In this paper, we describe an empirical study of data augmentation techniques with various pre-trained language models on the bilingual dataset which was presented at VLSP 2021 - Vietnamese and English-Vietnamese Textual Entailment. We apply machine translation tool to generate new training set from original then investigate compare effectiveness a monolingual multilingual model set. Our experi...

While recurrent neural network language models based on Long Short Term Memory (LSTM) have shown good gains in many automatic speech recognition tasks, Convolutional Neural Network (CNN) language models are relatively new and have not been studied in-depth. In this paper we present an empirical comparison of LSTM and CNN language models on English broadcast news and various conversational telep...

context-dependent modeling is a well-known approach to increase modeling accuracy in continuous speech recognition. the most common way to implement this approach is via triphone modeling. nevertheless, the large number of such models results in several problems in model training, whilst the robust training of such models is often hardly obtained. one approach to solve this problem is via param...

Deployment of model-based testing involves many difficulties that have slowed down its industrial adoption. The leap from traditional scripted testing to model-based testing seems as hard as moving from manual to automatic test execution. Two key factors in the deployment are the language used to define the test models, and the language used for defining the test objectives. Based on our experi...

Agent-based modeling has been criticized for its apparent lack of establishing causality of social phenomena. However, we demonstrate that when coupled with evolutionary computation techniques, agent-based models can be used to evolve plausible agent behaviors that are able to recreate patterns observed in real-world data, from which valuable insights into candidate explanations of the macro-ph...

Prediction of language mistakes is a task introduced by Duolingo as part the Second Language Acquisition Modeling topic that aims to learn from history improve experience learners. Using transfer learning means pre-trained models, we propose framework can actual distribution according which faraway words sentence have higher chance produce errors. To adapt information provided more approaches b...

Large language models have demonstrated outstanding performance on a wide range of tasks such as question answering and code generation. On high level, given an input, model can be used to automatically complete the sequence in statistically-likely way. Based this, users prompt these with instructions or examples, implement variety downstream tasks. Advanced prompting methods even imply interac...

There are two established strategies to create test models: Textual notations require developers to mentally reconstruct the involved graph structures ad hoc; maintenance effort and time are increased. Existing visual notations compel developers to switch frequently between different editors; keeping the resulting test artifacts synchronized is complicated by insufficient tool support. In this ...