Requery Rewrite (QR) هو مكون ناشئ في أنظمة المحادثة AI، مما يقلل من عيب المستخدم.سبب عيب المستخدم لأسباب مختلفة، مثل الأخطاء في نظام الحوار المنطوق أو عروض المستخدمين للسان أو لغتهم المختصرة.ينبع العديد من عيوب المستخدمين من العوامل الشخصية، مثل نمط خطاب المستخدم أو اللهجة أو التفضيلات.في هذا العمل، نقترح إطار عمل QR القائم على البحث شخصي، والذي يركز على التخفيض التلقائي لعيب المستخدم.نقوم ببناء مؤشر شخصي لكل مستخدم، يشمل طبقات تقارب متنوعة لتعكس التفضيلات الشخصية لكل مستخدم في منظمة العفو الدولية المحادثة.يحتوي نظام QR الشخصي الخاص بنا على طبقات استرجاع وترتيب.بدعم من التعلم القائم على ملاحظات المستخدم، تدريب نماذجنا لا يتطلب بيانات مشروح يدوية.أظهرت التجارب على مجموعة الاختبارات الشخصية أن نظام QR الشخصي الخاص بنا قادر على تصحيح أخطاء النظامية والمستخدم باستخدام المدخلات الصوتية والدلية.
Query rewrite (QR) is an emerging component in conversational AI systems, reducing user defect. User defect is caused by various reasons, such as errors in the spoken dialogue system, users' slips of the tongue or their abridged language. Many of the user defects stem from personalized factors, such as user's speech pattern, dialect, or preferences. In this work, we propose a personalized search-based QR framework, which focuses on automatic reduction of user defect. We build a personalized index for each user, which encompasses diverse affinity layers to reflect personal preferences for each user in the conversational AI. Our personalized QR system contains retrieval and ranking layers. Supported by user feedback based learning, training our models does not require hand-annotated data. Experiments on personalized test set showed that our personalized QR system is able to correct systematic and user errors by utilizing phonetic and semantic inputs.
References used
https://aclanthology.org/
Query Rewriting (QR) is proposed to solve the problem of the word mismatch between queries and documents in Web search. Existing approaches usually model QR with an end-to-end sequence-to-sequence (seq2seq) model. The state-of-the-art Transformer-bas
The next generation of conversational AI systems need to: (1) process language incrementally, token-by-token to be more responsive and enable handling of conversational phenomena such as pauses, restarts and self-corrections; (2) reason incrementally
Successful conversational search systems can present natural, adaptive and interactive shopping experience for online shopping customers. However, building such systems from scratch faces real word challenges from both imperfect product schema/knowle
Obtaining affective response is a key step in building empathetic dialogue systems. This task has been studied a lot in generation-based chatbots, but the related research in retrieval-based chatbots is still in the early stage. Existing works in ret
This paper describes a compact and effective model for low-latency passage retrieval in conversational search based on learned dense representations. Prior to our work, the state-of-the-art approach uses a multi-stage pipeline comprising conversation