Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userMultilingual Dependency Parsing for Low-Resource African Languages: Case Studies on Bambara, Wolof, and Yoruba
تحليل التبعية متعددة اللغات لغات الأفريقية المنخفضة: دراسات الحالة على Bambara، Wolof، و Yoruba
258
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تصف هذه الورقة منهجية لنقل المعرفة النحوية بين لغات الموارد عالية الموارد إلى لغات الموارد المنخفضة للغاية. تتألف المنهجية في الاستفادة من نموذج الانتباه الذاتي متعدد اللغات المحدد في مجموعات البيانات الكبيرة لتطوير نموذج متعدد اللغات متعدد اللغات يمكن أن يتوقع التشريحات التبعية الشاملة لثلاثة لغات موارد منخفضة الأفريقية. تشمل التعليقات التوضيحية UD جزءا عالميا من الكلام والميزات المورفولوجية وميمرات وأشجار الاعتماد. في تجاربنا، استخدمنا تضييق كلمة متعددة اللغات وما مجموعه 11 تبعا عالميا Treebanks تم استخلاصها من ثلاثة لغات موارد عالية (الإنجليزية والفرنسية والنرويجية) وثلاثة لغات موارد منخفضة (Bambara و Wolof و Yoruba). قمنا بتطوير نماذج مختلفة لاختبار مجموعات لغة محددة تنطوي على لغات مراقبة معاصرة أو لغات ذات صلة وراثيا. تبين نتائج التجارب أن النماذج متعددة اللغات التي تنطوي على لغات عالية الموارد ولغات منخفضة الموارد مع الاتصال المعاصر بين بعضها البعض يمكن أن توفر نتائج أفضل من المجموعات التي تشمل فقط اللغات التي لا علاقة لها. فيما يتعلق بالعلاقات الوراثية البعيدة، لم نتمكن من استخلاص أي استنتاج بشأن تأثير مجموعات اللغة التي تنطوي على لغات الموارد المنخفضة المختارة، وهي Wolof و Yoruba.
This paper describes a methodology for syntactic knowledge transfer between high-resource languages to extremely low-resource languages. The methodology consists in leveraging multilingual BERT self-attention model pretrained on large datasets to develop a multilingual multi-task model that can predict Universal Dependencies annotations for three African low-resource languages. The UD annotations include universal part-of-speech, morphological features, lemmas, and dependency trees. In our experiments, we used multilingual word embeddings and a total of 11 Universal Dependencies treebanks drawn from three high-resource languages (English, French, Norwegian) and three low-resource languages (Bambara, Wolof and Yoruba). We developed various models to test specific language combinations involving contemporary contact languages or genetically related languages. The results of the experiments show that multilingual models that involve high-resource languages and low-resource languages with contemporary contact between each other can provide better results than combinations that only include unrelated languages. As far genetic relationships are concerned, we could not draw any conclusion regarding the impact of language combinations involving the selected low-resource languages, namely Wolof and Yoruba.
References used
https://aclanthology.org/
rate research
Read More
This paper describes TenTrans' submission to WMT21 Multilingual Low-Resource Translation shared task for the Romance language pairs. This task focuses on improving translation quality from Catalan to Occitan, Romanian and Italian, with the assistance
of related high-resource languages. We mainly utilize back-translation, pivot-based methods, multilingual models, pre-trained model fine-tuning, and in-domain knowledge transfer to improve the translation quality. On the test set, our best-submitted system achieves an average of 43.45 case-sensitive BLEU scores across all low-resource pairs. Our data, code, and pre-trained models used in this work are available in TenTrans evaluation examples.
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.
This paper describes Charles University sub-mission for Terminology translation shared task at WMT21. The objective of this task is to design a system which translates certain terms based on a provided terminology database, while preserving high over
all translation quality. We competed in English-French language pair. Our approach is based on providing the desired translations alongside the input sentence and training the model to use these provided terms. We lemmatize the terms both during the training and inference, to allow the model to learn how to produce correct surface forms of the words, when they differ from the forms provided in the terminology database.
In this work, we investigate methods for the challenging task of translating between low- resource language pairs that exhibit some level of similarity. In particular, we consider the utility of transfer learning for translating between several Indo-
European low-resource languages from the Germanic and Romance language families. In particular, we build two main classes of transfer-based systems to study how relatedness can benefit the translation performance. The primary system fine-tunes a model pre-trained on a related language pair and the contrastive system fine-tunes one pre-trained on an unrelated language pair. Our experiments show that although relatedness is not necessary for transfer learning to work, it does benefit model performance.
Recent work has shown that monolingual masked language models learn to represent data-driven notions of language variation which can be used for domain-targeted training data selection. Dataset genre labels are already frequently available, yet remai
n largely unexplored in cross-lingual setups. We harness this genre metadata as a weak supervision signal for targeted data selection in zero-shot dependency parsing. Specifically, we project treebank-level genre information to the finer-grained sentence level, with the goal to amplify information implicitly stored in unsupervised contextualized representations. We demonstrate that genre is recoverable from multilingual contextual embeddings and that it provides an effective signal for training data selection in cross-lingual, zero-shot scenarios. For 12 low-resource language treebanks, six of which are test-only, our genre-specific methods significantly outperform competitive baselines as well as recent embedding-based methods for data selection. Moreover, genre-based data selection provides new state-of-the-art results for three of these target languages.
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
