Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userIt Is Not As Good As You Think! Evaluating Simultaneous Machine Translation on Interpretation Data
انها ليست جيدة كما تعتقد!تقييم الترجمة الآلية المتزامنة على بيانات التفسير
383
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
يتم تدريب معظم أنظمة الترجمة الآلية المتزامنة (SIMT) وتقييمها في Offline Translation Corpora.نحن نقول أن أنظمة SIMT يجب تدريبها واختبارها على بيانات التفسير الحقيقي.لتوضيح هذه الحجة، نقترح مجموعة اختبار التفسير وإجراء تقييم واقعي ل Simt المدربة على الترجمات دون اتصال.نتائجنا، في الاختبار المحدد لدينا مع 3 أزواج لغة صغيرة الحجم الحالية، تسليط الضوء على الفرق من النتيجة حتى 13.83 بلو عند تقييم نماذج Simt على بيانات الترجمة الشفوية للترجمة.في غياب بيانات التدريب على الترجمة الشفوية، نقترح طريقة نقل نمط الترجمة إلى الترجمة إلى الترجمة (T2I) التي تسمح بتحويل الترجمات غير المتصلة حاليا إلى بيانات نمط الترجمة الشفوية، مما يؤدي إلى تحسن ما يصل إلى 2.8 بلو.ومع ذلك، لا تزال فجوة التقييم ملحوظة، ودعا إلى بناء تفسير واسع النطاق مناسبة بشكل أفضل لتقييم وتطوير أنظمة SIMT.
Most existing simultaneous machine translation (SiMT) systems are trained and evaluated on offline translation corpora. We argue that SiMT systems should be trained and tested on real interpretation data. To illustrate this argument, we propose an interpretation test set and conduct a realistic evaluation of SiMT trained on offline translations. Our results, on our test set along with 3 existing smaller scale language pairs, highlight the difference of up-to 13.83 BLEU score when SiMT models are evaluated on translation vs interpretation data. In the absence of interpretation training data, we propose a translation-to-interpretation (T2I) style transfer method which allows converting existing offline translations into interpretation-style data, leading to up-to 2.8 BLEU improvement. However, the evaluation gap remains notable, calling for constructing large-scale interpretation corpora better suited for evaluating and developing SiMT systems.
References used
https://aclanthology.org/
rate research
Read More
We propose a generative framework for simultaneous machine translation. Conventional approaches use a fixed number of source words to translate or learn dynamic policies for the number of source words by reinforcement learning. Here we formulate simu
ltaneous translation as a structural sequence-to-sequence learning problem. A latent variable is introduced to model read or translate actions at every time step, which is then integrated out to consider all the possible translation policies. A re-parameterised Poisson prior is used to regularise the policies which allows the model to explicitly balance translation quality and latency. The experiments demonstrate the effectiveness and robustness of the generative framework, which achieves the best BLEU scores given different average translation latencies on benchmark datasets.
Simultaneous machine translation has recently gained traction thanks to significant quality improvements and the advent of streaming applications. Simultaneous translation systems need to find a trade-off between translation quality and response time
, and with this purpose multiple latency measures have been proposed. However, latency evaluations for simultaneous translation are estimated at the sentence level, not taking into account the sequential nature of a streaming scenario. Indeed, these sentence-level latency measures are not well suited for continuous stream translation, resulting in figures that are not coherent with the simultaneous translation policy of the system being assessed. This work proposes a stream level adaptation of the current latency measures based on a re-segmentation approach applied to the output translation, that is successfully evaluated on streaming conditions for a reference IWSLT task.
In this paper, we show that automatically-generated questions and answers can be used to evaluate the quality of Machine Translation (MT) systems. Building on recent work on the evaluation of abstractive text summarization, we propose a new metric for system-level MT evaluation, compare it with other state-of-the-art solutions, and show its robustness by conducting experiments for various MT directions.
We study the problem of domain adaptation in Neural Machine Translation (NMT) when domain-specific data cannot be shared due to confidentiality or copyright issues. As a first step, we propose to fragment data into phrase pairs and use a random sampl
e to fine-tune a generic NMT model instead of the full sentences. Despite the loss of long segments for the sake of confidentiality protection, we find that NMT quality can considerably benefit from this adaptation, and that further gains can be obtained with a simple tagging technique.
In simultaneous machine translation, finding an agent with the optimal action sequence of reads and writes that maintain a high level of translation quality while minimizing the average lag in producing target tokens remains an extremely challenging
problem. We propose a novel supervised learning approach for training an agent that can detect the minimum number of reads required for generating each target token by comparing simultaneous translations against full-sentence translations during training to generate oracle action sequences. These oracle sequences can then be used to train a supervised model for action generation at inference time. Our approach provides an alternative to current heuristic methods in simultaneous translation by introducing a new training objective, which is easier to train than previous attempts at training the agent using reinforcement learning techniques for this task. Our experimental results show that our novel training method for action generation produces much higher quality translations while minimizing the average lag in simultaneous 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
