کد مقاله | کد نشریه | سال انتشار | مقاله انگلیسی | نسخه تمام متن |
---|---|---|---|---|
11028022 | 1666131 | 2019 | 13 صفحه PDF | دانلود رایگان |
عنوان انگلیسی مقاله ISI
Dialogue breakdown detection robust to variations in annotators and dialogue systems
ترجمه فارسی عنوان
تشخیص شکستن گفتگو به تغییرات در آگهی ها و سیستم های گفتگو کمک می کند
دانلود مقاله + سفارش ترجمه
دانلود مقاله ISI انگلیسی
رایگان برای ایرانیان
کلمات کلیدی
تشخیص شکستن گفتگو، یادگیری گروهی خوشه بندی شبکه عصبی متقاطع، شبکه عصبی مکرر،
موضوعات مرتبط
مهندسی و علوم پایه
مهندسی کامپیوتر
پردازش سیگنال
چکیده انگلیسی
Dialogue breakdown is a significant problem in conversational agents. Timely breakdown detection helps the agents quickly recover from mistakes, minimizing the impact on user experience. In this paper, we focus on two problems: variations in determining a response that breakdowns a conversation i.e., subjectivity, and variations in breakdown types due to designs of conversational agents, i.e., variationality. To address the subjectivity, which decreases the agreement rate among annotators, our methods detect a dialogue breakdown by ensembling detectors trained by different sets of annotators that are grouped using a clustering algorithm. To address the variationality, our methods apply two types of detector architectures to capture global and local breakdowns. The long short-term memory detector considers the global context and the convolutional neural networks detector is sensitive to the local characteristics. The ensemble of all detectors makes a final judgment. The results of the Japanese task in the Dialogue Breakdown Detection Challenge 3 (DBDC3) confirm that our approach significantly outperforms the baseline, which uses the conventional conditional random field. Detailed error analysis reveals that our encoders based on a convolutional neural network and a long short-term memory have different characteristics. It also confirms the effects of annotator clustering.
ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Computer Speech & Language - Volume 54, March 2019, Pages 31-43
Journal: Computer Speech & Language - Volume 54, March 2019, Pages 31-43
نویسندگان
Junya Takayama, Eriko Nomoto, Yuki Arase,