Improving Robustness of Retrieval Augmented Translation via Shuffling of Suggestions

• URL: http://arxiv.org/abs/2210.05059v1
• Date: Tue, 11 Oct 2022 00:09:51 GMT
• Title: Improving Robustness of Retrieval Augmented Translation via Shuffling of Suggestions
• Authors: Cuong Hoang, Devendra Sachan, Prashant Mathur, Brian Thompson, Marcello Federico
• Abstract summary: We show that for existing retrieval augmented translation methods, using a TM with a domain mismatch to the test set can result in substantially worse performance compared to not using a TM at all. We propose a simple method to expose fuzzy-match NMT systems during training and show that it results in a system that is much more tolerant (regaining up to 5.8 BLEU) to inference with TMs with domain mismatch.
• Score: 15.845071122977158
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Several recent studies have reported dramatic performance improvements in neural machine translation (NMT) by augmenting translation at inference time with fuzzy-matches retrieved from a translation memory (TM). However, these studies all operate under the assumption that the TMs available at test time are highly relevant to the testset. We demonstrate that for existing retrieval augmented translation methods, using a TM with a domain mismatch to the test set can result in substantially worse performance compared to not using a TM at all. We propose a simple method to expose fuzzy-match NMT systems during training and show that it results in a system that is much more tolerant (regaining up to 5.8 BLEU) to inference with TMs with domain mismatch. Also, the model is still competitive to the baseline when fed with suggestions from relevant TMs.

Related papers

• Rethinking Translation Memory Augmented Neural Machine Translation [45.21285869556621]
  We show that TM-augmented NMT is good at the ability of fitting data but sensitive to fluctuations in the training data. We propose a simple yet effective TM-augmented NMT model to promote the variance and address the contradictory phenomenon. Extensive experiments show that the proposed TM-augmented NMT achieves consistent gains over both conventional NMT and existing TM-augmented NMT.
  arXiv  Detail & Related papers  (2023-06-12T08:32:04Z)
• Augmenting Large Language Model Translators via Translation Memories [32.28138249566329]
  Using translation memories (TMs) as prompts is a promising approach to in-context learning of machine translation models. We take a step towards prompting large language models (LLMs) with TMs and making them better translators.
  arXiv  Detail & Related papers  (2023-05-27T04:47:09Z)
• Prompting Neural Machine Translation with Translation Memories [32.5633128085849]
  We present a simple but effective method to introduce TMs into neural machine translation (NMT) systems. Specifically, we treat TMs as prompts to the NMT model at test time, but leave the training process unchanged. The result is a slight update of an existing NMT system, which can be implemented in a few hours by anyone who is familiar with NMT.
  arXiv  Detail & Related papers  (2023-01-13T03:33:26Z)
• Neural Machine Translation with Contrastive Translation Memories [71.86990102704311]
  Retrieval-augmented Neural Machine Translation models have been successful in many translation scenarios. We propose a new retrieval-augmented NMT to model contrastively retrieved translation memories that are holistically similar to the source sentence. In training phase, a Multi-TM contrastive learning objective is introduced to learn salient feature of each TM with respect to target sentence.
  arXiv  Detail & Related papers  (2022-12-06T17:10:17Z)
• Improving Simultaneous Machine Translation with Monolingual Data [94.1085601198393]
  Simultaneous machine translation (SiMT) is usually done via sequence-level knowledge distillation (Seq-KD) from a full-sentence neural machine translation (NMT) model. We propose to leverage monolingual data to improve SiMT, which trains a SiMT student on the combination of bilingual data and external monolingual data distilled by Seq-KD.
  arXiv  Detail & Related papers  (2022-12-02T14:13:53Z)
• Efficient Cluster-Based k-Nearest-Neighbor Machine Translation [65.69742565855395]
  k-Nearest-Neighbor Machine Translation (kNN-MT) has been recently proposed as a non-parametric solution for domain adaptation in neural machine translation (NMT)
  arXiv  Detail & Related papers  (2022-04-13T05:46:31Z)
• Reference-based Magnetic Resonance Image Reconstruction Using Texture Transforme [86.6394254676369]
  We propose a novel Texture Transformer Module (TTM) for accelerated MRI reconstruction. We formulate the under-sampled data and reference data as queries and keys in a transformer. The proposed TTM can be stacked on prior MRI reconstruction approaches to further improve their performance.
  arXiv  Detail & Related papers  (2021-11-18T03:06:25Z)
• Distributed Word Representation in Tsetlin Machine [14.62945824459286]
  Tsetlin Machine (TM) is an interpretable pattern recognition algorithm based on propositional logic. We propose a novel way of using pre-trained word representations for TM. The approach significantly enhances TM performance and maintains interpretability at the same time.
  arXiv  Detail & Related papers  (2021-04-14T14:48:41Z)
• On the Inference Calibration of Neural Machine Translation [54.48932804996506]
  We study the correlation between calibration and translation performance and linguistic properties of miscalibration. We propose a new graduated label smoothing method that can improve both inference calibration and translation performance.
  arXiv  Detail & Related papers  (2020-05-03T02:03:56Z)

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.