Online Automatic Post-editing for MT in a Multi-Domain Translation Environment

Chatterjee, Rajen; Gebremelak, Gebremedhen; Negri, Matteo; Turchi, Marco

doi:10.18653/v1/e17-1050

Cited by 17 publications

(15 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In statisti-cal MT, it was applied for the same purpose in [25,26] and later, in [27], for domain adaptation. More recently, different variants of the approach have been proposed for neural MT [28,29,30,31] and MT-related tasks [32]. However, differently from ST, all the previously explored translation scenarios involve managing textual data for domain adaptation purposes.…”

Section: Related Work and Open Issuesmentioning

confidence: 99%

Instance-based Model Adaptation for Direct Speech Translation

Gangi

Nguyen

Negri

et al. 2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

Despite recent technology advancements, the effectiveness of neural approaches to end-to-end speech-to-text translation is still limited by the paucity of publicly available training corpora. We tackle this limitation with a method to improve data exploitation and boost the system's performance at inference time. Our approach allows us to customize "on the fly" an existing model to each incoming translation request. At its core, it exploits an instance selection procedure to retrieve, from a given pool of data, a small set of samples similar to the input query in terms of latent properties of its audio signal. The retrieved samples are then used for an instance-specific finetuning of the model. We evaluate our approach in three different scenarios. In all data conditions (different languages, in/out-of-domain adaptation), our instance-based adaptation yields coherent performance gains over static models.Index Terms-End-to-end neural speech translation

show abstract

Section: Related Work and Open Issuesmentioning

confidence: 99%

Instance-based Model Adaptation for Direct Speech Translation

Gangi

Nguyen

Negri

et al. 2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

show abstract

“…The goal of automatic post-editing (APE) is to correct errors in an MT-ed text. The problem is typically approached as a "monolingual translation" task, in which models are trained on parallel corpora containing (MT_output, MT_post-edit) pairs, with MT post-edits coming from humans (Simard et al, 2007;Chatterjee et al, 2015bChatterjee et al, , 2017. In their attempt to translate the entire input sentence, APE systems usually tend to over-correct the source words, i.e.…”

Section: Resultsmentioning

confidence: 99%

Guiding Neural Machine Translation Decoding with External Knowledge

Chatterjee¹,

Negri²,

Turchi³

et al. 2017

Proceedings of the Second Conference on Machine Translation

Self Cite

View full text Add to dashboard Cite

Differently from the phrase-based paradigm, neural machine translation (NMT) operates on word and sentence representations in a continuous space. This makes the decoding process not only more difficult to interpret, but also harder to influence with external knowledge. For the latter problem, effective solutions like the XML-markup used by phrase-based models to inject fixed translation options as constraints at decoding time are not yet available. We propose a "guide" mechanism that enhances an existing NMT decoder with the ability to prioritize and adequately handle translation options presented in the form of XML annotations of source words. Positive results obtained in two different translation tasks indicate the effectiveness of our approach.

show abstract

“…Automatic Post-Editing (APE) (Simard and Foster, 2013;Chatterjee et al, 2017) aims to automatically correct errors in machine translation (MT) outputs in order to reduce the burden of human post-editors, especially with simple and repetitive corrections (e.g. typographic errors).…”

Section: Related Workmentioning

confidence: 99%

Deep Copycat Networks for Text-to-Text Generation

Ive

Madhyastha

Specia

2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

View full text Add to dashboard Cite

Most text-to-text generation tasks, for example text summarisation and text simplification, require copying words from the input to the output. We introduce copycat, a transformerbased pointer network for such tasks which obtains competitive results in abstractive text summarisation and generates more abstractive summaries. We propose a further extension of this architecture for automatic post-editing, where generation is conditioned over two inputs (source language and machine translation), and the model is capable of deciding where to copy information from. This approach achieves competitive performance when compared to state-of-the-art automated post-editing systems. More importantly, we show that it addresses a well-known limitation of automatic post-editing -overcorrecting translations -and that our novel mechanism for copying source language words improves the results.

show abstract

Online Automatic Post-editing for MT in a Multi-Domain Translation Environment

Cited by 17 publications

References 18 publications

Instance-based Model Adaptation for Direct Speech Translation

Instance-based Model Adaptation for Direct Speech Translation

Guiding Neural Machine Translation Decoding with External Knowledge

Deep Copycat Networks for Text-to-Text Generation

Contact Info

Product

Resources

About