Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userInverted Projection for Robust Speech Translation
ترجمة مقلوبة ترجمة خطاب قوية
370
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تقوم أنظمة الترجمة التقليدية المدربين على وثائق مكتوبة بشكل جيد للترجمة المستندة إلى النصوص ولكن ليس كذلك للتطبيقات المستندة إلى الكلام.نحن نهدف إلى تكييف نماذج الترجمة إلى الكلام عن طريق إدخال أخطاء معجمية حقيقية من أخطاء ASR والتجزئة من علامات الترقيم التلقائية في بيانات تدريب الترجمة الخاصة بنا.نقدم نهج إسقاط مقلوب تم اكتشافه تلقائيا شرائح النظام تلقائيا على النصوص البشرية ومن ثم إعادة الشرائح ترجمة الذهب إلى محاذاة النصوص الإنسانية المتوقعة.نوضح أن هذا يتغلب على عدم تطابق اختبار القطار الموجود في نهج التدريب الأخرى.يحقق نهج الإسقاط الجديد مكاسب أكثر من 1 نقطة بلو على خط أساس يتعرض للنصوص البشرية والجزء، وهذه المكاسب تعقد لكلا بيانات IWSLT وبيانات YouTube.
Traditional translation systems trained on written documents perform well for text-based translation but not as well for speech-based applications. We aim to adapt translation models to speech by introducing actual lexical errors from ASR and segmentation errors from automatic punctuation into our translation training data. We introduce an inverted projection approach that projects automatically detected system segments onto human transcripts and then re-segments the gold translations to align with the projected human transcripts. We demonstrate that this overcomes the train-test mismatch present in other training approaches. The new projection approach achieves gains of over 1 BLEU point over a baseline that is exposed to the human transcripts and segmentations, and these gains hold for both IWSLT data and YouTube data.
References used
https://aclanthology.org/
rate research
Read More
Multilingual neural machine translation (MNMT) learns to translate multiple language pairs with a single model, potentially improving both the accuracy and the memory-efficiency of deployed models. However, the heavy data imbalance between languages
hinders the model from performing uniformly across language pairs. In this paper, we propose a new learning objective for MNMT based on distributionally robust optimization, which minimizes the worst-case expected loss over the set of language pairs. We further show how to practically optimize this objective for large translation corpora using an iterated best response scheme, which is both effective and incurs negligible additional computational cost compared to standard empirical risk minimization. We perform extensive experiments on three sets of languages from two datasets and show that our method consistently outperforms strong baseline methods in terms of average and per-language performance under both many-to-one and one-to-many translation settings.
With the increased audiovisualisation of communication, the need for live subtitles in multilingual events is more relevant than ever. In an attempt to automatise the process, we aim at exploring the feasibility of simultaneous speech translation (Si
mulST) for live subtitling. However, the word-for-word rate of generation of SimulST systems is not optimal for displaying the subtitles in a comprehensible and readable way. In this work, we adapt SimulST systems to predict subtitle breaks along with the translation. We then propose a display mode that exploits the predicted break structure by presenting the subtitles in scrolling lines. We compare our proposed mode with a display 1) word-for-word and 2) in blocks, in terms of reading speed and delay. Experiments on three language pairs (en→it, de, fr) show that scrolling lines is the only mode achieving an acceptable reading speed while keeping delay close to a 4-second threshold. We argue that simultaneous translation for readable live subtitles still faces challenges, the main one being poor translation quality, and propose directions for steering future research.
This paper describes Maastricht University's participation in the IWSLT 2021 multilingual speech translation track. The task in this track is to build multilingual speech translation systems in supervised and zero-shot directions. Our primary system
is an end-to-end model that performs both speech transcription and translation. We observe that the joint training for the two tasks is complementary especially when the speech translation data is scarce. On the source and target side, we use data augmentation and pseudo-labels respectively to improve the performance of our systems. We also introduce an ensembling technique that consistently improves the quality of transcriptions and translations. The experiments show that the end-to-end system is competitive with its cascaded counterpart especially in zero-shot conditions.
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.
In this paper, we describe Zhejiang University's submission to the IWSLT2021 Multilingual Speech Translation Task. This task focuses on speech translation (ST) research across many non-English source languages. Participants can decide whether to work
on constrained systems or unconstrained systems which can using external data. We create both cascaded and end-to-end speech translation constrained systems, using the provided data only. In the cascaded approach, we combine Conformer-based automatic speech recognition (ASR) with the Transformer-based neural machine translation (NMT). Our end-to-end direct speech translation systems use ASR pretrained encoder and multi-task decoders. The submitted systems are ensembled by different cascaded models.
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
