Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userTraining Data Augmentation for Code-Mixed Translation
نقل بيانات التدريب الترجمة المختلطة
320
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
الترجمة الآلية للمدخلات المزدوجة التي تم إنشاؤها بواسطة المستخدمين إلى اللغة الإنجليزية ذات أهمية حاسمة في التطبيقات مثل البحث على شبكة الإنترنت والإعلانات المستهدفة.نحن نتطلع إلى ندرة البيانات التدريبية الموازية لتدريب هذه النماذج عن طريق تصميم استراتيجية لتحويل مصادر البيانات المتوازية الموجزة غير المزججة الحالية إلى البيانات الموازية المختلطة.نقدم إجراء يستند إلى M-Bert إلى مكونه الأساسي الذي يمكن أن يكون نموذج وضع العلامات ثلاثية التسلسلات، والتي يمكن تدريبها على Corpus محدود مختلط رمزيا وحدها.نعرض زيادة بنسبة 5.8 نقطة في بلو على الجمل المختلطة شفرة الشفرة من خلال تدريب نموذج الترجمة باستخدام استراتيجية تكبير البيانات الخاصة بنا حول مهمة الترجمة من اللغة الهندية-الإنجليزية المختلطة.
Machine translation of user-generated code-mixed inputs to English is of crucial importance in applications like web search and targeted advertising. We address the scarcity of parallel training data for training such models by designing a strategy of converting existing non-code-mixed parallel data sources to code-mixed parallel data. We present an m-BERT based procedure whose core learnable component is a ternary sequence labeling model, that can be trained with a limited code-mixed corpus alone. We show a 5.8 point increase in BLEU on heavily code-mixed sentences by training a translation model using our data augmentation strategy on an Hindi-English code-mixed translation task.
References used
https://aclanthology.org/
rate research
Read More
Non-autoregressive Transformer is a promising text generation model. However, current non-autoregressive models still fall behind their autoregressive counterparts in translation quality. We attribute this accuracy gap to the lack of dependency model
ing among decoder inputs. In this paper, we propose CNAT, which learns implicitly categorical codes as latent variables into the non-autoregressive decoding. The interaction among these categorical codes remedies the missing dependencies and improves the model capacity. Experiment results show that our model achieves comparable or better performance in machine translation tasks than several strong baselines.
Unsupervised neural machine translation (UNMT) that relies solely on massive monolingual corpora has achieved remarkable results in several translation tasks. However, in real-world scenarios, massive monolingual corpora do not exist for some extreme
ly low-resource languages such as Estonian, and UNMT systems usually perform poorly when there is not adequate training corpus for one language. In this paper, we first define and analyze the unbalanced training data scenario for UNMT. Based on this scenario, we propose UNMT self-training mechanisms to train a robust UNMT system and improve its performance in this case. Experimental results on several language pairs show that the proposed methods substantially outperform conventional UNMT systems.
Code-mixing has become a moving method of communication among multilingual speakers. Most of the social media content of the multilingual societies are written in code-mixed text. However, most of the current translation systems neglect to convert co
de-mixed texts to a standard language. Most of the user written code-mixed content in social media remains unprocessed due to the unavailability of linguistic resource such as parallel corpus. This paper proposes a Neural Machine Translation(NMT) model to translate the Sinhala-English code-mixed text to the Sinhala language. Due to the limited resources available for Sinhala-English code-mixed(SECM) text, a parallel corpus is created with SECM sentences and Sinhala sentences. Srilankan social media sites contain SECM texts more frequently than the standard languages. The model proposed for code-mixed text translation in this study is a combination of Encoder-Decoder framework with LSTM units and Teachers Forcing Algorithm. The translated sentences from the model are evaluated using BLEU(Bilingual Evaluation Understudy) metric. Our model achieved a remarkable BLEU score for the translation.
Extracting keyphrases that summarize the main points of a document is a fundamental task in natural language processing. Supervised approaches to keyphrase extraction(KPE) are largely developed based on the assumption that the training data is fully
annotated. However, due to the difficulty of keyphrase annotating, KPE models severely suffer from incomplete annotated problem in many scenarios. To this end, we propose a more robust training method that learns to mitigate the misguidance brought by unlabeled keyphrases. We introduce negative sampling to adjust training loss, and conduct experiments under different scenarios. Empirical studies on synthetic datasets and open domain dataset show that our model is robust to incomplete annotated problem and surpasses prior baselines. Extensive experiments on five scientific domain datasets of different scales demonstrate that our model is competitive with the state-of-the-art method.
This paper describes the participation of the UoB-NLP team in the ProfNER-ST shared subtask 7a. The task was aimed at detecting the mention of professions in social media text. Our team experimented with two methods of improving the performance of pr
e-trained models: Specifically, we experimented with data augmentation through translation and the merging of multiple language inputs to meet the objective of the task. While the best performing model on the test data consisted of mBERT fine-tuned on augmented data using back-translation, the improvement is minor possibly because multi-lingual pre-trained models such as mBERT already have access to the kind of information provided through back-translation and bilingual data.
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
