Fine-Tuning Small Embeddings for Elevated Performance

• URL: http://arxiv.org/abs/2411.18099v1
• Date: Wed, 27 Nov 2024 07:25:07 GMT
• Title: Fine-Tuning Small Embeddings for Elevated Performance
• Abstract summary: This work has taken an incomplete BERT model with six attention heads pretrained on Nepali language and finetuned it on previously unseen data.<n>Results demonstrate that even though the oracle is better on average, finetuning the small embeddings drastically improves results compared to the original baseline.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Contextual Embeddings have yielded state-of-the-art results in various natural language processing tasks. However, these embeddings are constrained by models requiring large amounts of data and huge computing power. This is an issue for low-resource languages like Nepali as the amount of data available over the internet is not always sufficient for the models. This work has taken an incomplete BERT model with six attention heads pretrained on Nepali language and finetuned it on previously unseen data. The obtained results from intrinsic and extrinsic evaluations have been compared to the results drawn from the original model baseline and a complete BERT model pretrained on Nepali language as the oracle. The results demonstrate that even though the oracle is better on average, finetuning the small embeddings drastically improves results compared to the original baseline.

Related papers

• Benchmarking BERT-based Models for Sentence-level Topic Classification in Nepali Language [1.6474262142781433]
  This study benchmarks multilingual, Indic, Hindi, and Nepali BERT variants to evaluate their effectiveness in Nepali topic classification.<n>Ten pre-trained models, including mBERT, XLM-R, MuRIL, DevBERT, HindiBERT, IndicBERT, and NepBERTa, were fine-tuned and tested.<n>Indic models, particularly MuRIL-large, achieved the highest F1-score of 90.60%, outperforming multilingual and monolingual models.
  arXiv  Detail & Related papers  (2026-02-27T11:42:38Z)
• Pretraining Language Models to Ponder in Continuous Space [50.52734567589996]
  We introduce this pondering process into language models by repeatedly invoking the forward process within a single token generation step.<n>We show that the model can learn to ponder in this way through self-supervised learning, without any human annotations.
  arXiv  Detail & Related papers  (2025-05-27T03:47:33Z)
• Pre-training a Transformer-Based Generative Model Using a Small Sepedi Dataset [0.5530212768657544]
  We use the Sepedi monolingual (SepMono) dataset from several South African resources and the Sepedi radio news (SepNews) dataset from the radio news domain. Our results show that the non-occlusion models perform better compared to the occlusion-based models when measuring validation loss and perplexity.
  arXiv  Detail & Related papers  (2025-01-25T17:25:06Z)
• Can Perplexity Predict Fine-Tuning Performance? An Investigation of Tokenization Effects on Sequential Language Models for Nepali [0.0]
  The study of how subwording affects the understanding capacity of language models has been very few and only limited to a handful of languages. We used 6 different tokenization schemes to pretrain relatively small language models in Nepali and used the representations learned to finetune on several downstream tasks.
  arXiv  Detail & Related papers  (2024-04-28T05:26:12Z)
• 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)
• mFACE: Multilingual Summarization with Factual Consistency Evaluation [79.60172087719356]
  Abstractive summarization has enjoyed renewed interest in recent years, thanks to pre-trained language models and the availability of large-scale datasets. Despite promising results, current models still suffer from generating factually inconsistent summaries. We leverage factual consistency evaluation models to improve multilingual summarization.
  arXiv  Detail & Related papers  (2022-12-20T19:52:41Z)
• Falsesum: Generating Document-level NLI Examples for Recognizing Factual Inconsistency in Summarization [63.21819285337555]
  We show that NLI models can be effective for this task when the training data is augmented with high-quality task-oriented examples. We introduce Falsesum, a data generation pipeline leveraging a controllable text generation model to perturb human-annotated summaries. We show that models trained on a Falsesum-augmented NLI dataset improve the state-of-the-art performance across four benchmarks for detecting factual inconsistency in summarization.
  arXiv  Detail & Related papers  (2022-05-12T10:43:42Z)
• MoEBERT: from BERT to Mixture-of-Experts via Importance-Guided Adaptation [68.30497162547768]
  We propose MoEBERT, which uses a Mixture-of-Experts structure to increase model capacity and inference speed. We validate the efficiency and effectiveness of MoEBERT on natural language understanding and question answering tasks.
  arXiv  Detail & Related papers  (2022-04-15T23:19:37Z)
• Finding the Winning Ticket of BERT for Binary Text Classification via Adaptive Layer Truncation before Fine-tuning [7.797987384189306]
  We construct a series of BERT-based models with different size and compare their predictions on 8 binary classification tasks. The results show there truly exist smaller sub-networks performing better than the full model.
  arXiv  Detail & Related papers  (2021-11-22T02:22:47Z)
• Understanding by Understanding Not: Modeling Negation in Language Models [81.21351681735973]
  Negation is a core construction in natural language. We propose to augment the language modeling objective with an unlikelihood objective that is based on negated generic sentences. We reduce the mean top1 error rate to 4% on the negated LAMA dataset.
  arXiv  Detail & Related papers  (2021-05-07T21:58:35Z)
• Comparison of Interactive Knowledge Base Spelling Correction Models for Low-Resource Languages [81.90356787324481]
  Spelling normalization for low resource languages is a challenging task because the patterns are hard to predict. This work shows a comparison of a neural model and character language models with varying amounts on target language data. Our usage scenario is interactive correction with nearly zero amounts of training examples, improving models as more data is collected.
  arXiv  Detail & Related papers  (2020-10-20T17:31:07Z)
• WikiBERT models: deep transfer learning for many languages [1.3455090151301572]
  We introduce a simple, fully automated pipeline for creating languagespecific BERT models from Wikipedia data. We assess the merits of these models using the state-of-the-art UDify on Universal Dependencies data.
  arXiv  Detail & Related papers  (2020-06-02T11:57:53Z)
• ParsBERT: Transformer-based Model for Persian Language Understanding [0.7646713951724012]
  This paper proposes a monolingual BERT for the Persian language (ParsBERT) It shows its state-of-the-art performance compared to other architectures and multilingual models. ParsBERT obtains higher scores in all datasets, including existing ones as well as composed ones.
  arXiv  Detail & Related papers  (2020-05-26T05:05:32Z)

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.