonsense Knowledge Transfer for Pre-trained Language Models [83.01121484432801]
  We introduce commonsense knowledge transfer, a framework to transfer the commonsense knowledge stored in a neural commonsense knowledge model to a general-purpose pre-trained language model. It first exploits general texts to form queries for extracting commonsense knowledge from the neural commonsense knowledge model. It then refines the language model with two self-supervised objectives: commonsense mask infilling and commonsense relation prediction.
  arXiv  Detail & Related papers  (2023-06-04T15:44:51Z)
• Language Model Behavior: A Comprehensive Survey [5.663056267168211]
  We discuss over 250 recent studies of English language model behavior before task-specific fine-tuning. Despite dramatic increases in generated text quality as models scale to hundreds of billions of parameters, the models are still prone to unfactual responses, commonsense errors, memorized text, and social biases.
  arXiv  Detail & Related papers  (2023-03-20T23:54:26Z)
• Testing the Ability of Language Models to Interpret Figurative Language [69.59943454934799]
  Figurative and metaphorical language are commonplace in discourse. It remains an open question to what extent modern language models can interpret nonliteral phrases. We introduce Fig-QA, a Winograd-style nonliteral language understanding task.
  arXiv  Detail & Related papers  (2022-04-26T23:42:22Z)
• Specializing Multilingual Language Models: An Empirical Study [50.7526245872855]
  Contextualized word representations from pretrained multilingual language models have become the de facto standard for addressing natural language tasks. For languages rarely or never seen by these models, directly using such models often results in suboptimal representation or use of data.
  arXiv  Detail & Related papers  (2021-06-16T18:13:55Z)
• Sentiment analysis in tweets: an assessment study from classical to modern text representation models [59.107260266206445]
  Short texts published on Twitter have earned significant attention as a rich source of information. Their inherent characteristics, such as the informal, and noisy linguistic style, remain challenging to many natural language processing (NLP) tasks. This study fulfils an assessment of existing language models in distinguishing the sentiment expressed in tweets by using a rich collection of 22 datasets.
  arXiv  Detail & Related papers  (2021-05-29T21:05:28Z)
• Unsupervised Domain Adaptation of a Pretrained Cross-Lingual Language Model [58.27176041092891]
  Recent research indicates that pretraining cross-lingual language models on large-scale unlabeled texts yields significant performance improvements. We propose a novel unsupervised feature decomposition method that can automatically extract domain-specific features from the entangled pretrained cross-lingual representations. Our proposed model leverages mutual information estimation to decompose the representations computed by a cross-lingual model into domain-invariant and domain-specific parts.
  arXiv  Detail & Related papers  (2020-11-23T16:00:42Z)
• Linguistic Features for Readability Assessment [0.0]
  It is unknown whether augmenting deep learning models with linguistically motivated features would improve performance further. We find that, given sufficient training data, augmenting deep learning models with linguistically motivated features does not improve state-of-the-art performance. Our results provide preliminary evidence for the hypothesis that the state-of-the-art deep learning models represent linguistic features of the text related to readability.
  arXiv  Detail & Related papers  (2020-05-30T22:14:46Z)
• Adapting Deep Learning for Sentiment Classification of Code-Switched Informal Short Text [1.6752182911522517]
  We present a labeled dataset called MultiSenti for sentiment classification of code-switched informal short text. We propose a deep learning-based model for sentiment classification of code-switched informal short text.
  arXiv  Detail & Related papers  (2020-01-04T06:31:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.