One-shot Learning for Question-Answering in Gaokao History Challenge
arXiv:1806.09105
Abstract
Answering questions from university admission exams (Gaokao in Chinese) is a challenging AI task since it requires effective representation to capture complicated semantic relations between questions and answers. In this work, we propose a hybrid neural model for deep question-answering task from history examinations. Our model employs a cooperative gated neural network to retrieve answers with the assistance of extra labels given by a neural turing machine labeler. Empirical study shows that the labeler works well with only a small training dataset and the gated mechanism is good at fetching the semantic representation of lengthy answers. Experiments on question answering demonstrate the proposed model obtains substantial performance gains over various neural model baselines in terms of multiple evaluation metrics.
Proceedings of the 27th International Conference on Computational Linguistics (COLING 2018)
References in corpus (2)
Cited by in corpus (14)
- QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehension
- Modeling Multi-turn Conversation with Deep Utterance Aggregation
- Machine Reading Comprehension: The Role of Contextualized Language Models and Beyond
- Leveraging Siamese Networks for One-Shot Intrusion Detection Model
- Explicit Contextual Semantics for Text Comprehension
- SG-Net: Syntax-Guided Machine Reading Comprehension
- Head-Driven Phrase Structure Grammar Parsing on Penn Treebank
- Bipartite Flat-Graph Network for Nested Named Entity Recognition
- Topic-Aware Multi-turn Dialogue Modeling
- Effective Subword Segmentation for Text Comprehension
- MATINF: A Jointly Labeled Large-Scale Dataset for Classification, Question Answering and Summarization
- Open Vocabulary Learning for Neural Chinese Pinyin IME
- Adaptive Convolution for Semantic Role Labeling
- Effective Character-augmented Word Embedding for Machine Reading Comprehension