Modelling Domain Relationships for Transfer Learning on Retrieval-based Question Answering Systems in E-commerce
Authors:
- Jianfei YuJYJianfei Yu
- Minghui QiuMQMinghui Qiu
- Jing JiangJJJing Jiang
- Jun HuangJHJun Huang
- Shuangyong SongSSShuangyong Song
- Wei ChuWCWei Chu
- Haiqing ChenHCHaiqing Chen
Preprint
Abstract
In this paper, we study transfer learning for the PI and NLI problems, aiming to propose a general framework, which can effectively and efficiently adapt the shared knowledge learned from a resource-rich source domain to a resource- poor target domain. Specifically, since most existing transfer learning methods only focus on learning a shared feature space across domains while ignoring the relationship between the source and target domains, we propose to simultaneously learn shared representations and domain relationships in a unified framework. Furthermore, we propose an efficient and effective hybrid model by combining a sentence encoding- based method and a sentence interaction-based method as our base model. Extensive experiments on both paraphrase identification and natural language inference demonstrate that our base model is efficient and has promising performance compared to the competing models, and our transfer learning method can help to significantly boost the performance. Further analysis shows that the inter-domain and intra-domain relationship captured by our model are insightful. Last but not least, we deploy our transfer learning model for PI into our online chatbot system, which can bring in significant improvements over our existing system. Finally, we launch our new system on the chatbot platform Eva in our E-commerce site AliExpress.Keywords
All Related Versions
This publication has 21 references indexed in Scilit:
- A Short-Term Rainfall Prediction Model Using Multi-task Convolutional Neural Networks2017
- ABCNN: Attention-Based Convolutional Neural Network for Modeling Sentence PairsTransactions of the Association for Computational Linguistics, 2016
- Learning to Respond with Deep Neural Networks for Retrieval-Based Human-Computer Conversation System2016
- Text Matching as Image RecognitionProceedings of the AAAI Conference on Artificial Intelligence, 2016
- How Transferable are Neural Networks in NLP Applications?2016
- Learning Sentence Embeddings with Auxiliary Tasks for Cross-Domain Sentiment Classification2016
- Adaptation Regularization: A General Framework for Transfer LearningIEEE Transactions on Knowledge and Data Engineering, 2013
- Manifold alignment using Procrustes analysis2008
- Learning a meta-level prior for feature relevance from multiple related tasks2007
- Some statistical issues in the comparison of speech recognition algorithms2003