Related papers: Characterization and Prediction of Questions witho…
Document-based question answering (QA) increasingly includes abstract questions that require synthesizing scattered information from long documents or across multiple documents into coherent answers. However, this setting is still poorly…
Community Question Answering forums such as Quora, Stackoverflow are rich knowledge resources, often catering to information on topics overlooked by major search engines. Answers submitted to these forums are often elaborated, contain spam,…
Many unanswerable adversarial questions fool the question-answer (QA) system with some plausible answers. Building a robust, frequently asked questions (FAQ) chatbot needs a large amount of diverse adversarial examples. Recent question…
Previous studies that used data from Stack Overflow to develop predictive models often employed limited benchmarks of 3-5 models or adopted arbitrary selection methods. Despite being insightful, their limited scope suggests the need to…
Conversational question answering (CQA) facilitates an incremental and interactive understanding of a given context, but building a CQA system is difficult for many domains due to the problem of data scarcity. In this paper, we introduce a…
Open-domain question answering (QA) aims to find the answer to a question from a large collection of documents.Though many models for single-document machine comprehension have achieved strong performance, there is still much room for…
Complex question-answering (CQA) involves answering complex natural-language questions on a knowledge base (KB). However, the conventional neural program induction (NPI) approach exhibits uneven performance when the questions have different…
Improved software discovery is a prerequisite for greater software reuse: after all, if someone cannot find software for a particular task, they cannot reuse it. Understanding people's approaches and preferences when they look for software…
Developers often search for relevant code examples on the web for their programming tasks. Unfortunately, they face two major problems. First, the search is impaired due to a lexical gap between their query (task description) and the…
Knowledge and language understanding of models evaluated through question answering (QA) has been usually studied on static snapshots of knowledge, like Wikipedia. However, our world is dynamic, evolves over time, and our models' knowledge…
Version incompatibility issues are rampant when reusing or reproducing deep learning models and applications. Existing techniques are limited to library dependency specifications declared in PyPI. Therefore, these techniques cannot detect…
Stack Overflow (SO) is the largest Q&A website for developers, providing a huge amount of copyable code snippets. Using these snippets raises various maintenance and legal issues. The SO license requires attribution, i.e., referencing the…
Recent pretrained language models "solved" many reading comprehension benchmarks, where questions are written with access to the evidence document. However, datasets containing information-seeking queries where evidence documents are…
Despite the successes of pretrained language models, there are still few high-quality, general-purpose QA systems that are freely available. In response, we present Macaw, a versatile, generative question-answering (QA) system that we are…
When Question-Answering (QA) systems are deployed in the real world, users query them through a variety of interfaces, such as speaking to voice assistants, typing questions into a search engine, or even translating questions to languages…
Visual Question Answering (VQA) presents a unique challenge as it requires the ability to understand and encode the multi-modal inputs - in terms of image processing and natural language processing. The algorithm further needs to learn how…
Developers collaboratively discuss, implement, use, and share software entities hosted on software repositories. Proper documentation plays an important role in successful software management and maintenance. Users exploit Issue Tracking…
Search and recommender systems that take the initiative to ask clarifying questions to better understand users' information needs are receiving increasing attention from the research community. However, to the best of our knowledge, there…
Answering a programming question using only its title is difficult as salient contextual information is omitted. Based on this observation, we present a corpus of over 40,000 StackOverflow question texts to be used in conjunction with their…
Enriched by natural language texts, Stack Overflow code snippets are an invaluable code-centric knowledge base of small units of source code. Besides being useful for software developers, these annotated snippets can potentially serve as…