ShopTalk: A System for Conversational Faceted Search (2109.00702v1)
Abstract: We present ShopTalk, a multi-turn conversational faceted search system for shopping that is designed to handle large and complex schemas that are beyond the scope of state of the art slot-filling systems. ShopTalk decouples dialog management from fulfiLLMent, thereby allowing the dialog understanding system to be domain-agnostic and not tied to the particular shopping application. The dialog understanding system consists of a deep-learned Contextual Language Understanding module, which interprets user utterances, and a primarily rules-based Dialog-State Tracker (DST), which updates the dialog state and formulates search requests intended for the fulfiLLMent engine. The interface between the two modules consists of a minimal set of domain-agnostic "intent operators," which instruct the DST on how to update the dialog state. ShopTalk was deployed in 2020 on the Google Assistant for Shopping searches.
- Gurmeet Manku (1 paper)
- James Lee-Thorp (10 papers)
- Bhargav Kanagal (7 papers)
- Joshua Ainslie (32 papers)
- Jingchen Feng (11 papers)
- Zach Pearson (1 paper)
- Ebenezer Anjorin (1 paper)
- Sudeep Gandhe (2 papers)
- Ilya Eckstein (5 papers)
- Jim Rosswog (1 paper)
- Sumit Sanghai (15 papers)
- Michael Pohl (1 paper)
- Larry Adams (1 paper)
- D. Sivakumar (3 papers)