Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userEfficient Multilingual Text Classification for Indian Languages
كفاءة النص متعدد اللغات التصنيف اللغات الهندية
527
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
الهند هي واحدة من أغنى مراكز اللغات على الأرض وهي متنوعة للغاية وتعدد اللغات. ولكن بصرف النظر عن عدد قليل من اللغات الهندية، ما زال معظمهم يعتبرون فقراء الموارد. نظرا لأن معظم تقنيات NLP تتطلب معرفة لغوية لا يمكن تطويرها إلا من قبل الخبراء والمتحدثين الأصليين في هذه اللغة أو أنها تتطلب الكثير من البيانات المسمى باهظة الثمن مرة أخرى لتوليد، فإن مهمة تصنيف النص تصبح تحديا لمعظم الهندي اللغات. الهدف الرئيسي من هذه الورقة هو معرفة كيف يمكن للمرء الاستفادة من التشابه المعجمي الموجود باللغات الهندية في سيناريو متعدد اللغات. هل يمكن إعادة استخدام نموذج تصنيف مدرب على لغة هندية واحدة لغات هندية أخرى؟ لذا، أجرينا تصنيف نصي بالرصاص عن طريق استغلال التشابه المعجمي وملاحظ أن طرازنا ينفذ بشكل أفضل في تلك الحالات حيث يتداخل المفردات بين مجموعات البيانات اللغوية كحد أقصى. تؤكد تجاربنا أيضا أن نموذجا واحدا متعدد اللغات مدرب عبر رابط استغلال اللغة يتفوق على الأساس من الهوامش الهامة.
India is one of the richest language hubs on the earth and is very diverse and multilingual. But apart from a few Indian languages, most of them are still considered to be resource poor. Since most of the NLP techniques either require linguistic knowledge that can only be developed by experts and native speakers of that language or they require a lot of labelled data which is again expensive to generate, the task of text classification becomes challenging for most of the Indian languages. The main objective of this paper is to see how one can benefit from the lexical similarity found in Indian languages in a multilingual scenario. Can a classification model trained on one Indian language be reused for other Indian languages? So, we performed zero-shot text classification via exploiting lexical similarity and we observed that our model performs best in those cases where the vocabulary overlap between the language datasets is maximum. Our experiments also confirm that a single multilingual model trained via exploiting language relatedness outperforms the baselines by significant margins.
References used
https://aclanthology.org/
rate research
Read More
India is known as the land of many tongues and dialects. Neural machine translation (NMT) is the current state-of-the-art approach for machine translation (MT) but performs better only with large datasets which Indian languages usually lack, making t
his approach infeasible. So, in this paper, we address the problem of data scarcity by efficiently training multilingual and multilingual multi domain NMT systems involving languages of the ?????? ????????????. We are proposing the technique for using the joint domain and language tags in a multilingual setup. We draw three major conclusions from our experiments: (i) Training a multilingual system via exploiting lexical similarity based on language family helps in achieving an overall average improvement of ?.?? ???? ?????? over bilingual baselines, (ii) Technique of incorporating domain information into the language tokens helps multilingual multi-domain system in getting a significant average improvement of ? ???? ?????? over the baselines, (iii) Multistage fine-tuning further helps in getting an improvement of ?-?.? ???? ?????? for the language pair of interest.
This paper describes the work and the systems submitted by the IIIT-Hyderbad team in the WAT 2021 MultiIndicMT shared task. The task covers 10 major languages of the Indian subcontinent. For the scope of this task, we have built multilingual systems
for 20 translation directions namely English-Indic (one-to- many) and Indic-English (many-to-one). Individually, Indian languages are resource poor which hampers translation quality but by leveraging multilingualism and abundant monolingual corpora, the translation quality can be substantially boosted. But the multilingual systems are highly complex in terms of time as well as computational resources. Therefore, we are training our systems by efficiently se- lecting data that will actually contribute to most of the learning process. Furthermore, we are also exploiting the language related- ness found in between Indian languages. All the comparisons were made using BLEU score and we found that our final multilingual sys- tem significantly outperforms the baselines by an average of 11.3 and 19.6 BLEU points for English-Indic (en-xx) and Indic-English (xx- en) directions, respectively.
Transformer-based methods are appealing for multilingual text classification, but common research benchmarks like XNLI (Conneau et al., 2018) do not reflect the data availability and task variety of industry applications. We present an empirical comp
arison of transformer-based text classification models in a variety of practical monolingual and multilingual pretraining and fine-tuning settings. We evaluate these methods on two distinct tasks in five different languages. Departing from prior work, our results show that multilingual language models can outperform monolingual ones in some downstream tasks and target languages. We additionally show that practical modifications such as task- and domain-adaptive pretraining and data augmentation can improve classification performance without the need for additional labeled data.
Adapter modules have emerged as a general parameter-efficient means to specialize a pretrained encoder to new domains. Massively multilingual transformers (MMTs) have particularly benefited from additional training of language-specific adapters. Howe
ver, this approach is not viable for the vast majority of languages, due to limitations in their corpus size or compute budgets. In this work, we propose MAD-G (Multilingual ADapter Generation), which contextually generates language adapters from language representations based on typological features. In contrast to prior work, our time- and space-efficient MAD-G approach enables (1) sharing of linguistic knowledge across languages and (2) zero-shot inference by generating language adapters for unseen languages. We thoroughly evaluate MAD-G in zero-shot cross-lingual transfer on part-of-speech tagging, dependency parsing, and named entity recognition. While offering (1) improved fine-tuning efficiency (by a factor of around 50 in our experiments), (2) a smaller parameter budget, and (3) increased language coverage, MAD-G remains competitive with more expensive methods for language-specific adapter training across the board. Moreover, it offers substantial benefits for low-resource languages, particularly on the NER task in low-resource African languages. Finally, we demonstrate that MAD-G's transfer performance can be further improved via: (i) multi-source training, i.e., by generating and combining adapters of multiple languages with available task-specific training data; and (ii) by further fine-tuning generated MAD-G adapters for languages with monolingual data.
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.
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
