Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userLearning Feature Weights using Reward Modeling for Denoising Parallel Corpora
التعلم ميزة الأوزان باستخدام النمذجة المكافأة ل Denoising Corpora الموازي
223
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تمثل شركة كورسا الكبيرة من الويب موردا ممتازا لتحسين أداء أنظمة الترجمة الآلية العصبية (NMT) عبر العديد من أزواج اللغة. ومع ذلك، نظرا لأن هذه كورسيا صاخبة للغاية، فإن استخدامها محدود إلى حد ما. تركز النهج الحالية للتعامل مع هذه المشكلة أساسا على الترشيح باستخدام الاستدلال أو ميزات واحدة مثل درجات نموذج اللغة أو التشابه الثنائي اللغوي. يقدم هذا العمل نهجا بديلا يتعلم الأوزان لميزات متعددة على مستوى الجملة. يتم استخدام هذه الأوزان الميزة التي تم تحسينها مباشرة لمهمة تحسين أداء الترجمة، وتسجيل الجمل والتصفية في كورسا صاخبة بشكل أكثر فعالية. نحن نقدم نتائج تطبيق هذه التقنية لبناء أنظمة NMT باستخدام Corpus Paracrawl For Estonian-English وإظهار أنه يدق خطوط خطوط ميزة واحدة قوية ومجموعات مصممة باليد. بالإضافة إلى ذلك، نقوم بتحليل حساسية هذه الطريقة لأنواع مختلفة من الضوضاء واستكشاف إذا تعميم الأوزان المستفادة إلى أزواج لغة أخرى باستخدام Corpus Maltese-English Paracrawl Corpus.
Large web-crawled corpora represent an excellent resource for improving the performance of Neural Machine Translation (NMT) systems across several language pairs. However, since these corpora are typically extremely noisy, their use is fairly limited. Current approaches to deal with this problem mainly focus on filtering using heuristics or single features such as language model scores or bi-lingual similarity. This work presents an alternative approach which learns weights for multiple sentence-level features. These feature weights which are optimized directly for the task of improving translation performance, are used to score and filter sentences in the noisy corpora more effectively. We provide results of applying this technique to building NMT systems using the Paracrawl corpus for Estonian-English and show that it beats strong single feature baselines and hand designed combinations. Additionally, we analyze the sensitivity of this method to different types of noise and explore if the learned weights generalize to other language pairs using the Maltese-English Paracrawl corpus.
References used
https://aclanthology.org/
rate research
Read More
We propose a new approach for learning contextualised cross-lingual word embeddings based on a small parallel corpus (e.g. a few hundred sentence pairs). Our method obtains word embeddings via an LSTM encoder-decoder model that simultaneously transla
tes and reconstructs an input sentence. Through sharing model parameters among different languages, our model jointly trains the word embeddings in a common cross-lingual space. We also propose to combine word and subword embeddings to make use of orthographic similarities across different languages. We base our experiments on real-world data from endangered languages, namely Yongning Na, Shipibo-Konibo, and Griko. Our experiments on bilingual lexicon induction and word alignment tasks show that our model outperforms existing methods by a large margin for most language pairs. These results demonstrate that, contrary to common belief, an encoder-decoder translation model is beneficial for learning cross-lingual representations even in extremely low-resource conditions. Furthermore, our model also works well on high-resource conditions, achieving state-of-the-art performance on a German-English word-alignment task.
For task-oriented dialog systems, training a Reinforcement Learning (RL) based Dialog Management module suffers from low sample efficiency and slow convergence speed due to the sparse rewards in RL. To solve this problem, many strategies have been pr
oposed to give proper rewards when training RL, but their rewards lack interpretability and cannot accurately estimate the distribution of state-action pairs in real dialogs. In this paper, we propose a multi-level reward modeling approach that factorizes a reward into a three-level hierarchy: domain, act, and slot. Based on inverse adversarial reinforcement learning, our designed reward model can provide more accurate and explainable reward signals for state-action pairs. Extensive evaluations show that our approach can be applied to a wide range of reinforcement learning-based dialog systems and significantly improves both the performance and the speed of convergence.
The paper presents our submission to the WMT2021 Shared Task on Quality Estimation (QE). We participate in sentence-level predictions of human judgments and post-editing effort. We propose a glass-box approach based on attention weights extracted fro
m machine translation systems. In contrast to the previous works, we directly explore attention weight matrices without replacing them with general metrics (like entropy). We show that some of our models can be trained with a small amount of a high-cost labelled data. In the absence of training data our approach still demonstrates a moderate linear correlation, when trained with synthetic data.
Term and glossary management are vital steps of preparation of every language specialist, and they play a very important role at the stage of education of translation professionals. The growing trend of efficient time management and constant time con
straints we may observe in every job sector increases the necessity of the automatic glossary compilation. Many well-performing bilingual AET systems are based on processing parallel data, however, such parallel corpora are not always available for a specific domain or a language pair. Domain-specific, bilingual access to information and its retrieval based on comparable corpora is a very promising area of research that requires a detailed analysis of both available data sources and the possible extraction techniques. This work focuses on domain-specific automatic terminology extraction from comparable corpora for the English -- Russian language pair by utilizing neural word embeddings.
The present work aims at assigning a complexity score between 0 and 1 to a target word or phrase in a given sentence. For each Single Word Target, a Random Forest Regressor is trained on a feature set consisting of lexical, semantic, and syntactic in
formation about the target. For each Multiword Target, a set of individual word features is taken along with single word complexities in the feature space. The system yielded the Pearson correlation of 0.7402 and 0.8244 on the test set for the Single and Multiword Targets, respectively.
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
