Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userMutual-Learning Improves End-to-End Speech Translation
التعلم المتبادل يحسن ترجمة خط الكلام في النهاية
187
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تتمثل منطقة البحث الشعبية حاليا في الترجمة الانتهاء من الكلام في النهاية باستخدام تقنورة المعرفة من مهمة ترجمة آلية (MT) لتحسين مهمة ترجمة الكلام (ST).ومع ذلك، من الواضح أن مثل هذا السيناريو يسمح فقط بنقل طريقة واحدة، وهو محدود من أداء نموذج المعلم.لذلك، نحن فرضية أن الأساليب القائمة على تقطر المعرفة هي الأمثل.في هذه الورقة، نقترح بديلا - سيناريو تعليمي متبادل قابل للتدريب، حيث تم تدريب MT ونماذج ST بشكل تعاوني وتعتبر أقرانها، بدلا من المعلم / الطالب.هذا يسمح لنا بتحسين أداء الشك الواحد إلى نهاية أكثر فعالية من نموذج معلم طالب.كمنفعة جانبية، يتحسن أداء نموذج MT أيضا.تظهر النتائج التجريبية أنه في سيناريو التعلم المتبادل لدينا، يمكن أن تستخدم النماذج بشكل فعال المعلومات المساعدة من نماذج الأقران وتحقيق نتائج مقنعة على مجموعة بيانات MUST-C.
A currently popular research area in end-to-end speech translation is the use of knowledge distillation from a machine translation (MT) task to improve the speech translation (ST) task. However, such scenario obviously only allows one way transfer, which is limited by the performance of the teacher model. Therefore, We hypothesis that the knowledge distillation-based approaches are sub-optimal. In this paper, we propose an alternative--a trainable mutual-learning scenario, where the MT and the ST models are collaboratively trained and are considered as peers, rather than teacher/student. This allows us to improve the performance of end-to-end ST more effectively than with a teacher-student paradigm. As a side benefit, performance of the MT model also improves. Experimental results show that in our mutual-learning scenario, models can effectively utilise the auxiliary information from peer models and achieve compelling results on Must-C dataset.
References used
https://aclanthology.org/
rate research
Read More
This paper describes the submission of the NiuTrans end-to-end speech translation system for the IWSLT 2021 offline task, which translates from the English audio to German text directly without intermediate transcription. We use the Transformer-based
model architecture and enhance it by Conformer, relative position encoding, and stacked acoustic and textual encoding. To augment the training data, the English transcriptions are translated to German translations. Finally, we employ ensemble decoding to integrate the predictions from several models trained with the different datasets. Combining these techniques, we achieve 33.84 BLEU points on the MuST-C En-De test set, which shows the enormous potential of the end-to-end model.
Current approaches to incorporating terminology constraints in machine translation (MT) typically assume that the constraint terms are provided in their correct morphological forms. This limits their application to real-world scenarios where constrai
nt terms are provided as lemmas. In this paper, we introduce a modular framework for incorporating lemma constraints in neural MT (NMT) in which linguistic knowledge and diverse types of NMT models can be flexibly applied. It is based on a novel cross-lingual inflection module that inflects the target lemma constraints based on the source context. We explore linguistically motivated rule-based and data-driven neural-based inflection modules and design English-German health and English-Lithuanian news test suites to evaluate them in domain adaptation and low-resource MT settings. Results show that our rule-based inflection module helps NMT models incorporate lemma constraints more accurately than a neural module and outperforms the existing end-to-end approach with lower training costs.
A conventional approach to improving the performance of end-to-end speech translation (E2E-ST) models is to leverage the source transcription via pre-training and joint training with automatic speech recognition (ASR) and neural machine translation (
NMT) tasks. However, since the input modalities are different, it is difficult to leverage source language text successfully. In this work, we focus on sequence-level knowledge distillation (SeqKD) from external text-based NMT models. To leverage the full potential of the source language information, we propose backward SeqKD, SeqKD from a target-to-source backward NMT model. To this end, we train a bilingual E2E-ST model to predict paraphrased transcriptions as an auxiliary task with a single decoder. The paraphrases are generated from the translations in bitext via back-translation. We further propose bidirectional SeqKD in which SeqKD from both forward and backward NMT models is combined. Experimental evaluations on both autoregressive and non-autoregressive models show that SeqKD in each direction consistently improves the translation performance, and the effectiveness is complementary regardless of the model capacity.
Current abstractive summarization systems outperform their extractive counterparts, but their widespread adoption is inhibited by the inherent lack of interpretability. Extractive summarization systems, though interpretable, suffer from redundancy an
d possible lack of coherence. To achieve the best of both worlds, we propose EASE, an extractive-abstractive framework that generates concise abstractive summaries that can be traced back to an extractive summary. Our framework can be applied to any evidence-based text generation problem and can accommodate various pretrained models in its simple architecture. We use the Information Bottleneck principle to jointly train the extraction and abstraction in an end-to-end fashion. Inspired by previous research that humans use a two-stage framework to summarize long documents (Jing and McKeown, 2000), our framework first extracts a pre-defined amount of evidence spans and then generates a summary using only the evidence. Using automatic and human evaluations, we show that the generated summaries are better than strong extractive and extractive-abstractive baselines.
This paper contains the description for the submission of Karlsruhe Institute of Technology (KIT) for the multilingual TEDx translation task in the IWSLT 2021 evaluation campaign. Our main approach is to develop both cascade and end-to-end systems an
d eventually combine them together to achieve the best possible results for this extremely low-resource setting. The report also confirms certain consistent architectural improvement added to the Transformer architecture, for all tasks: translation, transcription and speech translation.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
