Related papers: It's Like Python But: Towards Supporting Transfer …
Transfer learning based on pretraining language models on a large amount of raw data has become a new norm to reach state-of-the-art performance in NLP. Still, it remains unclear how this approach should be applied for unseen languages that…
Neural machine translation is known to require large numbers of parallel training sentences, which generally prevent it from excelling on low-resource language pairs. This thesis explores the use of cross-lingual transfer learning on neural…
The transfer learning toolkit wraps the codes of 17 transfer learning models and provides integrated interfaces, allowing users to use those models by calling a simple function. It is easy for primary researchers to use this toolkit and to…
Multilingual machine translation systems aim to make knowledge accessible across languages, yet learning effective cross-lingual representations remains challenging. These challenges are especially pronounced for low-resource languages,…
The availability of abundant labeled data in recent years led the researchers to introduce a methodology called transfer learning, which utilizes existing data in situations where there are difficulties in collecting new annotated data.…
Large language models (LLMs) have achieved state-of-the-art performance in various software engineering tasks, including error detection, clone detection, and code translation, primarily leveraging high-resource programming languages like…
Cross-lingual transfer is a leading technique for parsing low-resource languages in the absence of explicit supervision. Simple `direct transfer' of a learned model based on a multilingual input encoding has provided a strong benchmark.…
Style is a significant component of natural language text, reflecting a change in the tone of text while keeping the underlying information the same. Even though programming languages have strict syntax rules, they also have style. Code can…
Learning to transfer considers learning solutions to tasks in a such way that relevant knowledge can be transferred from known task solutions to new, related tasks. This is important for general learning, as well as for improving the…
Knowledge transfer is fundamental to human collaboration and is therefore common in software engineering. Pair programming is a prominent instance. With the rise of AI coding assistants, developers now not only work with human partners but…
Most Transformer language models are primarily pretrained on English text, limiting their use for other languages. As the model sizes grow, the performance gap between English and other languages with fewer compute and data resources…
Transfer learning has been proven as an effective technique for neural machine translation under low-resource conditions. Existing methods require a common target language, language relatedness, or specific training tricks and regimes. We…
The feedback provided by current testing education tools about the deficiencies in a student's test suite either mimics industry code coverage tools or lists specific instructor test cases that are missing from the student's test suite.…
This study examines how AI code assistants shape novice programmers experiences during a two-part exam in an introductory programming course. In the first part, students completed a programming task with access to AI support; in the second,…
Code pre-trained models (CodePTMs) have recently demonstrated a solid capacity to process various software intelligence tasks, e.g., code clone detection, code translation, and code summarization. The current mainstream method that deploys…
We conduct the first empirical study on using knowledge transfer to improve the generalization ability of large language models (LLMs) in software engineering tasks, which often require LLMs to generalize beyond their training data. Our…
Recent progress in neural machine translation is directed towards larger neural networks trained on an increasing amount of hardware resources. As a result, NMT models are costly to train, both financially, due to the electricity and…
Transfer learning is a vital technique that generalizes models trained for one setting or task to other settings or tasks. For example in speech recognition, an acoustic model trained for one language can be used to recognize speech in…
Developing automated and smart software vulnerability detection models has been receiving great attention from both research and development communities. One of the biggest challenges in this area is the lack of code samples for all…
Generation of pseudo-code descriptions of legacy source code for software maintenance is a manually intensive task. Recent encoder-decoder language models have shown promise for automating pseudo-code generation for high resource…