Machine Translation with Unsupervised Length-Constraints

• URL: http://arxiv.org/abs/2004.03176v1
• Date: Tue, 7 Apr 2020 07:55:41 GMT
• Title: Machine Translation with Unsupervised Length-Constraints
• Authors: Jan Niehues
• Abstract summary: We focus on length constraints, which are essential if the translation should be displayed in a given format. Compared to a traditional method that first translates and then performs sentence compression, the text compression is learned completely unsupervised. We are able to significantly improve the translation quality under constraints.
• Score: 12.376309678270275
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We have seen significant improvements in machine translation due to the usage of deep learning. While the improvements in translation quality are impressive, the encoder-decoder architecture enables many more possibilities. In this paper, we explore one of these, the generation of constraint translation. We focus on length constraints, which are essential if the translation should be displayed in a given format. In this work, we propose an end-to-end approach for this task. Compared to a traditional method that first translates and then performs sentence compression, the text compression is learned completely unsupervised. By combining the idea with zero-shot multilingual machine translation, we are also able to perform unsupervised monolingual sentence compression. In order to fulfill the length constraints, we investigated several methods to integrate the constraints into the model. Using the presented technique, we are able to significantly improve the translation quality under constraints. Furthermore, we are able to perform unsupervised monolingual sentence compression.

Related papers

• Mitigating Hallucinations and Off-target Machine Translation with Source-Contrastive and Language-Contrastive Decoding [53.84948040596055]
  We introduce two related methods to mitigate failure cases with a modified decoding objective. Experiments on the massively multilingual models M2M-100 (418M) and SMaLL-100 show that these methods suppress hallucinations and off-target translations.
  arXiv  Detail & Related papers  (2023-09-13T17:15:27Z)
• On the Copying Problem of Unsupervised NMT: A Training Schedule with a Language Discriminator Loss [120.19360680963152]
  unsupervised neural machine translation (UNMT) has achieved success in many language pairs. The copying problem, i.e., directly copying some parts of the input sentence as the translation, is common among distant language pairs. We propose a simple but effective training schedule that incorporates a language discriminator loss.
  arXiv  Detail & Related papers  (2023-05-26T18:14:23Z)
• Interactive-Chain-Prompting: Ambiguity Resolution for Crosslingual Conditional Generation with Interaction [38.73550742775257]
  A source query in one language may yield several translation options in another language without any extra context. We propose a novel method interactive-chain prompting that reduces translations into a list of subproblems addressing ambiguities. We create a dataset exhibiting different linguistic phenomena which leads to ambiguities at inference for four languages.
  arXiv  Detail & Related papers  (2023-01-24T21:08:13Z)
• Multilingual Neural Machine Translation with Deep Encoder and Multiple Shallow Decoders [77.2101943305862]
  We propose a deep encoder with multiple shallow decoders (DEMSD) where each shallow decoder is responsible for a disjoint subset of target languages. DEMSD model with 2-layer decoders is able to obtain a 1.8x speedup on average compared to a standard transformer model with no drop in translation quality.
  arXiv  Detail & Related papers  (2022-06-05T01:15:04Z)
• Principled Paraphrase Generation with Parallel Corpora [52.78059089341062]
  We formalize the implicit similarity function induced by round-trip Machine Translation. We show that it is susceptible to non-paraphrase pairs sharing a single ambiguous translation. We design an alternative similarity metric that mitigates this issue.
  arXiv  Detail & Related papers  (2022-05-24T17:22:42Z)
• DEEP: DEnoising Entity Pre-training for Neural Machine Translation [123.6686940355937]
  It has been shown that machine translation models usually generate poor translations for named entities that are infrequent in the training corpus. We propose DEEP, a DEnoising Entity Pre-training method that leverages large amounts of monolingual data and a knowledge base to improve named entity translation accuracy within sentences.
  arXiv  Detail & Related papers  (2021-11-14T17:28:09Z)
• BitextEdit: Automatic Bitext Editing for Improved Low-Resource Machine Translation [53.55009917938002]
  We propose to refine the mined bitexts via automatic editing. Experiments demonstrate that our approach successfully improves the quality of CCMatrix mined bitext for 5 low-resource language-pairs and 10 translation directions by up to 8 BLEU points.
  arXiv  Detail & Related papers  (2021-11-12T16:00:39Z)
• Using Machine Translation to Localize Task Oriented NLG Output [5.770385426429663]
  This paper explores doing this by applying machine translation to the English output. The required quality bar is close to perfection, the range of sentences is extremely narrow, and the sentences are often very different from the ones in the machine translation training data. We are able to reach the required quality bar by building on existing ideas and adding new ones.
  arXiv  Detail & Related papers  (2021-07-09T15:56:45Z)
• End-to-End Lexically Constrained Machine Translation for Morphologically Rich Languages [0.0]
  We investigate mechanisms to allow neural machine translation to infer the correct word inflection given lemmatized constraints. Our experiments on the English-Czech language pair show that this approach improves the translation of constrained terms in both automatic and manual evaluation.
  arXiv  Detail & Related papers  (2021-06-23T13:40:13Z)
• Improving Zero-Shot Translation by Disentangling Positional Information [24.02434897109097]
  We show that a main factor causing the language-specific representations is the positional correspondence to input tokens. We gain up to 18.5 BLEU points on zero-shot translation while retaining quality on supervised directions.
  arXiv  Detail & Related papers  (2020-12-30T12:20:41Z)
• Incorporating Bilingual Dictionaries for Low Resource Semi-Supervised Neural Machine Translation [5.958653653305609]
  We incorporate widely available bilingual dictionaries that yield word-by-word translations to generate synthetic sentences. This automatically expands the vocabulary of the model while maintaining high quality content.
  arXiv  Detail & Related papers  (2020-04-05T02:14:14Z)

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.