Transformer-based Automatic Post-Editing Model with Joint Encoder and Multi-source Attention of Decoder

Lee, WonKee; Shin, Jaehun; Lee, Jong-Hyeok

doi:10.18653/v1/w19-5412

Cited by 13 publications

(9 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For this data construction process, they used the parallel corpora and the NMT model released for the WMT20 Quality Estimation shared task. As APE model, they chose the sequential model proposed in (Lee et al, 2019), applying some minor modifications to increase the training efficiency. They submitted two ensemble models.…”

Section: Postechmentioning

confidence: 99%

Findings of the WMT 2018 Shared Task on Automatic Post-Editing

Chatterjee¹,

Negri²,

Rubino³

et al. 2018

Proceedings of the Third Conference on Machine Translation: Shared Task Papers

View full text Add to dashboard Cite

We present the results from the fourth round of the WMT shared task on MT Automatic Post-Editing. The task consists in automatically correcting the output of a "black-box" machine translation system by learning from human corrections. Keeping the same general evaluation setting of the three previous rounds, this year we focused on one language pair (English-German) and on domainspecific data (Information Technology), with MT outputs produced by two different paradigms: phrase-based (PBSMT) and neural (NMT). Five teams submitted respectively 11 runs for the PBSMT subtask and 10 runs for the NMT subtask. In the former subtask, characterized by original translations of lower quality, top results achieved impressive improvements, up to-6.24 TER and +9.53 BLEU points over the baseline "do-nothing" system. The NMT subtask proved to be more challenging due to the higher quality of the original translations and the availability of less training data. In this case, top results show smaller improvements up to-0.38 TER and +0.8 BLEU points.

show abstract

Section: Postechmentioning

confidence: 99%

Findings of the WMT 2018 Shared Task on Automatic Post-Editing

Chatterjee¹,

Negri²,

Rubino³

et al. 2018

Proceedings of the Third Conference on Machine Translation: Shared Task Papers

View full text Add to dashboard Cite

show abstract

“…A representative dataset that employs this method is eSCAPE [23]. Recent studies have also introduced high-performance APE models by applying this method [18,26]. As an alternative to utilizing a translation model, a noising scheme has been adopted to generate the MT in augmenting the APE triplet from the parallel corpus [19].…”

Section: Two Research Directions Of Ape a Backgroundmentioning

confidence: 99%

An Empirical Study on Automatic Post Editing for Neural Machine Translation

Moon

Park

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Automatic post editing (APE) researches aim to correct errors in the machine translation results. Recently, APE research has mainly been conducted in two directions: noise-based APE and adapterbased APE. This study poses three questions based on existing APE studies and conducted a verification. The first is a question about the optimal APE research direction, and this has been figured out through a comparative analysis of the previous studies on noise-based APE and adapter-based APE. The second is about the substantial effectiveness of the bottleneck adapter layer (BAL) in adapter based APE. For the verification, various experiments on the different size of BAL has been conducted, and through these experiments, optimal approaches in adapter based APE has been proposed. For the last, this work raises a question about the reason why leveraging external knowledge is influential in APE. In this regard, we conducted several comparative experiments on the method of utilizing external data to APE training to achieve a better performance. The results revealed that the performance can be improved by applying the method of concatenating the external data with the existing data when training the APE model.Through deep analysis on these experiments, this work propose the optimal research direction in APE.

show abstract

“…Motivated by the recent research on using the second decoder to do post-editing [19,20,21,22,23], we use the similar structure to achieve the goal of proofreading. As shown in Figure 2, we use the basic setting of the transformer decoder [18], and add an additional stacked multi-head attention layer after the original multi-head attention layer to deal with the phone embedding of the source speech.…”

Section: Decoder Fusionmentioning

confidence: 99%

AlloST: Low-Resource Speech Translation Without Source Transcription

Cheng¹,

Lee

Wang

2021

Interspeech 2021

View full text Add to dashboard Cite

The end-to-end architecture has made promising progress in speech translation (ST). However, the ST task is still challenging under low-resource conditions. Most ST models have shown unsatisfactory results, especially in the absence of word information from the source speech utterance. In this study, we survey methods to improve ST performance without using source transcription, and propose a learning framework that utilizes a language-independent universal phone recognizer. The framework is based on an attention-based sequence-to-sequence model, where the encoder generates the phonetic embeddings and phone-aware acoustic representations, and the decoder controls the fusion of the two embedding streams to produce the target token sequence. In addition to investigating different fusion strategies, we explore the specific usage of byte pair encoding (BPE), which compresses a phone sequence into a syllablelike segmented sequence with semantic information. Experiments conducted on the Fisher Spanish-English and Taigi-Mandarin drama corpora show that our method outperforms the conformer-based baseline, and the performance is close to that of the existing best method using source transcription.

show abstract

Transformer-based Automatic Post-Editing Model with Joint Encoder and Multi-source Attention of Decoder

Cited by 13 publications

References 11 publications

Findings of the WMT 2018 Shared Task on Automatic Post-Editing

Findings of the WMT 2018 Shared Task on Automatic Post-Editing

An Empirical Study on Automatic Post Editing for Neural Machine Translation

AlloST: Low-Resource Speech Translation Without Source Transcription

Contact Info

Product

Resources

About