معظم أدب Chatbot الذي يركز على تحسين طلاقة وتماسك Chatbot، مكرس لصنع Chatbots المزيد من البشر. ومع ذلك، فإن العمل القليل جدا يلحق ما يفصل حقا عن البشر من Chatbots - البشر يفهمون جوهريا تأثير ردودهم على المحاور وغالبا ما يستجيبون بنية مثل اقتراح نظرة متفائلة لجعل المحاور يشعر بالتحسن. تقترح هذه الورقة إطارا مبتكرا لتدريب Chatbots لامتلاك نوايا تشبه الإنسان. يشتمل إطار عملنا على تشاتبوت توجيهي وطراز محاور يلعب دور البشر. يتم تعيين chatbot التوجيهي وتعلم أن يحفز المحاور للرد بالردود التي تطابق النية، على سبيل المثال، الاستجابات الطويلة، الاستجابات بهيجة، الاستجابات ذات الكلمات المحددة، إلخ. لقد درسنا الإطار الخاص بنا باستخدام ثلاث من الإعدادات التجريبية وتقييم Chatbot التوجيهي مع أربعة مقاييس مختلفة لإظهار المرونة ومزايا الأداء. بالإضافة إلى ذلك، أجرينا تجارب مع محاورات بشرية لإثبات فعالية Chatbot التوجيهية في التأثير على ردود البشر إلى حد ما. سيتم توفير الكود للجمهور.
Most chatbot literature that focuses on improving the fluency and coherence of a chatbot, is dedicated to making chatbots more human-like. However, very little work delves into what really separates humans from chatbots -- humans intrinsically understand the effect their responses have on the interlocutor and often respond with an intention such as proposing an optimistic view to make the interlocutor feel better. This paper proposes an innovative framework to train chatbots to possess human-like intentions. Our framework includes a guiding chatbot and an interlocutor model that plays the role of humans. The guiding chatbot is assigned an intention and learns to induce the interlocutor to reply with responses matching the intention, for example, long responses, joyful responses, responses with specific words, etc. We examined our framework using three experimental setups and evaluated the guiding chatbot with four different metrics to demonstrate flexibility and performance advantages. Additionally, we performed trials with human interlocutors to substantiate the guiding chatbot's effectiveness in influencing the responses of humans to a certain extent. Code will be made available to the public.
References used
https://aclanthology.org/
Amidst rising mental health needs in society, virtual agents are increasingly deployed in counselling. In order to give pertinent advice, counsellors must first gain an understanding of the issues at hand by eliciting sharing from the counsellee. It
Many existing chatbots do not effectively support mixed initiative, forcing their users to either respond passively or lead constantly. We seek to improve this experience by introducing new mechanisms to encourage user initiative in social chatbot co
Neural generative dialogue agents have shown an increasing ability to hold short chitchat conversations, when evaluated by crowdworkers in controlled settings. However, their performance in real-life deployment -- talking to intrinsically-motivated u
Artificial intelligence chatbots are the vanguard in technology-based intervention to change people's behavior. To develop intervention chatbots, the first step is to understand natural language conversation strategies in human conversation. This wor
Personalized dialogue systems are an essential step toward better human-machine interaction. Existing personalized dialogue agents rely on properly designed conversational datasets, which are mostly monolingual (e.g., English), which greatly limits t