Product Question Intent Detection using Indicative Clause Attention and Adversarial Learning
8 citations recorded by the source corpus.
Due to the provision of QA service in many E-commerce sites, product question understanding becomes important. Product questions have different characteristics from traditional questions in that they are long and verbose as well as associated with different intents unique for the E-commerce setting. We conduct a thorough investigation on product questions covering different product categories from some commercial E-commerce sites. A set of question intent classes suitable for the E-commerce setting are identified. We also investigate the challenges of automatic intent detection and develop an intent detection framework based on a tailor-made deep neural model. The first characteristic of our framework is that it is capable of coping with long and verbose questions via identifying the indicative clauses. The second characteristic is that an adversarial learning algorithm is designed making use of an auxiliary classifier for avoiding the interference of product aspects with question intent detection quality. Extensive experiment results demonstrate the effectiveness of the proposed framework.
Subfields: Artificial Intelligence
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
Citations in the corpus
- Towards Open Intent Discovery for Conversational Text (2019, background): “Improvements in intent detection and slot filling based on adversarial learning have also been explored [25, 32, 50].”