Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userA Study of Morphological Robustness of Neural Machine Translation
دراسة متانة مورفولوجية للترجمة الآلية العصبية
267
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
في هذا العمل، نحلل متانة أنظمة الترجمة الآلية العصبية نحو الاضطرابات النحوية في المصدر.على وجه الخصوص، نركز على اضطرابات الانعطاف المورفولوجي.بينما تمت دراسة هذا مؤخرا للغة الإنجليزية → French (Morpheus) (Tan et al.، 2020)، فمن غير الواضح كيف تمتد هذا إلى أي أنظمة ترجمة إنجليزية →.نقترح Morpheus - متعدد اللغات التي تستخدم قواميس Unimorph لتحديد اضطرابات مورفولوجية للمصدر الذي يؤثر سلبا على نماذج الترجمة.جنبا إلى جنب مع تحليل أنظمة MT المسبقة للحكانات، نقوم بتدريب وتحليل الأنظمة لمدة 11 أزواج لغة باستخدام كوربوس TED متعددة اللغات (Qi et al.، 2018).نحن نقارن أيضا هذا مع الأخطاء الفعلية من مكبرات البيانات غير الأصلية باستخدام مجموعات بيانات تصحيح الأخطاء النحوية.أخيرا، نقدم تحليلا نوعيا وكميا لأغاني أي أنظمة ترجمة إنجليزية →.
In this work, we analyze the robustness of neural machine translation systems towards grammatical perturbations in the source. In particular, we focus on morphological inflection related perturbations. While this has been recently studied for English→French (MORPHEUS) (Tan et al., 2020), it is unclear how this extends to Any→English translation systems. We propose MORPHEUS-MULTILINGUAL that utilizes UniMorph dictionaries to identify morphological perturbations to source that adversely affect the translation models. Along with an analysis of state-of-the-art pretrained MT systems, we train and analyze systems for 11 language pairs using the multilingual TED corpus (Qi et al., 2018). We also compare this to actual errors of non-native speakers using Grammatical Error Correction datasets. Finally, we present a qualitative and quantitative analysis of the robustness of Any→English translation systems.
References used
https://aclanthology.org/
rate research
Read More
Neural machine translation (NMT) models are data-driven and require large-scale training corpus. In practical applications, NMT models are usually trained on a general domain corpus and then fine-tuned by continuing training on the in-domain corpus.
However, this bears the risk of catastrophic forgetting that the performance on the general domain is decreased drastically. In this work, we propose a new continual learning framework for NMT models. We consider a scenario where the training is comprised of multiple stages and propose a dynamic knowledge distillation technique to alleviate the problem of catastrophic forgetting systematically. We also find that the bias exists in the output linear projection when fine-tuning on the in-domain corpus, and propose a bias-correction module to eliminate the bias. We conduct experiments on three representative settings of NMT application. Experimental results show that the proposed method achieves superior performance compared to baseline models in all settings.
Recent research questions the importance of the dot-product self-attention in Transformer models and shows that most attention heads learn simple positional patterns. In this paper, we push further in this research line and propose a novel substitute
mechanism for self-attention: Recurrent AtteNtion (RAN) . RAN directly learns attention weights without any token-to-token interaction and further improves their capacity by layer-to-layer interaction. Across an extensive set of experiments on 10 machine translation tasks, we find that RAN models are competitive and outperform their Transformer counterpart in certain scenarios, with fewer parameters and inference time. Particularly, when apply RAN to the decoder of Transformer, there brings consistent improvements by about +0.5 BLEU on 6 translation tasks and +1.0 BLEU on Turkish-English translation task. In addition, we conduct extensive analysis on the attention weights of RAN to confirm their reasonableness. Our RAN is a promising alternative to build more effective and efficient NMT models.
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.
We propose a data augmentation method for neural machine translation. It works by interpreting language models and phrasal alignment causally. Specifically, it creates augmented parallel translation corpora by generating (path-specific) counterfactua
l aligned phrases. We generate these by sampling new source phrases from a masked language model, then sampling an aligned counterfactual target phrase by noting that a translation language model can be interpreted as a Gumbel-Max Structural Causal Model (Oberst and Sontag, 2019). Compared to previous work, our method takes both context and alignment into account to maintain the symmetry between source and target sequences. Experiments on IWSLT'15 English → Vietnamese, WMT'17 English → German, WMT'18 English → Turkish, and WMT'19 robust English → French show that the method can improve the performance of translation, backtranslation and translation robustness.
Data augmentation, which refers to manipulating the inputs (e.g., adding random noise,masking specific parts) to enlarge the dataset,has been widely adopted in machine learning. Most data augmentation techniques operate on a single input, which limit
s the diversity of the training corpus. In this paper, we propose a simple yet effective data augmentation technique for neural machine translation, mixSeq, which operates on multiple inputs and their corresponding targets. Specifically, we randomly select two input sequences,concatenate them together as a longer input aswell as their corresponding target sequencesas an enlarged target, and train models on theaugmented dataset. Experiments on nine machine translation tasks demonstrate that such asimple method boosts the baselines by a non-trivial margin. Our method can be further combined with single input based data augmentation methods to obtain further improvements.
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
