Comparison between parameter-efficient techniques and full fine-tuning: A case study on multilingual news article classification

• URL: http://arxiv.org/abs/2308.07282v2
• Date: Mon, 8 Apr 2024 13:01:17 GMT
• Title: Comparison between parameter-efficient techniques and full fine-tuning: A case study on multilingual news article classification
• Authors: Olesya Razuvayevskaya, Ben Wu, Joao A. Leite, Freddy Heppell, Ivan Srba, Carolina Scarton, Kalina Bontcheva, Xingyi Song,
• Abstract summary: Adapters and Low-Rank Adaptation (LoRA) are parameter-efficient fine-tuning techniques designed to make the training of language models more efficient. Previous results demonstrated that these methods can even improve performance on some classification tasks. This paper investigates how these techniques influence the classification performance and computation costs compared to full fine-tuning.
• Score: 4.498100922387482
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Adapters and Low-Rank Adaptation (LoRA) are parameter-efficient fine-tuning techniques designed to make the training of language models more efficient. Previous results demonstrated that these methods can even improve performance on some classification tasks. This paper complements the existing research by investigating how these techniques influence the classification performance and computation costs compared to full fine-tuning when applied to multilingual text classification tasks (genre, framing, and persuasion techniques detection; with different input lengths, number of predicted classes and classification difficulty), some of which have limited training data. In addition, we conduct in-depth analyses of their efficacy across different training scenarios (training on the original multilingual data; on the translations into English; and on a subset of English-only data) and different languages. Our findings provide valuable insights into the applicability of the parameter-efficient fine-tuning techniques, particularly to complex multilingual and multilabel classification tasks.

Related papers

• Language Models for Text Classification: Is In-Context Learning Enough? [54.869097980761595]
  Recent foundational language models have shown state-of-the-art performance in many NLP tasks in zero- and few-shot settings. An advantage of these models over more standard approaches is the ability to understand instructions written in natural language (prompts) This makes them suitable for addressing text classification problems for domains with limited amounts of annotated instances.
  arXiv  Detail & Related papers  (2024-03-26T12:47:39Z)
• Hierarchical Classification of Transversal Skills in Job Ads Based on Sentence Embeddings [0.0]
  This paper aims to identify correlations between job ad requirements and skill sets using a deep learning model. The approach involves data collection, preprocessing, and labeling using ESCO (European Skills, Competences, and Occupations) taxonomy.
  arXiv  Detail & Related papers  (2024-01-10T11:07:32Z)
• Comparative Analysis of Multilingual Text Classification & Identification through Deep Learning and Embedding Visualization [0.0]
  The study employs LangDetect, LangId, FastText, and Sentence Transformer on a dataset encompassing 17 languages. The FastText multi-layer perceptron model achieved remarkable accuracy, precision, recall, and F1 score, outperforming the Sentence Transformer model.
  arXiv  Detail & Related papers  (2023-12-06T12:03:27Z)
• T3L: Translate-and-Test Transfer Learning for Cross-Lingual Text Classification [50.675552118811]
  Cross-lingual text classification is typically built on large-scale, multilingual language models (LMs) pretrained on a variety of languages of interest. We propose revisiting the classic "translate-and-test" pipeline to neatly separate the translation and classification stages.
  arXiv  Detail & Related papers  (2023-06-08T07:33:22Z)
• Beyond Contrastive Learning: A Variational Generative Model for Multilingual Retrieval [109.62363167257664]
  We propose a generative model for learning multilingual text embeddings. Our model operates on parallel data in $N$ languages. We evaluate this method on a suite of tasks including semantic similarity, bitext mining, and cross-lingual question retrieval.
  arXiv  Detail & Related papers  (2022-12-21T02:41:40Z)
• Sample Efficient Approaches for Idiomaticity Detection [6.481818246474555]
  This work explores sample efficient methods of idiomaticity detection. In particular, we study the impact of Pattern Exploit Training (PET), a few-shot method of classification, and BERTRAM, an efficient method of creating contextual embeddings. Our experiments show that whilePET improves performance on English, they are much less effective on Portuguese and Galician, leading to an overall performance about on par with vanilla mBERT.
  arXiv  Detail & Related papers  (2022-05-23T13:46:35Z)
• Exploring Dimensionality Reduction Techniques in Multilingual Transformers [64.78260098263489]
  This paper gives a comprehensive account of the impact of dimensional reduction techniques on the performance of state-of-the-art multilingual Siamese Transformers. It shows that it is possible to achieve an average reduction in the number of dimensions of $91.58% pm 2.59%$ and $54.65% pm 32.20%$, respectively.
  arXiv  Detail & Related papers  (2022-04-18T17:20:55Z)
• Probing Structured Pruning on Multilingual Pre-trained Models: Settings, Algorithms, and Efficiency [62.0887259003594]
  This work investigates three aspects of structured pruning on multilingual pre-trained language models: settings, algorithms, and efficiency. Experiments on nine downstream tasks show several counter-intuitive phenomena. We present Dynamic Sparsification, a simple approach that allows training the model once and adapting to different model sizes at inference.
  arXiv  Detail & Related papers  (2022-04-06T06:29:52Z)
• Cross-lingual Text Classification with Heterogeneous Graph Neural Network [2.6936806968297913]
  Cross-lingual text classification aims at training a classifier on the source language and transferring the knowledge to target languages. Recent multilingual pretrained language models (mPLM) achieve impressive results in cross-lingual classification tasks. We propose a simple yet effective method to incorporate heterogeneous information within and across languages for cross-lingual text classification.
  arXiv  Detail & Related papers  (2021-05-24T12:45:42Z)
• Gradient Vaccine: Investigating and Improving Multi-task Optimization in Massively Multilingual Models [63.92643612630657]
  This paper attempts to peek into the black-box of multilingual optimization through the lens of loss function geometry. We find that gradient similarity measured along the optimization trajectory is an important signal, which correlates well with language proximity. We derive a simple and scalable optimization procedure, named Gradient Vaccine, which encourages more geometrically aligned parameter updates for close tasks.
  arXiv  Detail & Related papers  (2020-10-12T17:26:34Z)

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.