Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userCo-Teaching Student-Model through Submission Results of Shared Task
نموذج الطالب التدريس من خلال نتائج التقديم للمهمة المشتركة
213
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
المهام المشتركة لها تاريخ طويل وأصبحت السائدة لأبحاث NLP. تتطلب معظم المهام المشتركة المشاركين تقديم مخرجات وأوصاف النظام فقط. من غير المألوف أن تطلب المهمة المشتركة تقديم النظام نفسه بسبب قضايا الترخيص وفروق التنفيذ. لذلك، يتم التخلي عن العديد من الأنظمة دون استخدامها في التطبيقات الحقيقية أو المساهمة في أنظمة أفضل. في هذا البحث، نقترح مخططا للاستفادة من كل تلك النظم التي شاركت في المهام المشتركة. نستخدم جميع مخرجات النظام المشارك كمعلمي المهام في هذا المخطط وتطوير نموذج جديد كطالب يهدف إلى تعلم خصائص كل نظام. نسمي هذا التدريس المشترك بين المخطط. "هذا المخطط يخلق نظام موحد يؤدي أفضل من أفضل نظام المهام الموحد. يتطلب فقط مخرجات النظام، والجهد الإضافي قليلا هناك حاجة إلى المشاركين والمنظمين. نحن نطبق هذا المخطط على المهمة المشتركة Shinra2019-JP، التي لديها تسعة مشاركين بدقة مختلفة من الإخراج، مما يؤكد أن النظام الموحد يتفوق على أفضل نظام. علاوة على ذلك، تم إصدار الرمز المستخدم في تجاربنا.
Shared tasks have a long history and have become the mainstream of NLP research. Most of the shared tasks require participants to submit only system outputs and descriptions. It is uncommon for the shared task to request submission of the system itself because of the license issues and implementation differences. Therefore, many systems are abandoned without being used in real applications or contributing to better systems. In this research, we propose a scheme to utilize all those systems which participated in the shared tasks. We use all participated system outputs as task teachers in this scheme and develop a new model as a student aiming to learn the characteristics of each system. We call this scheme Co-Teaching.'' This scheme creates a unified system that performs better than the task's single best system. It only requires the system outputs, and slightly extra effort is needed for the participants and organizers. We apply this scheme to the SHINRA2019-JP'' shared task, which has nine participants with various output accuracies, confirming that the unified system outperforms the best system. Moreover, the code used in our experiments has been released.
References used
https://aclanthology.org/
rate research
Read More
The Shared Task on Evaluating Accuracy focused on techniques (both manual and automatic) for evaluating the factual accuracy of texts produced by neural NLG systems, in a sports-reporting domain. Four teams submitted evaluation techniques for this ta
sk, using very different approaches and techniques. The best-performing submissions did encouragingly well at this difficult task. However, all automatic submissions struggled to detect factual errors which are semantically or pragmatically complex (for example, based on incorrect computation or inference).
In this paper we discuss an ongoing effort to enrich students' learning by involving them in sense tagging. The main goal is to lead students to discover how we can represent meaning and where the limits of our current theories lie. A subsidiary goal
is to create sense tagged corpora and an accompanying linked lexicon (in our case wordnets). We present the results of tagging several texts and suggest some ways in which the tagging process could be improved. Two authors of this paper present their own experience as students. Overall, students reported that they found the tagging an enriching experience. The annotated corpora and changes to the wordnet are made available through the NTU multilingual corpus and associated wordnets (NTU-MC).
We present the University of Central Florida systems for the LoResMT 2021 Shared Task, participating in the English-Irish and English-Marathi translation pairs. We focused our efforts on constrained track of the task, using transfer learning and subw
ord segmentation to enhance our models given small amounts of training data. Our models achieved the highest BLEU scores on the fully constrained tracks of English-Irish, Irish-English, and Marathi-English with scores of 13.5, 21.3, and 17.9 respectively
We present the BME submission for the SIGMORPHON 2021 Task 0 Part 1, Generalization Across Typologically Diverse Languages shared task. We use an LSTM encoder-decoder model with three step training that is first trained on all languages, then fine-tu
ned on each language family and finally fine-tuned on individual languages. We use a different type of data augmentation technique in the first two steps. Our system outperformed the only other submission. Although it remains worse than the Transformer baseline released by the organizers, our model is simpler and our data augmentation techniques are easily applicable to new languages. We perform ablation studies and show that the augmentation techniques and the three training steps often help but sometimes have a negative effect. Our code is publicly available.
This paper describes Papago submission to the WMT 2021 Quality Estimation Task 1: Sentence-level Direct Assessment. Our multilingual Quality Estimation system explores the combination of Pretrained Language Models and Multi-task Learning architecture
s. We propose an iterative training pipeline based on pretraining with large amounts of in-domain synthetic data and finetuning with gold (labeled) data. We then compress our system via knowledge distillation in order to reduce parameters yet maintain strong performance. Our submitted multilingual systems perform competitively in multilingual and all 11 individual language pair settings including zero-shot.
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
