Neural Duplicate Question Detection without Labeled Training Data
This work addresses the cost and data scarcity issues for community Question Answering platforms by enabling effective model training without labeled data, though it is incremental as it builds on existing unsupervised or weakly supervised approaches.
The paper tackles the problem of duplicate question detection in community Question Answering without labeled training data by proposing two methods: automatic generation of duplicate questions and weak supervision using question titles and bodies, achieving improved performances in many cases.
Supervised training of neural models to duplicate question detection in community Question Answering (cQA) requires large amounts of labeled question pairs, which are costly to obtain. To minimize this cost, recent works thus often used alternative methods, e.g., adversarial domain adaptation. In this work, we propose two novel methods: (1) the automatic generation of duplicate questions, and (2) weak supervision using the title and body of a question. We show that both can achieve improved performances even though they do not require any labeled data. We provide comprehensive comparisons of popular training strategies, which provides important insights on how to best train models in different scenarios. We show that our proposed approaches are more effective in many cases because they can utilize larger amounts of unlabeled data from cQA forums. Finally, we also show that our proposed approach for weak supervision with question title and body information is also an effective method to train cQA answer selection models without direct answer supervision.