Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userMixup Decoding for Diverse Machine Translation
مزيج فك التشفير للحصول على ترجمة آلية متنوعة
293
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تهدف الترجمة الآلية المتنوعة إلى توليد ترجمات لغة مستهدفة مختلفة عن عقوبة لغة مصدر معينة. للاستفادة من العلاقة الخطية في مجال الجملة الكامنة التي أدخلت من خلال التدريب المزيج، نقترح طريقة رواية، خلطتيبات، لتوليد ترجمات مختلفة عن جملة الإدخال من خلال الاسترجاء الخطي مع أزواج من الجملة المختلفة من كوربوس التدريب أثناء فك التشفير. لزيادة تحسين الإخلاص وتنوع الترجمات، نقترح مقاربتين بسيطة ولكنها فعالة لتحديد أزواج جملة متنوعة في كوربوس التدريب وضبط وزن الاستيفاء لكل زوج في المقابل. علاوة على ذلك، من خلال التحكم في وزن الاستيفاء، يمكن لطريقتنا تحقيق المفاضلة بين الإخلاص والتنوع دون أي تدريب إضافي، وهو مطلوب في معظم الأساليب السابقة. تتم تجارب WMT'16 EN-RO، WMT'14 EN-DE، و WMT'17 Zh-en لإظهار أن طريقتنا تتفوق بشكل كبير على جميع أساليب الترجمة الآلية المتنوعة السابقة.
Diverse machine translation aims at generating various target language translations for a given source language sentence. To leverage the linear relationship in the sentence latent space introduced by the mixup training, we propose a novel method, MixDiversity, to generate different translations for the input sentence by linearly interpolating it with different sentence pairs sampled from the training corpus during decoding. To further improve the faithfulness and diversity of the translations, we propose two simple but effective approaches to select diverse sentence pairs in the training corpus and adjust the interpolation weight for each pair correspondingly. Moreover, by controlling the interpolation weight, our method can achieve the trade-off between faithfulness and diversity without any additional training, which is required in most of the previous methods. Experiments on WMT'16 en-ro, WMT'14 en-de, and WMT'17 zh-en are conducted to show that our method substantially outperforms all previous diverse machine translation methods.
References used
https://aclanthology.org/
rate research
Read More
Most current neural machine translation models adopt a monotonic decoding order of either left-to-right or right-to-left. In this work, we propose a novel method that breaks up the limitation of these decoding orders, called Smart-Start decoding. Mor
e specifically, our method first predicts a median word. It starts to decode the words on the right side of the median word and then generates words on the left. We evaluate the proposed Smart-Start decoding method on three datasets. Experimental results show that the proposed method can significantly outperform strong baseline models.
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.
The shift to neural models in Referring Expression Generation (REG) has enabled more natural set-ups, but at the cost of interpretability. We argue that integrating pragmatic reasoning into the inference of context-agnostic generation models could re
concile traits of traditional and neural REG, as this offers a separation between context-independent, literal information and pragmatic adaptation to context. With this in mind, we apply existing decoding strategies from discriminative image captioning to REG and evaluate them in terms of pragmatic informativity, likelihood to ground-truth annotations and linguistic diversity. Our results show general effectiveness, but a relatively small gain in informativity, raising important questions for REG in general.
The dominant paradigm for semantic parsing in recent years is to formulate parsing as a sequence-to-sequence task, generating predictions with auto-regressive sequence decoders. In this work, we explore an alternative paradigm. We formulate semantic
parsing as a dependency parsing task, applying graph-based decoding techniques developed for syntactic parsing. We compare various decoding techniques given the same pre-trained Transformer encoder on the TOP dataset, including settings where training data is limited or contains only partially-annotated examples. We find that our graph-based approach is competitive with sequence decoders on the standard setting, and offers significant improvements in data efficiency and settings where partially-annotated data is available.
Encoder-decoder models have been commonly used for many tasks such as machine translation and response generation. As previous research reported, these models suffer from generating redundant repetition. In this research, we propose a new mechanism f
or encoder-decoder models that estimates the semantic difference of a source sentence before and after being fed into the encoder-decoder model to capture the consistency between two sides. This mechanism helps reduce repeatedly generated tokens for a variety of tasks. Evaluation results on publicly available machine translation and response generation datasets demonstrate the effectiveness of our proposal.
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
