Summarizing Lengthy Questions
نویسندگان
چکیده
In this research, we propose the task of question summarization. We first analyzed question-summary pairs extracted from a Community Question Answering (CQA) site, and found that a proportion of questions cannot be summarized by extractive approaches but requires abstractive approaches. We created a dataset by regarding the question-title pairs posted on the CQA site as question-summary pairs. By using the data, we trained extractive and abstractive summarization models, and compared them based on ROUGE scores and manual evaluations. Our experimental results show an abstractive method using an encoder-decoder model with a copying mechanism achieves better scores for both ROUGE-2 F-measure and the evaluations by human judges.
منابع مشابه
The Annotation Conundrum
Without lengthy, iterative refinement of guidelines, and equally lengthy and iterative training of annotators, the level of inter-subjective agreement on simple tasks of phonetic, phonological, syntactic, semantic, and pragmatic annotation is shockingly low. This is a significant practical problem in speech and language technology, but it poses questions of interest to psychologists, philosophe...
متن کاملFacilitating Issue Categorization & Analysis in Rulemaking
One task common to all notice-and-comment rulemaking is identifying substantive claims and arguments made in the comments by stakeholders and other members of the public. Extracting and summarizing this material may be helpful to internal decisionmaking; to produce the legally required public explanation of the final rule, it is essential. When comments are lengthy or numerous, natural language...
متن کاملBoundary Condition Independent Dynamic Compact Models of Packages and Heat Sinks from Thermal Transient Measurements
In this paper a methodology developed for the generation of transient compact models of packages and heat sinks from measured thermal transient results is described. The main advantage of generating dynamic compact models solely from measured results is the time-gain: the lengthy transient simulations, suggested by the DELPHI methodology can he omitted. After summarizing the procedure of genera...
متن کاملWearable imaging system for summarizing personal experiences
Digitization of lengthy personal experiences would be made possible by constant recording using wearable video cameras. It is conceivable that the resulting amount of video content would be extraordinarily large. In order to retrieve and browse the desired scenes, a vast amount of video would need to be organized with structural information. In this paper, we attempt to develop a “Wearable Imag...
متن کاملMining Query Subtopics from Questions in Community Question Answering
This paper proposes mining query subtopics from questions in community question answering (CQA). The subtopics are represented as a number of clusters of questions with keywords summarizing the clusters. The task is unique in that the subtopics from questions can not only facilitate user browsing in CQA search, but also describe aspects of queries from a question-answering perspective. The chal...
متن کامل