Beyond Literal Token Overlap: Token Alignability for Multilinguality
- URL: http://arxiv.org/abs/2502.06468v1
- Date: Mon, 10 Feb 2025 13:50:12 GMT
- Title: Beyond Literal Token Overlap: Token Alignability for Multilinguality
- Authors: Katharina Hämmerl, Tomasz Limisiewicz, Jindřich Libovický, Alexander Fraser,
- Abstract summary: We propose subword token alignability as a new way to understand the impact and quality of multilingual tokenisation.
In particular, this metric predicts multilinguality much better when scripts are disparate and the overlap of literal tokens is low.
We recommend our subword token alignability metric for identifying optimal language pairs for cross-lingual transfer.
- Score: 53.680462160878925
- License:
- Abstract: Previous work has considered token overlap, or even similarity of token distributions, as predictors for multilinguality and cross-lingual knowledge transfer in language models. However, these very literal metrics assign large distances to language pairs with different scripts, which can nevertheless show good cross-linguality. This limits the explanatory strength of token overlap for knowledge transfer between language pairs that use distinct scripts or follow different orthographic conventions. In this paper, we propose subword token alignability as a new way to understand the impact and quality of multilingual tokenisation. In particular, this metric predicts multilinguality much better when scripts are disparate and the overlap of literal tokens is low. We analyse this metric in the context of both encoder and decoder models, look at data size as a potential distractor, and discuss how this insight may be applied to multilingual tokenisation in future work. We recommend our subword token alignability metric for identifying optimal language pairs for cross-lingual transfer, as well as to guide the construction of better multilingual tokenisers in the future. We publish our code and reproducibility details.
Related papers
- mCL-NER: Cross-Lingual Named Entity Recognition via Multi-view
Contrastive Learning [54.523172171533645]
Cross-lingual named entity recognition (CrossNER) faces challenges stemming from uneven performance due to the scarcity of multilingual corpora.
We propose Multi-view Contrastive Learning for Cross-lingual Named Entity Recognition (mCL-NER)
Our experiments on the XTREME benchmark, spanning 40 languages, demonstrate the superiority of mCL-NER over prior data-driven and model-based approaches.
arXiv Detail & Related papers (2023-08-17T16:02:29Z) - Language Model Tokenizers Introduce Unfairness Between Languages [98.92630681729518]
We show how disparity in the treatment of different languages arises at the tokenization stage, well before a model is even invoked.
Character-level and byte-level models also exhibit over 4 times the difference in the encoding length for some language pairs.
We make the case that we should train future language models using multilingually fair subword tokenizers.
arXiv Detail & Related papers (2023-05-17T14:17:57Z) - VECO 2.0: Cross-lingual Language Model Pre-training with
Multi-granularity Contrastive Learning [56.47303426167584]
We propose a cross-lingual pre-trained model VECO2.0 based on contrastive learning with multi-granularity alignments.
Specifically, the sequence-to-sequence alignment is induced to maximize the similarity of the parallel pairs and minimize the non-parallel pairs.
token-to-token alignment is integrated to bridge the gap between synonymous tokens excavated via the thesaurus dictionary from the other unpaired tokens in a bilingual instance.
arXiv Detail & Related papers (2023-04-17T12:23:41Z) - How Do Multilingual Encoders Learn Cross-lingual Representation? [8.409283426564977]
Cross-lingual transfer benefits languages with little to no training data by transferring from other languages.
This thesis first shows such surprising cross-lingual effectiveness compared against prior art on various tasks.
We also look at how to inject different cross-lingual signals into multilingual encoders, and the optimization behavior of cross-lingual transfer with these models.
arXiv Detail & Related papers (2022-07-12T17:57:05Z) - Exposing Cross-Lingual Lexical Knowledge from Multilingual Sentence
Encoders [85.80950708769923]
We probe multilingual language models for the amount of cross-lingual lexical knowledge stored in their parameters, and compare them against the original multilingual LMs.
We also devise a novel method to expose this knowledge by additionally fine-tuning multilingual models.
We report substantial gains on standard benchmarks.
arXiv Detail & Related papers (2022-04-30T13:23:16Z) - Improving Pretrained Cross-Lingual Language Models via Self-Labeled Word
Alignment [49.45399359826453]
Cross-lingual language models are typically pretrained with language modeling on multilingual text or parallel sentences.
We introduce denoising word alignment as a new cross-lingual pre-training task.
Experimental results show that our method improves cross-lingual transferability on various datasets.
arXiv Detail & Related papers (2021-06-11T13:36:01Z) - Looking for Clues of Language in Multilingual BERT to Improve
Cross-lingual Generalization [56.87201892585477]
Token embeddings in multilingual BERT (m-BERT) contain both language and semantic information.
We control the output languages of multilingual BERT by manipulating the token embeddings.
arXiv Detail & Related papers (2020-10-20T05:41:35Z)
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.