Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userSampling and Filtering of Neural Machine Translation Distillation Data
أخذ العينات وتصفية بيانات التقطير الجهاز العصبي
287
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
في معظم سيناريوهات جهاز التقطير أو سرقة الترجمة الآلية العصبية، يتم استخدام فرضية التسجيل أعلى النموذج المستهدف (المعلم) لتدريب نموذج جديد (طالب).إذا كانت الترجمات المرجعية متاحة أيضا، فيمكن إظهار الفرضيات الأفضل (فيما يتعلق بالمراجع) وفرضيات فقراء إما إما إما إما أو إشرافها.تستكشف هذه الورقة طريقة مشهد أخذ العينات (تشذيب، فرضية ترشيحها وتشكيلها، واستكريسيا ومجمديها) مع الإنجليزية إلى التشيكية والإنجليزية إلى طرازات MT الألمانية باستخدام مقاييس تقييم MT القياسية.نظرا لأن الإرتفاع الدقيق والتركيبة مع البيانات الأصلية يؤدي إلى أداء أفضل عند مقارنتها بالتدريب فقط على البيانات الأصلية أو المركبة أو تركيها المباشر.
In most of neural machine translation distillation or stealing scenarios, the highest-scoring hypothesis of the target model (teacher) is used to train a new model (student). If reference translations are also available, then better hypotheses (with respect to the references) can be oversampled and poor hypotheses either removed or undersampled. This paper explores the sampling method landscape (pruning, hypothesis oversampling and undersampling, deduplication and their combination) with English to Czech and English to German MT models using standard MT evaluation metrics. We show that careful oversampling and combination with the original data leads to better performance when compared to training only on the original or synthesized data or their direct combination.
References used
https://aclanthology.org/
rate research
Read More
Scheduled sampling is widely used to mitigate the exposure bias problem for neural machine translation. Its core motivation is to simulate the inference scene during training by replacing ground-truth tokens with predicted tokens, thus bridging the g
ap between training and inference. However, vanilla scheduled sampling is merely based on training steps and equally treats all decoding steps. Namely, it simulates an inference scene with uniform error rates, which disobeys the real inference scene, where larger decoding steps usually have higher error rates due to error accumulations. To alleviate the above discrepancy, we propose scheduled sampling methods based on decoding steps, increasing the selection chance of predicted tokens with the growth of decoding steps. Consequently, we can more realistically simulate the inference scene during training, thus better bridging the gap between training and inference. Moreover, we investigate scheduled sampling based on both training steps and decoding steps for further improvements. Experimentally, our approaches significantly outperform the Transformer baseline and vanilla scheduled sampling on three large-scale WMT tasks. Additionally, our approaches also generalize well to the text summarization task on two popular benchmarks.
We implemented a neural machine translation system that uses automatic sequence tagging to improve the quality of translation. Instead of operating on unannotated sentence pairs, our system uses pre-trained tagging systems to add linguistic features
to source and target sentences. Our proposed neural architecture learns a combined embedding of tokens and tags in the encoder, and simultaneous token and tag prediction in the decoder. Compared to a baseline with unannotated training, this architecture increased the BLEU score of German to English film subtitle translation outputs by 1.61 points using named entity tags; however, the BLEU score decreased by 0.38 points using part-of-speech tags. This demonstrates that certain token-level tag outputs from off-the-shelf tagging systems can improve the output of neural translation systems using our combined embedding and simultaneous decoding extensions.
Multilingual pretrained language models are rapidly gaining popularity in NLP systems for non-English languages. Most of these models feature an important corpus sampling step in the process of accumulating training data in different languages, to en
sure that the signal from better resourced languages does not drown out poorly resourced ones. In this study, we train multiple multilingual recurrent language models, based on the ELMo architecture, and analyse both the effect of varying corpus size ratios on downstream performance, as well as the performance difference between monolingual models for each language, and broader multilingual language models. As part of this effort, we also make these trained models available for public use.
In image captioning, multiple captions are often provided as ground truths, since a valid caption is not always uniquely determined. Conventional methods randomly select a single caption and treat it as correct, but there have been few effective trai
ning methods that utilize multiple given captions. In this paper, we proposed two training technique for making effective use of multiple reference captions: 1) validity-based caption sampling (VBCS), which prioritizes the use of captions that are estimated to be highly valid during training, and 2) weighted caption smoothing (WCS), which applies smoothing only to the relevant words the reference caption to reflect multiple reference captions simultaneously. Experiments show that our proposed methods improve CIDEr by 2.6 points and BLEU4 by 0.9 points from baseline on the MSCOCO dataset.
Deep-learning models for language generation tasks tend to produce repetitive output. Various methods have been proposed to encourage lexical diversity during decoding, but this often comes at a cost to the perceived fluency and adequacy of the outpu
t. In this work, we propose to ameliorate this cost by using an Imitation Learning approach to explore the level of diversity that a language generation model can reliably produce. Specifically, we augment the decoding process with a meta-classifier trained to distinguish which words at any given timestep will lead to high-quality output. We focus our experiments on concept-to-text generation where models are sensitive to the inclusion of irrelevant words due to the strict relation between input and output. Our analysis shows that previous methods for diversity underperform in this setting, while human evaluation suggests that our proposed method achieves a high level of diversity with minimal effect on the output's fluency and adequacy.
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
