Matches in SemOpenAlex for { <https://semopenalex.org/work/W4213130420> ?p ?o ?g. }
Showing items 1 to 68 of
68
with 100 items per page.
- W4213130420 abstract "Predicting query intents is crucial for understanding user demands in chatbots. In real-world applications, accurate query intent classification can be highly challenging as human-machine interactions are often conducted in multiple turns, which requires the models to capture related information from the entire contexts. In addition, query intents tend to be fine-grained (up to hundreds of classes), containing lots of casual chats without clear intents. Hence, it is difficult for standard transformer-based models to capture complicated language characteristics of dialogues to support these applications. In this demo, we present AliMeTerp, a multi-turn query interpretation system, which can be seamlessly integrated into e-commercial chatbots in order to generate appropriate responses. Specifically, in AliMeTerp, we introduce SAM-BERT, a pre-trained language model for fine-grained query intent understanding, based on Sparse-to-dense Attentive Modeling. For model pre-training, a stack of Sparse-to-dense Attentive Encoders are employed to model the complicated dialogue structures from different levels. We further design Hierarchical Multi-grained Classification tasks for model fine-tuning. Experiments show SAM-BERT consistently outperforms strong baselines over multiple multi-turn chatbot datasets. We further show how AliMeTerp is deployed in real-world e-commercial chatbots to support real-time customer service." @default.
- W4213130420 created "2022-02-24" @default.
- W4213130420 creator A5031233380 @default.
- W4213130420 creator A5034474990 @default.
- W4213130420 creator A5042259471 @default.
- W4213130420 creator A5054699544 @default.
- W4213130420 date "2022-02-11" @default.
- W4213130420 modified "2023-10-14" @default.
- W4213130420 title "Building Multi-turn Query Interpreters for E-commercial Chatbots with Sparse-to-dense Attentive Modeling" @default.
- W4213130420 cites W1832693441 @default.
- W4213130420 cites W2508865106 @default.
- W4213130420 cites W2798367796 @default.
- W4213130420 cites W2972777589 @default.
- W4213130420 doi "https://doi.org/10.1145/3488560.3502189" @default.
- W4213130420 hasPublicationYear "2022" @default.
- W4213130420 type Work @default.
- W4213130420 citedByCount "1" @default.
- W4213130420 crossrefType "proceedings-article" @default.
- W4213130420 hasAuthorship W4213130420A5031233380 @default.
- W4213130420 hasAuthorship W4213130420A5034474990 @default.
- W4213130420 hasAuthorship W4213130420A5042259471 @default.
- W4213130420 hasAuthorship W4213130420A5054699544 @default.
- W4213130420 hasConcept C111919701 @default.
- W4213130420 hasConcept C118505674 @default.
- W4213130420 hasConcept C119857082 @default.
- W4213130420 hasConcept C121332964 @default.
- W4213130420 hasConcept C137293760 @default.
- W4213130420 hasConcept C154945302 @default.
- W4213130420 hasConcept C165801399 @default.
- W4213130420 hasConcept C192028432 @default.
- W4213130420 hasConcept C204321447 @default.
- W4213130420 hasConcept C23123220 @default.
- W4213130420 hasConcept C2779041454 @default.
- W4213130420 hasConcept C41008148 @default.
- W4213130420 hasConcept C44291984 @default.
- W4213130420 hasConcept C62520636 @default.
- W4213130420 hasConcept C66322947 @default.
- W4213130420 hasConceptScore W4213130420C111919701 @default.
- W4213130420 hasConceptScore W4213130420C118505674 @default.
- W4213130420 hasConceptScore W4213130420C119857082 @default.
- W4213130420 hasConceptScore W4213130420C121332964 @default.
- W4213130420 hasConceptScore W4213130420C137293760 @default.
- W4213130420 hasConceptScore W4213130420C154945302 @default.
- W4213130420 hasConceptScore W4213130420C165801399 @default.
- W4213130420 hasConceptScore W4213130420C192028432 @default.
- W4213130420 hasConceptScore W4213130420C204321447 @default.
- W4213130420 hasConceptScore W4213130420C23123220 @default.
- W4213130420 hasConceptScore W4213130420C2779041454 @default.
- W4213130420 hasConceptScore W4213130420C41008148 @default.
- W4213130420 hasConceptScore W4213130420C44291984 @default.
- W4213130420 hasConceptScore W4213130420C62520636 @default.
- W4213130420 hasConceptScore W4213130420C66322947 @default.
- W4213130420 hasLocation W42131304201 @default.
- W4213130420 hasOpenAccess W4213130420 @default.
- W4213130420 hasPrimaryLocation W42131304201 @default.
- W4213130420 hasRelatedWork W3092323224 @default.
- W4213130420 hasRelatedWork W3098382480 @default.
- W4213130420 hasRelatedWork W3104417388 @default.
- W4213130420 hasRelatedWork W3213193316 @default.
- W4213130420 hasRelatedWork W4205605869 @default.
- W4213130420 hasRelatedWork W4225351729 @default.
- W4213130420 hasRelatedWork W4285291329 @default.
- W4213130420 hasRelatedWork W4286859161 @default.
- W4213130420 hasRelatedWork W4287598411 @default.
- W4213130420 hasRelatedWork W4385572674 @default.
- W4213130420 isParatext "false" @default.
- W4213130420 isRetracted "false" @default.
- W4213130420 workType "article" @default.