Extreme multi-label learning for semantic matching in product search
We consider the problem of semantic matching in product search: given a customer query,
retrieve all semantically related products from a huge catalog of size 100 million, or more …
retrieve all semantically related products from a huge catalog of size 100 million, or more …
Learning to detect relevant contexts and knowledge for response selection in retrieval-based dialogue systems
Recently, knowledge-grounded conversations in the open domain gain great attention from
researchers. Existing works on retrieval-based dialogue systems have paid tremendous …
researchers. Existing works on retrieval-based dialogue systems have paid tremendous …
Length adaptive regularization for retrieval-based chatbot models
D Wang, H Fang - Proceedings of the 2020 ACM SIGIR on International …, 2020 - dl.acm.org
Chatbots aim to mimic real conversations between humans. They have started playing an
increasingly important role in our daily life. Given past conversations, a retrieval-based …
increasingly important role in our daily life. Given past conversations, a retrieval-based …
The First Impression: Understanding the Impact of Multimodal System Responses on User Behavior in Task-oriented Agents
D Silva - Proceedings of the 30th ACM International Conference …, 2022 - dl.acm.org
In task-oriented dialog agents, the initial user experience sets the tone for future interactions
and plays a major role in whether the user returns to the system. But with the diversity of …
and plays a major role in whether the user returns to the system. But with the diversity of …