Forecasting Live Chat Intent from Browsing History
Customers reach out to online live chat agents with various intents, such as asking about product details or requesting a return. In this paper, we propose the problem of predicting user intent from browsing history and address it through a two-stage approach. The first stage classifies a user's browsing history into high-level intent categories. Here, we represent each browsing history as a text sequence of page attributes and use the ground-truth class labels to fine-tune pretrained Transformers. The second stage provides a large language model (LLM) with the browsing history and predicted intent class to generate fine-grained intents. For automatic evaluation, we use a separate LLM to judge the similarity between generated and ground-truth intents, which closely aligns with human judgments. Our two-stage approach yields significant performance gains compared to generating intents without the classification stage.
Code (0)
등록된 구현이 없습니다.
Tasks
Language ModelingLanguage ModellingLarge Language ModelSimilar Papers 제목 키워드 기반
Automatic Generation of Chatbots for Conversational Web Browsing
In this paper, we describe the foundations for generating a chatbot out of a website equipped with simple, bot-specific HTML annotations. The approach is part of what we call conversational web browsing, i.e., a dialog-b…
ChatbotIntentTune: Using user demand and personalization to resolve "unknown" query intents for e-commerce search
Understanding user intent is fundamental to delivering relevant search results in e-commerce. However, substantial fraction of real-world queries are under-specified (e.g., "watch" or "shirt"), lacking explicit attribute…
Intent DetectionFrom Passive Feeds to Guided Discovery: AI-Initiated Interaction for Vague Intent in Content Exploration
Recommendation feeds work well when people are simply browsing, and search works well when they can formulate a query. Between these two cases is a common but poorly supported state: users feel that their feed has become…
Improving Native Ads CTR Prediction by Large Scale Event Embedding and Recurrent Networks
Click through rate (CTR) prediction is very important for Native advertisement but also hard as there is no direct query intent. In this paper we propose a large-scale event embedding scheme to encode the each user brows…
Click-Through Rate PredictionPredictionSemantic Web Search based on Ontology Modeling using Protege Reasoner
The Semantic Web works on the existing Web which presents the meaning of information as well-defined vocabularies understood by the people. Semantic Search, at the same time, works on improving the accuracy if a search b…