MorphPiece : A Linguistic Tokenizer for Large Language Models

• URL: http://arxiv.org/abs/2307.07262v2
• Date: Sat, 3 Feb 2024 05:42:54 GMT
• Title: MorphPiece : A Linguistic Tokenizer for Large Language Models
• Authors: Haris Jabbar
• Abstract summary: I propose a linguistically motivated tokenization scheme, MorphPiece, which is based partly on morphological segmentation of the underlying text. A GPT-style causal language model trained on this tokenizer (called MorphGPT) shows comparable or superior performance on a variety of supervised and unsupervised NLP tasks.
• Score: 3.8073142980733
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Tokenization is a critical part of modern NLP pipelines. However, contemporary tokenizers for Large Language Models are based on statistical analysis of text corpora, without much consideration to the linguistic features. I propose a linguistically motivated tokenization scheme, MorphPiece, which is based partly on morphological segmentation of the underlying text. A GPT-style causal language model trained on this tokenizer (called MorphGPT) shows comparable or superior performance on a variety of supervised and unsupervised NLP tasks, compared to the OpenAI GPT-2 model. Specifically I evaluated MorphGPT on language modeling tasks, zero-shot performance on GLUE Benchmark with various prompt templates, massive text embedding benchmark (MTEB) for supervised and unsupervised performance, and lastly with another morphological tokenization scheme (FLOTA, Hoffmann et al., 2022) and find that the model trained on MorphPiece outperforms GPT-2 on most evaluations, at times with considerable margin, despite being trained for about half the training iterations.

Related papers

• MAGNET: Improving the Multilingual Fairness of Language Models with Adaptive Gradient-Based Tokenization [81.83460411131931]
  In multilingual settings, non-Latin scripts and low-resource languages are usually disadvantaged in terms of language models' utility, efficiency, and cost. We propose multilingual adaptive gradient-based tokenization to reduce over-segmentation via adaptive gradient-based subword tokenization.
  arXiv  Detail & Related papers  (2024-07-11T18:59:21Z)
• ML-SUPERB 2.0: Benchmarking Multilingual Speech Models Across Modeling Constraints, Languages, and Datasets [106.7760874400261]
  This paper presents ML-SUPERB2.0, which is a new benchmark for evaluating pre-trained SSL and supervised speech models. We find performance improvements over the setup of ML-SUPERB, but performance depends on the downstream model design. Also, we find large performance differences between languages and datasets, suggesting the need for more targeted approaches.
  arXiv  Detail & Related papers  (2024-06-12T21:01:26Z)
• 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)
• TAMS: Translation-Assisted Morphological Segmentation [3.666125285899499]
  We present a sequence-to-sequence model for canonical morpheme segmentation. Our model outperforms the baseline in a super-low resource setting but yields mixed results on training splits with more data. While further work is needed to make translations useful in higher-resource settings, our model shows promise in severely resource-constrained settings.
  arXiv  Detail & Related papers  (2024-03-21T21:23:35Z)
• Expedited Training of Visual Conditioned Language Generation via Redundancy Reduction [61.16125290912494]
  $textEVL_textGen$ is a framework designed for the pre-training of visually conditioned language generation models. We show that our approach accelerates the training of vision-language models by a factor of 5 without a noticeable impact on overall performance.
  arXiv  Detail & Related papers  (2023-10-05T03:40:06Z)
• Effects of sub-word segmentation on performance of transformer language models [0.628122931748758]
  We compare GPT and BERT models trained with the statistical segmentation algorithm BPE vs. two unsupervised algorithms for morphological segmentation. We show that training with morphological segmentation allows the LMs to: 1. achieve lower perplexity, 2. converge more efficiently in terms of training time, and 3. achieve equivalent or better evaluation scores on downstream tasks.
  arXiv  Detail & Related papers  (2023-05-09T14:30:29Z)
• Impact of Tokenization on Language Models: An Analysis for Turkish [2.4660652494309936]
  We train tokenizers and pretrain medium-sized language models using RoBERTa pretraining procedure on the Turkish split of the OSCAR corpus. Our experiments, supported by statistical tests, reveal that Morphological-level tokenizer has challenging performance with de facto tokenizers. We find that increasing the vocabulary size improves the performance of Morphological and Word-level tokenizers more than that of de facto tokenizers.
  arXiv  Detail & Related papers  (2022-04-19T12:01:46Z)
• KinyaBERT: a Morphology-aware Kinyarwanda Language Model [1.2183405753834562]
  Unsupervised sub-word tokenization methods are sub-optimal at handling morphologically rich languages. We propose a simple yet effective two-tier BERT architecture that leverages a morphological analyzer and explicitly represents morphological compositionality. We evaluate our proposed method on the low-resource morphologically rich Kinyarwanda language, naming the proposed model architecture KinyaBERT.
  arXiv  Detail & Related papers  (2022-03-16T08:36:14Z)
• CoreLM: Coreference-aware Language Model Fine-Tuning [0.0]
  We propose a Fine-Tuning framework, named CoreLM, that extends the architecture of current Pretrained Language Models. We make available information outside the contextual space of the model, which results in a better Language Model for a fraction of the computational cost. Our proposed model achieves a lower Perplexity in GUMBY and LAMBDADA datasets when compared to GPT2 and a fine-tuned version of GPT2 without any changes.
  arXiv  Detail & Related papers  (2021-11-04T08:44:31Z)
• Language Models are Few-shot Multilingual Learners [66.11011385895195]
  We evaluate the multilingual skills of the GPT and T5 models in conducting multi-class classification on non-English languages. We show that, given a few English examples as context, pre-trained language models can predict not only English test samples but also non-English ones.
  arXiv  Detail & Related papers  (2021-09-16T03:08:22Z)
• Grounded Compositional Outputs for Adaptive Language Modeling [59.02706635250856]
  A language model's vocabulary$-$typically selected before training and permanently fixed later$-$affects its size. We propose a fully compositional output embedding layer for language models. To our knowledge, the result is the first word-level language model with a size that does not depend on the training vocabulary.
  arXiv  Detail & Related papers  (2020-09-24T07:21:14Z)

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.