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
Neural Generation of Diverse Questions using Answer Focus, Contextual and Linguistic Features
TL;DR: This paper proposed a new attentional encoder-decoder recurrent neural network model for question generation, which incorporates linguistic features and an additional sentence embedding to capture meaning at both sentence and word levels.
Proceedings ArticleDOI
SPARTQA: A Textual Question Answering Benchmark for Spatial Reasoning
TL;DR: Experiments show that further pretraining LMs on these automatically generated data significantly improves LMs’ capability on spatial understanding, which in turn helps to better solve two external datasets, bAbI, and boolQ.
Proceedings ArticleDOI
Towards Generating Math Word Problems from Equations and Topics
Qingyu Zhou,Danqing Huang +1 more
TL;DR: A novel neural network model is proposed to generate math word problems from the given equations and topics with a fusion mechanism to incorporate the information of both equations and Topics.
Proceedings ArticleDOI
Stay Hungry, Stay Focused: Generating Informative and Specific Questions in Information-Seeking Conversations
TL;DR: The authors use reinforcement learning to optimize an informativeness metric, combined with a reward function designed to promote more specific questions, and demonstrate that the resulting pragmatic questioner substantially improves the informativity and specificity of questions generated over a baseline model, as evaluated by their metrics as well as humans.
Journal ArticleDOI
Biomedical Question Answering: A Survey of Approaches and Challenges
TL;DR: There have been tremendous developments of BQA in the past two decades, which can be classified into five distinctive approaches: classic, information retrieval, machine reading comprehension, knowledge base, and question entailment approaches as discussed by the authors .
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.