Why don't people use character-level machine translation?

• URL: http://arxiv.org/abs/2110.08191v1
• Date: Fri, 15 Oct 2021 16:43:31 GMT
• Title: Why don't people use character-level machine translation?
• Authors: Jind\v{r}ich Libovick\'y, Helmut Schmid, Alexander Fraser
• Abstract summary: Despite evidence that character-level systems are comparable with subword systems, they are virtually never used in competitive setups in machine translation competitions. Character-level MT systems show neither better domain robustness, nor better morphological generalization, despite being often so motivated.
• Score: 69.53730499849023
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present a literature and empirical survey that critically assesses the state of the art in character-level modeling for machine translation (MT). Despite evidence in the literature that character-level systems are comparable with subword systems, they are virtually never used in competitive setups in WMT competitions. We empirically show that even with recent modeling innovations in character-level natural language processing, character-level MT systems still struggle to match their subword-based counterparts both in terms of translation quality and training and inference speed. Character-level MT systems show neither better domain robustness, nor better morphological generalization, despite being often so motivated. On the other hand, they tend to be more robust towards source side noise and the translation quality does not degrade with increasing beam size at decoding time.

Related papers

• On Search Strategies for Document-Level Neural Machine Translation [51.359400776242786]
  Document-level neural machine translation (NMT) models produce a more consistent output across a document. In this work, we aim to answer the question how to best utilize a context-aware translation model in decoding.
  arXiv  Detail & Related papers  (2023-06-08T11:30:43Z)
• Revisiting Machine Translation for Cross-lingual Classification [91.43729067874503]
  Most research in the area focuses on the multilingual models rather than the Machine Translation component. We show that, by using a stronger MT system and mitigating the mismatch between training on original text and running inference on machine translated text, translate-test can do substantially better than previously assumed.
  arXiv  Detail & Related papers  (2023-05-23T16:56:10Z)
• Discourse Centric Evaluation of Machine Translation with a Densely Annotated Parallel Corpus [82.07304301996562]
  This paper presents a new dataset with rich discourse annotations, built upon the large-scale parallel corpus BWB introduced in Jiang et al. We investigate the similarities and differences between the discourse structures of source and target languages. We discover that MT outputs differ fundamentally from human translations in terms of their latent discourse structures.
  arXiv  Detail & Related papers  (2023-05-18T17:36:41Z)
• Adaptive Machine Translation with Large Language Models [7.803471587734353]
  We investigate how we can utilize in-context learning to improve real-time adaptive machine translation. We conduct experiments across five diverse language pairs, namely English-to-Arabic (EN-AR), English-to-Chinese (EN-ZH), English-to-French (EN-FR), English-to-Kinyarwanda (EN-RW), and English-to-Spanish (EN-ES)
  arXiv  Detail & Related papers  (2023-01-30T21:17:15Z)
• How sensitive are translation systems to extra contexts? Mitigating gender bias in Neural Machine Translation models through relevant contexts [11.684346035745975]
  A growing number of studies highlight the inherent gender bias that Neural Machine Translation models incorporate during training. We investigate whether these models can be instructed to fix their bias during inference using targeted, guided instructions as contexts. We observe large improvements in reducing the gender bias in translations, across three popular test suites.
  arXiv  Detail & Related papers  (2022-05-22T06:31:54Z)
• When Does Translation Require Context? A Data-driven, Multilingual Exploration [71.43817945875433]
  proper handling of discourse significantly contributes to the quality of machine translation (MT) Recent works in context-aware MT attempt to target a small set of discourse phenomena during evaluation. We develop the Multilingual Discourse-Aware benchmark, a series of taggers that identify and evaluate model performance on discourse phenomena.
  arXiv  Detail & Related papers  (2021-09-15T17:29:30Z)
• Can Your Context-Aware MT System Pass the DiP Benchmark Tests? : Evaluation Benchmarks for Discourse Phenomena in Machine Translation [7.993547048820065]
  We introduce the first of their kind MT benchmark datasets that aim to track and hail improvements across four main discourse phenomena. Surprisingly, we find that existing context-aware models do not improve discourse-related translations consistently across languages and phenomena.
  arXiv  Detail & Related papers  (2020-04-30T07:15:36Z)
• Towards Reasonably-Sized Character-Level Transformer NMT by Finetuning Subword Systems [78.80826533405019]
  We show that we can obtain a neural machine translation model that works at the character level without requiring token segmentation. Our study is a significant step towards high-performance and easy to train character-based models that are not extremely large.
  arXiv  Detail & Related papers  (2020-04-29T15:56:02Z)
• When Does Unsupervised Machine Translation Work? [23.690875724726908]
  We conduct an empirical evaluation of unsupervised machine translation (MT) using dissimilar language pairs, dissimilar domains, diverse datasets, and authentic low-resource languages. We find that performance rapidly deteriorates when source and target corpora are from different domains. We additionally find that unsupervised MT performance declines when source and target languages use different scripts, and observe very poor performance on authentic low-resource language pairs.
  arXiv  Detail & Related papers  (2020-04-12T00:57:47Z)

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.