اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدDetecting Speech Act Types in Developer Question/Answer Conversations During Bug Repair
314
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
This paper targets the problem of speech act detection in conversations about bug repair. We conduct a Wizard of Oz experiment with 30 professional programmers, in which the programmers fix bugs for two hours, and use a simulated virtual assistant for help. Then, we use an open coding manual annotation procedure to identify the speech act types in the conversations. Finally, we train and evaluate a supervised learning algorithm to automatically detect the speech act types in the conversations. In 30 two-hour conversations, we made 2459 annotations and uncovered 26 speech act types. Our automated detection achieved 69% precision and 50% recall. The key application of this work is to advance the state of the art for virtual assistants in software engineering. Virtual assistant technology is growing rapidly, though applications in software engineering are behind those in other areas, largely due to a lack of relevant data and experiments. This paper targets this problem in the area of developer Q/A conversations about bug repair.
قيم البحث
اقرأ أيضاً
Eclipse, an open source software project, acknowledges its donors by presenting donation badges in its issue tracking system Bugzilla. However, the rewarding effect of this strategy is currently unknown. We applied a framework of causal inference to
investigate relative promptness of developer response to bug reports with donation badges compared with bug reports without the badges, and estimated that donation badges decreases developer response time by a median time of about two hours. The appearance of donation badges is appealing for both donors and organizers because of its practical, rewarding and yet inexpensive effect.
While day-to-day questions come with a variety of answer types, the current question-answering (QA) literature has failed to adequately address the answer diversity of questions. To this end, we present GooAQ, a large-scale dataset with a variety of
answer types. This dataset contains over 5 million questions and 3 million answers collected from Google. GooAQ questions are collected semi-automatically from the Google search engine using its autocomplete feature. This results in naturalistic questions of practical interest that are nonetheless short and expressed using simple language. GooAQ answers are mined from Googles responses to our collected questions, specifically from the answer boxes in the search results. This yields a rich space of answer types, containing both textual answers (short and long) as well as more structured ones such as collections. We benchmarkT5 models on GooAQ and observe that: (a) in line with recent work, LMs strong performance on GooAQs short-answer questions heavily benefit from annotated data; however, (b) their quality in generating coherent and accurate responses for questions requiring long responses (such as how and why questions) is less reliant on observing annotated data and mainly supported by their pre-training. We release GooAQ to facilitate further research on improving QA with diverse response types.
Automated program repair is an emerging technology that seeks to automatically rectify bugs and vulnerabilities using learning, search, and semantic analysis. Trust in automatically generated patches is necessary for achieving greater adoption of pro
gram repair. Towards this goal, we survey more than 100 software practitioners to understand the artifacts and setups needed to enhance trust in automatically generated patches. Based on the feedback from the survey on developer preferences, we quantitatively evaluate existing test-suite based program repair tools. We find that they cannot produce high-quality patches within a top-10 ranking and an acceptable time period of 1 hour. The developer feedback from our qualitative study and the observations from our quantitative examination of existing repair tools point to actionable insights to drive program repair research. Specifically, we note that producing repairs within an acceptable time-bound is very much dependent on leveraging an abstract search space representation of a rich enough search space. Moreover, while additional developer inputs are valuable for generating or ranking patches, developers do not seem to be interested in a significant human-in-the-loop interaction.
We study a novel task, Video Question-Answer Generation (VQAG), for challenging Video Question Answering (Video QA) task in multimedia. Due to expensive data annotation costs, many widely used, large-scale Video QA datasets such as Video-QA, MSVD-QA
and MSRVTT-QA are automatically annotated using Caption Question Generation (CapQG) which inputs captions instead of the video itself. As captions neither fully represent a video, nor are they always practically available, it is crucial to generate question-answer pairs based on a video via Video Question-Answer Generation (VQAG). Existing video-to-text (V2T) approaches, despite taking a video as the input, only generate a question alone. In this work, we propose a novel model Generator-Pretester Network that focuses on two components: (1) The Joint Question-Answer Generator (JQAG) which generates a question with its corresponding answer to allow Video Question Answering training. (2) The Pretester (PT) verifies a generated question by trying to answer it and checks the pretested answer with both the models proposed answer and the ground truth answer. We evaluate our system with the only two available large-scale human-annotated Video QA datasets and achieves state-of-the-art question generation performances. Furthermore, using our generated QA pairs only on the Video QA task, we can surpass some supervised baselines. We apply our generated questions to Video QA applications and surpasses some supervised baselines using generated questions only. As a pre-training strategy, we outperform both CapQG and transfer learning approaches when employing semi-supervised (20%) or fully supervised learning with annotated data. These experimental results suggest the novel perspectives for Video QA training.
Studies over the past decade demonstrated that developers contributing to open source software systems tend to self-organize in emerging communities. This latent community structure has a significant impact on software quality. While several approach
es address the analysis of developer interaction networks, the question of whether these emerging communities align with the developer teams working on various subsystems remains unanswered. Work on socio-technical congruence implies that people that work on the same task or artifact need to coordinate and thus communicate, potentially forming stronger interaction ties. Our empirical study of 10 open source projects revealed that developer communities change considerably across a projects lifetime (hence implying that relevant relations between developers change) and that their alignment with subsystem developer teams is mostly low. However, subsystems teams tend to remain more stable. These insights are useful for practitioners and researchers to better understand developer interaction structure of open source systems.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
