Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userLearning Contextualised Cross-lingual Word Embeddings and Alignments for Extremely Low-Resource Languages Using Parallel Corpora
التعلم السياقية الكلمات المتبقية الكلمة ومحاذاة لغات الموارد المنخفضة للغاية باستخدام Corpora الموازي
310
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
نقترح نهجا جديدا لتعلم تضمين الكلمات المتبادلة عبر السياق بناء على كائن مواز صغير (E.G. بضع مئات من أزواج الجملة). تتمتع طريقتنا بدمج الكلمات عبر نموذج فك تشفير LSTM يترجم في وقت واحد وإعادة بناء جملة مدخلات. من خلال تقاسم المعلمات النموذجية بين لغات مختلفة، يدرك نموذجنا بشكل مشترك كلمة تضمين الكلمة في مساحة شائعة تبادل اللغات. نقترح أيضا الجمع بين وظائف الكلمة والكلمات الفرعية للاستفادة من أوجه التشابه الهجري عبر لغات مختلفة. نحن نؤدي تجاربنا على بيانات العالم الحقيقي من اللغات المهددة بالانقراض، وهي يونغينغ نا، Shipibo-Konibo، و Griko. تجاربنا على تحيزي المعجم الثنائي اللغة ومهام محاذاة الكلمات تظهر أن نموذجنا يفوق على الأساليب الحالية من قبل هامش كبير لمعظم أزواج اللغات. توضح هذه النتائج أنه على خلاف المعتقد الشائع، فإن نموذج الترجمة المشترك - ترميز الترميز مفيد لتعلم التمثيلات المتبادلة حتى في ظروف الموارد المنخفضة للغاية. علاوة على ذلك، يعمل نموذجنا أيضا بشكل جيد في ظروف الموارد العالية، وتحقيق الأداء الحديث في مهمة محاذاة الكلمة باللغة الألمانية.
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 translates 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.
References used
https://aclanthology.org/
rate research
Read More
Cross-lingual word embeddings (CLWEs) have proven indispensable for various natural language processing tasks, e.g., bilingual lexicon induction (BLI). However, the lack of data often impairs the quality of representations. Various approaches requiri
ng only weak cross-lingual supervision were proposed, but current methods still fail to learn good CLWEs for languages with only a small monolingual corpus. We therefore claim that it is necessary to explore further datasets to improve CLWEs in low-resource setups. In this paper we propose to incorporate data of related high-resource languages. In contrast to previous approaches which leverage independently pre-trained embeddings of languages, we (i) train CLWEs for the low-resource and a related language jointly and (ii) map them to the target language to build the final multilingual space. In our experiments we focus on Occitan, a low-resource Romance language which is often neglected due to lack of resources. We leverage data from French, Spanish and Catalan for training and evaluate on the Occitan-English BLI task. By incorporating supporting languages our method outperforms previous approaches by a large margin. Furthermore, our analysis shows that the degree of relatedness between an incorporated language and the low-resource language is critically important.
Cross-lingual word embeddings provide a way for information to be transferred between languages. In this paper we evaluate an extension of a joint training approach to learning cross-lingual embeddings that incorporates sub-word information during tr
aining. This method could be particularly well-suited to lower-resource and morphologically-rich languages because it can be trained on modest size monolingual corpora, and is able to represent out-of-vocabulary words (OOVs). We consider bilingual lexicon induction, including an evaluation focused on OOVs. We find that this method achieves improvements over previous approaches, particularly for OOVs.
We translate a closed text that is known in advance and available in many languages into a new and severely low resource language. Most human translation efforts adopt a portionbased approach to translate consecutive pages/chapters in order, which ma
y not suit machine translation. We compare the portion-based approach that optimizes coherence of the text locally with the random sampling approach that increases coverage of the text globally. Our results show that the random sampling approach performs better. When training on a seed corpus of ∼1,000 lines from the Bible and testing on the rest of the Bible (∼30,000 lines), random sampling gives a performance gain of +11.0 BLEU using English as a simulated low resource language, and +4.9 BLEU using Eastern Pokomchi, a Mayan language. Furthermore, we compare three ways of updating machine translation models with increasing amount of human post-edited data through iterations. We find that adding newly post-edited data to training after vocabulary update without self-supervision performs the best. We propose an algorithm for human and machine to work together seamlessly to translate a closed text into a severely low resource language.
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.
The widespread presence of offensive language on social media motivated the development of systems capable of recognizing such content automatically. Apart from a few notable exceptions, most research on automatic offensive language identification ha
s dealt with English. To address this shortcoming, we introduce MOLD, the Marathi Offensive Language Dataset. MOLD is the first dataset of its kind compiled for Marathi, thus opening a new domain for research in low-resource Indo-Aryan languages. We present results from several machine learning experiments on this dataset, including zero-short and other transfer learning experiments on state-of-the-art cross-lingual transformers from existing data in Bengali, English, and Hindi.
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
