غالبا ما يتطلب تحسين تجربة المستخدم لنظام الحوار جهدا مكثفا مطورا مكثفا لقراءة سجلات المحادثة، وتشغيل التحليلات الإحصائية، والأهمية النسبية لأوجه القصور النسبية.تقدم هذه الورقة نهجا جديدا للتحليل الآلي لسجلات المحادثة التي تتعلم العلاقة بين تفاعلات نظام المستخدم وجودة الحوار الشاملة.على عكس العمل السابق على التنبؤ بجودة الكلام على مستوى الكلام، يتعلم نهجنا تأثير كل تفاعل من تصنيف المستخدمين العام دون إشراف على مستوى الكلام، مما يسمح باستنتاجات النماذج الناتجة عن الاستمتاع على أساس الأدلة التجريبية وتكلفة منخفضة.يحدد نموذجنا التفاعلات التي لها علاقة قوية بجودة الحوار الشاملة في إعداد chatbot.تشير التجارب إلى أن التحليل الآلي من طرازنا يوافق على أحكام الخبراء، مما يجعل هذا العمل الأول من يوضح أن هذا التعلم الإشرافه ضعيف في التنبؤ بجودة الكلام هو قابلة للتحقيق بشدة.
Improving user experience of a dialogue system often requires intensive developer effort to read conversation logs, run statistical analyses, and intuit the relative importance of system shortcomings. This paper presents a novel approach to automated analysis of conversation logs that learns the relationship between user-system interactions and overall dialogue quality. Unlike prior work on utterance-level quality prediction, our approach learns the impact of each interaction from the overall user rating without utterance-level annotation, allowing resultant model conclusions to be derived on the basis of empirical evidence and at low cost. Our model identifies interactions that have a strong correlation with the overall dialogue quality in a chatbot setting. Experiments show that the automated analysis from our model agrees with expert judgments, making this work the first to show that such weakly-supervised learning of utterance-level quality prediction is highly achievable.
References used
https://aclanthology.org/
Recent task-oriented dialogue systems learn a model from annotated dialogues, and such dialogues are in turn collected and annotated so that they are consistent with certain domain knowledge. However, in real scenarios, domain knowledge is subject to
Identifying relevant knowledge to be used in conversational systems that are grounded in long documents is critical to effective response generation. We introduce a knowledge identification model that leverages the document structure to provide dialo
This study proposes an utterance position-aware approach for a neural network-based dialogue act recognition (DAR) model, which incorporates positional encoding for utterance's absolute or relative position. The proposed approach is inspired by the o
Word embeddings capture semantic meaning of individual words. How to bridge word-level linguistic knowledge with sentence-level language representation is an open problem. This paper examines whether sentence-level representations can be achieved by
Knowledge Grounded Conversation Models are usually based on a selection/retrieval module and a generation module, trained separately or simultaneously, with or without having access to a gold' knowledge option. With the introduction of large pre-trai