تم إحراك المصالح المتزايدة في أنظمة الموافقة على المحادثة (CRS)، والتي تستكشف تفضيل المستخدم من خلال تفاعلات المحادثة من أجل تقديم توصية مناسبة. ومع ذلك، لا يزال هناك نقص في القدرة في CRS الحالية إلى (1) اجتياز مسارات التفكير المتعددة على المعرفة الأساسية لإدخال العناصر والسمات ذات الصلة، و (2) ترتيب كيانات مختارة بشكل مناسب بموجب نود النظام الحالي للسيطرة على جيل الاستجابة. لمعالجة هذه المشكلات، نقترح Walker CR-Walker في هذه الورقة، وهو نموذج يقوم بتنفيذ التفكير منظم في الأشجار في رسم بياني للمعرفة، ويولد أعمال حوار إعلامية لتوجيه توليد اللغة. ينظر المخطط الفريد من المنطق المنظم في الأشجار إلى الكيان اجتاز كل قفزة كجزء من أعمال الحوار لتسهيل توليد اللغة، والذي يربط كيف يتم اختيار الكيانات والأعرب عنها. تظهر التقييمات التلقائية والبشرية أن CR-Walker يمكن أن يصل إلى توصية أكثر دقة، وتوليد استجابات أكثر إعلامية وجذابة.
Growing interests have been attracted in Conversational Recommender Systems (CRS), which explore user preference through conversational interactions in order to make appropriate recommendation. However, there is still a lack of ability in existing CRS to (1) traverse multiple reasoning paths over background knowledge to introduce relevant items and attributes, and (2) arrange selected entities appropriately under current system intents to control response generation. To address these issues, we propose CR-Walker in this paper, a model that performs tree-structured reasoning on a knowledge graph, and generates informative dialog acts to guide language generation. The unique scheme of tree-structured reasoning views the traversed entity at each hop as part of dialog acts to facilitate language generation, which links how entities are selected and expressed. Automatic and human evaluations show that CR-Walker can arrive at more accurate recommendation, and generate more informative and engaging responses.
References used
https://aclanthology.org/
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
Visual dialog is a task of answering a sequence of questions grounded in an image using the previous dialog history as context. In this paper, we study how to address two fundamental challenges for this task: (1) reasoning over underlying semantic st
Conversational semantic role labeling (CSRL) is believed to be a crucial step towards dialogue understanding. However, it remains a major challenge for existing CSRL parser to handle conversational structural information. In this paper, we present a
Abstract To develop commonsense-grounded NLP applications, a comprehensive and accurate commonsense knowledge graph (CKG) is needed. It is time-consuming to manually construct CKGs and many research efforts have been devoted to the automatic construc
Many state-of-art neural models designed for monotonicity reasoning perform poorly on downward inference. To address this shortcoming, we developed an attentive tree-structured neural network. It consists of a tree-based long-short-term-memory networ