هناك مصلحة ناشئة في تطبيق نماذج معالجة اللغة الطبيعية لمهام معالجة التعليمات البرمجية المصدر.أحد المشاكل الرئيسية في تطبيق التعلم العميق لهندسة البرمجيات هو أن الكود المصدري غالبا ما يحتوي على الكثير من المعرفات النادرة، مما يؤدي إلى مفردات ضخمة.نقترح طريقة بسيطة، ولكنها فعالة، بناء على معرفة الهوية المعرفية، للتعامل مع المعرفات خارج المفردات (OOV).يمكن التعامل مع طريقتنا كخطوة مسبقة مسبقا، وبالتالي، تسمح بتنفيذ سهولة.نظرا لأن طريقة إخفاء مصطلحات OOV المقترحة تحسن بشكل كبير من أداء المحول في مهام معالجة التعليمات البرمجية: إكمال التعليمات البرمجية وإصلاح الأخطاء.
There is an emerging interest in the application of natural language processing models to source code processing tasks. One of the major problems in applying deep learning to software engineering is that source code often contains a lot of rare identifiers, resulting in huge vocabularies. We propose a simple, yet effective method, based on identifier anonymization, to handle out-of-vocabulary (OOV) identifiers. Our method can be treated as a preprocessing step and, therefore, allows for easy implementation. We show that the proposed OOV anonymization method significantly improves the performance of the Transformer in two code processing tasks: code completion and bug fixing.
References used
https://aclanthology.org/
We consider the task of linking social media accounts that belong to the same author in an automated fashion on the basis of the content and meta-data of the corresponding document streams. We focus on learning an embedding that maps variable-sized s
We propose CodeQA, a free-form question answering dataset for the purpose of source code comprehension: given a code snippet and a question, a textual answer is required to be generated. CodeQA contains a Java dataset with 119,778 question-answer pai
Conditioned dialogue generation suffers from the scarcity of labeled responses. In this work, we exploit labeled non-dialogue text data related to the condition, which are much easier to collect. We propose a multi-task learning approach to leverage
The exponential growth of the internet and social media in the past decade gave way to the increase in dissemination of false or misleading information. Since the 2016 US presidential election, the term fake news'' became increasingly popular and thi
Detecting out-of-domain (OOD) intents is crucial for the deployed task-oriented dialogue system. Previous unsupervised OOD detection methods only extract discriminative features of different in-domain intents while supervised counterparts can directl