Learning to Ask: Neural Question Generation for Reading Comprehension
Xinya Du,Junru Shao,Claire Cardie +2 more
- Vol. 1, pp 1342-1352
TLDR
This paper proposed an attention-based sequence learning model for question generation from text passages in reading comprehension, which is trainable end-to-end via sequence-tosequence learning and significantly outperforms the state-of-the-art rule-based system.Abstract:
We study automatic question generation for sentences from text passages in reading comprehension. We introduce an attention-based sequence learning model for the task and investigate the effect of encoding sentence- vs. paragraph-level information. In contrast to all previous work, our model does not rely on hand-crafted rules or a sophisticated NLP pipeline; it is instead trainable end-to-end via sequence-to-sequence learning. Automatic evaluation results show that our system significantly outperforms the state-of-the-art rule-based system. In human evaluations, questions generated by our system are also rated as being more natural (i.e.,, grammaticality, fluency) and as more difficult to answer (in terms of syntactic and lexical divergence from the original text and reasoning needed to answer).read more
Citations
More filters
Proceedings ArticleDOI
Generative Data Augmentation for Commonsense Reasoning
Yiben Yang,Chaitanya Malaviya,Jared Fernandez,Swabha Swayamdipta,Ronan Le Bras,Ji Ping Wang,Chandra Bhagavatula,Yejin Choi,Doug Downey +8 more
TL;DR: G-DAUGˆC as discussed by the authors generates synthetic examples using pretrained language models and selects the most informative and diverse set of examples for data augmentation, achieving state-of-the-art performance on commonsense reasoning benchmarks.
Posted Content
Embedding-based Zero-shot Retrieval through Query Generation.
Davis Liang,Peng Xu,Siamak Shakeri,Cicero Nogueira dos Santos,Ramesh Nallapati,Zhiheng Huang,Bing Xiang +6 more
TL;DR: This work considers the embedding-based two-tower architecture as the neural retrieval model and proposes a novel method for generating synthetic training data for retrieval, which produces remarkable results, significantly outperforming BM25 on 5 out of 6 datasets tested.
Posted Content
Improving Question Generation With to the Point Context
TL;DR: This work proposes a method to jointly model the unstructured sentence and the structured answer-relevant relation (extracted from the sentence in advance) for question generation and shows that to the point context helps the question generation model achieve significant improvements on several automatic evaluation metrics.
Proceedings ArticleDOI
Quiz-Style Question Generation for News Stories
TL;DR: This work proposes a series of novel techniques for applying large pre-trained Transformer encoder-decoder models, namely PEGASUS and T5, to the tasks of question-answer generation and distractor generation, and shows that these models outperform strong baselines using both automated metrics and human raters.
Proceedings ArticleDOI
Multi-hop Question Generation with Graph Convolutional Network
TL;DR: This article proposed a multi-hop Encoding Fusion Network (MulQG) which does context encoding in multiple hops with Graph Convolutional Network and encoding fusion via an Encoder Reasoning Gate.
References
More filters
Journal ArticleDOI
Long short-term memory
TL;DR: A novel, efficient, gradient based method called long short-term memory (LSTM) is introduced, which can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units.
Proceedings ArticleDOI
Glove: Global Vectors for Word Representation
TL;DR: A new global logbilinear regression model that combines the advantages of the two major model families in the literature: global matrix factorization and local context window methods and produces a vector space with meaningful substructure.
Proceedings ArticleDOI
Bleu: a Method for Automatic Evaluation of Machine Translation
TL;DR: This paper proposed a method of automatic machine translation evaluation that is quick, inexpensive, and language-independent, that correlates highly with human evaluation, and that has little marginal cost per run.
Proceedings Article
Neural Machine Translation by Jointly Learning to Align and Translate
TL;DR: It is conjecture that the use of a fixed-length vector is a bottleneck in improving the performance of this basic encoder-decoder architecture, and it is proposed to extend this by allowing a model to automatically (soft-)search for parts of a source sentence that are relevant to predicting a target word, without having to form these parts as a hard segment explicitly.
Proceedings ArticleDOI
Learning Phrase Representations using RNN Encoder--Decoder for Statistical Machine Translation
Kyunghyun Cho,Bart van Merriënboer,Caglar Gulcehre,Dzmitry Bahdanau,Fethi Bougares,Holger Schwenk,Yoshua Bengio,Yoshua Bengio,Yoshua Bengio +8 more
TL;DR: In this paper, the encoder and decoder of the RNN Encoder-Decoder model are jointly trained to maximize the conditional probability of a target sequence given a source sequence.