Why do language models perform worse for morphologically complex languages?

• URL: http://arxiv.org/abs/2411.14198v1
• Date: Thu, 21 Nov 2024 15:06:51 GMT
• Title: Why do language models perform worse for morphologically complex languages?
• Authors: Catherine Arnett, Benjamin K. Bergen,
• Abstract summary: We find new evidence for a performance gap between agglutinative and fusional languages. We propose three possible causes for this performance gap: morphological alignment of tokenizers, tokenization quality, and disparities in dataset sizes and measurement. Results suggest that no language is harder or easier for a language model to learn on the basis of its morphological typology.
• Score: 0.913127392774573
• License:
• Abstract: Language models perform differently across languages. It has been previously suggested that morphological typology may explain some of this variability (Cotterell et al., 2018). We replicate previous analyses and find additional new evidence for a performance gap between agglutinative and fusional languages, where fusional languages, such as English, tend to have better language modeling performance than morphologically more complex languages like Turkish. We then propose and test three possible causes for this performance gap: morphological alignment of tokenizers, tokenization quality, and disparities in dataset sizes and measurement. To test the morphological alignment hypothesis, we present MorphScore, a tokenizer evaluation metric, and supporting datasets for 22 languages. We find some evidence that tokenization quality explains the performance gap, but none for the role of morphological alignment. Instead we find that the performance gap is most reduced when training datasets are of equivalent size across language types, but only when scaled according to the so-called "byte-premium" -- the different encoding efficiencies of different languages and orthographies. These results suggest that no language is harder or easier for a language model to learn on the basis of its morphological typology. Differences in performance can be attributed to disparities in dataset size. These results bear on ongoing efforts to improve performance for low-performing and under-resourced languages.

Related papers

• Tokenization and Morphology in Multilingual Language Models: A Comparative Analysis of mT5 and ByT5 [4.779196219827507]
  We capture the impact of tokenization by contrasting two multilingual language models: mT5 and ByT5. Probing the morphological knowledge encoded in these models on four tasks and 17 languages, our analyses show that the models learn the morphological systems of some languages better than others.
  arXiv  Detail & Related papers  (2024-10-15T14:14:19Z)
• The Role of Language Imbalance in Cross-lingual Generalisation: Insights from Cloned Language Experiments [57.273662221547056]
  In this study, we investigate an unintuitive novel driver of cross-lingual generalisation: language imbalance. We observe that the existence of a predominant language during training boosts the performance of less frequent languages. As we extend our analysis to real languages, we find that infrequent languages still benefit from frequent ones, yet whether language imbalance causes cross-lingual generalisation there is not conclusive.
  arXiv  Detail & Related papers  (2024-04-11T17:58:05Z)
• 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)
• MYTE: Morphology-Driven Byte Encoding for Better and Fairer Multilingual Language Modeling [70.34758460372629]
  We introduce a new paradigm that encodes the same information with segments of consistent size across diverse languages. MYTE produces shorter encodings for all 99 analyzed languages. This, in turn, improves multilingual LM performance and diminishes the perplexity gap throughout diverse languages.
  arXiv  Detail & Related papers  (2024-03-15T21:21:11Z)
• GradSim: Gradient-Based Language Grouping for Effective Multilingual Training [13.730907708289331]
  We propose GradSim, a language grouping method based on gradient similarity. Our experiments on three diverse multilingual benchmark datasets show that it leads to the largest performance gains. Besides linguistic features, the topics of the datasets play an important role for language grouping.
  arXiv  Detail & Related papers  (2023-10-23T18:13:37Z)
• Do Not Fire the Linguist: Grammatical Profiles Help Language Models Detect Semantic Change [6.7485485663645495]
  We first compare the performance of grammatical profiles against that of a multilingual neural language model (XLM-R) on 10 datasets, covering 7 languages. Our results show that ensembling grammatical profiles with XLM-R improves semantic change detection performance for most datasets and languages.
  arXiv  Detail & Related papers  (2022-04-12T11:20:42Z)
• A Massively Multilingual Analysis of Cross-linguality in Shared Embedding Space [61.18554842370824]
  In cross-lingual language models, representations for many different languages live in the same space. We compute a task-based measure of cross-lingual alignment in the form of bitext retrieval performance. We examine a range of linguistic, quasi-linguistic, and training-related features as potential predictors of these alignment metrics.
  arXiv  Detail & Related papers  (2021-09-13T21:05:37Z)
• Enhancing deep neural networks with morphological information [0.0]
  We analyse the effect of adding morphological features to LSTM and BERT models. Our results suggest that adding morphological features has mixed effects depending on the quality of features and the task.
  arXiv  Detail & Related papers  (2020-11-24T22:35:44Z)
• 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)
• On the Importance of Word Order Information in Cross-lingual Sequence Labeling [80.65425412067464]
  Cross-lingual models that fit into the word order of the source language might fail to handle target languages. We investigate whether making models insensitive to the word order of the source language can improve the adaptation performance in target languages.
  arXiv  Detail & Related papers  (2020-01-30T03:35:44Z)

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.