Summary of Forecasting Live Chat Intent From Browsing History, by Se-eun Yoon et al.
Forecasting Live Chat Intent from Browsing History
by Se-eun Yoon, Ahmad Bin Rabiah, Zaid Alibadi, Surya Kallumadi, Julian McAuley
First submitted to arxiv on: 7 Aug 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Information Retrieval (cs.IR)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper proposes a two-stage approach to predict user intent from browsing history in online live chat interactions. The first stage classifies browsing history into high-level intent categories using pre-trained Transformers and fine-tuning with ground-truth labels. The second stage generates fine-grained intents by providing the browsing history and predicted intent class to a large language model (LLM). Automatic evaluation uses a separate LLM to judge similarity between generated and ground-truth intents, aligning closely with human judgments. This approach outperforms generating intents without classification. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary In this paper, researchers try to figure out what customers want when they talk to online chat agents. They use two stages to do this. The first stage looks at what the customer has been browsing and groups it into big categories like “asking about product details” or “requesting a return”. The second stage uses a super smart computer model to guess exactly what the customer wants, based on what they’ve been looking at and what category they fit into. This helps the chat agent understand what the customer is asking for and give them the right answer. |
Keywords
» Artificial intelligence » Classification » Fine tuning » Large language model
