Supervised and Unsupervised Transfer Learning for Question Answering
arXiv:1711.05345
Abstract
Although transfer learning has been shown to be successful for tasks like object and speech recognition, its applicability to question answering (QA) has yet to be well-studied. In this paper, we conduct extensive experiments to investigate the transferability of knowledge learned from a source QA dataset to a target dataset using two QA models. The performance of both models on a TOEFL listening comprehension test (Tseng et al., 2016) and MCTest (Richardson et al., 2013) is significantly improved via a simple transfer learning technique from MovieQA (Tapaswi et al., 2016). In particular, one of the models achieves the state-of-the-art on all target datasets; for the TOEFL listening comprehension test, it outperforms the previous best model by 7%. Finally, we show that transfer learning is helpful even in unsupervised scenarios when correct answers for target QA dataset examples are not available.
arXiv commentTo appear in NAACL HLT 2018 (long paper)
References in corpus (9)
- VQA: Visual Question Answering
- SQuAD: 100,000+ Questions for Machine Comprehension of Text
- Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding
- How Transferable are Neural Networks in NLP Applications?
- Speech2Vec: A Sequence-to-Sequence Framework for Learning Word Embeddings from Speech
- Audio Word2Vec: Unsupervised Learning of Audio Segment Representations using Sequence-to-sequence Autoencoder
- A Parallel-Hierarchical Model for Machine Comprehension on Sparse Data
- Learning Word Embeddings from Speech
- Query-based Attention CNN for Text Similarity Map