Learning to Paraphrase for Question Answering

Dong, Li; Mallinson, Jonathan; Reddy, Siva; Lapata, Mirella

doi:10.18653/v1/d17-1091

Cited by 163 publications

(133 citation statements)

References 38 publications

Supporting

Mentioning

132

Contrasting

Order By: Relevance

“…One main difference between these methods and our approach is that, while adversarial training only manipulates training data, we in addition apply transformations to data at test time to help prediction. This is closer to (Dong et al, 2017) in spirit.…”

Section: Related Workmentioning

confidence: 57%

Data Augmentation for Neural Online Chats Response Selection

Wen¹,

Black²

2018

Proceedings of the 2018 EMNLP Workshop SCAI: The 2nd International Workshop on Search-Oriented Conversational AI

View full text Add to dashboard Cite

Data augmentation seeks to manipulate the available data for training to improve the generalization ability of models. We investigate two data augmentation proxies, permutation and flipping, for neural dialog response selection task on various models over multiple datasets, including both Chinese and English languages. Different from standard data augmentation techniques, our method combines the original and synthesized data for prediction. Empirical results show that our approach can gain 1 to 3 recall-at-1 points over baseline models in both full-scale and small-scale settings.

show abstract

Section: Related Workmentioning

confidence: 57%

Data Augmentation for Neural Online Chats Response Selection

Wen¹,

Black²

2018

Proceedings of the 2018 EMNLP Workshop SCAI: The 2nd International Workshop on Search-Oriented Conversational AI

View full text Add to dashboard Cite

show abstract

“…Improving QA with QG This work also relates to recent studies that uses a QG model to improve the performance of a discriminative QA model (Wang et al, 2017;Yang et al, 2017;. The majority of these works generate a question from an answer, while there also exists a recent work (Dong et al, 2017) that generates a question from a question through paraphrasing. In addition, consider QA and QG as dual tasks, and further improve the QG model in a dual learning framework.…”

Section: Related Workmentioning

confidence: 94%

“…In addition, consider QA and QG as dual tasks, and further improve the QG model in a dual learning framework. These works fall into three categories: (1) regarding the artificially generated results as additional training instances (Yang et al, 2017;Golub et al, 2017); (2) using generated questions to calculate additional features Dong et al, 2017); and (3) using the QG results as additional constraints in the training objectives . This work belongs to the first direction.…”

Section: Related Workmentioning

confidence: 99%

Question Generation from SQL Queries Improves Neural Semantic Parsing

Guo¹,

Sun²,

Tang³

et al. 2018

Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

We study how to learn a semantic parser of state-of-the-art accuracy with less supervised training data. We conduct our study on WikiSQL, the largest hand-annotated semantic parsing dataset to date. First, we demonstrate that question generation is an effective method that empowers us to learn a state-ofthe-art neural network based semantic parser with thirty percent of the supervised training data. Second, we show that applying question generation to the full supervised training data further improves the state-of-the-art model. In addition, we observe that there is a logarithmic relationship between the accuracy of a semantic parser and the amount of training data.

show abstract

“…Paraphrase generation has the potential of being used in many other NLP research topics, such as machine translation (Madnani et al, 2007) and question answering (Buck et al, 2017;Dong et al, 2017). Early work mainly focuses on extracting paraphrases from parallel monolingual texts (Barzilay and McKeown, 2001;Ibrahim et al, 2003;Pang et al, 2003).…”

Section: Related Workmentioning

confidence: 99%

An Empirical Comparison on Imitation Learning and Reinforcement Learning for Paraphrase Generation

Du¹,

Ji²

2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

View full text Add to dashboard Cite

Generating paraphrases from given sentences involves decoding words step by step from a large vocabulary. To learn a decoder, supervised learning which maximizes the likelihood of tokens always suffers from the exposure bias. Although both reinforcement learning (RL) and imitation learning (IL) have been widely used to alleviate the bias, the lack of direct comparison leads to only a partial image on their benefits. In this work, we present an empirical study on how RL and IL can help boost the performance of generating paraphrases, with the pointer-generator as a base model 1 . Experiments on the benchmark datasets show that (1) imitation learning is constantly better than reinforcement learning; and (2) the pointer-generator models with imitation learning outperform the state-of-theart methods with a large margin. 2 In this work, we view scheduled sampling as an imitation learning algorithm similar to DAG-GER (Ross et al., 2011).

show abstract

Learning to Paraphrase for Question Answering

Cited by 163 publications

References 38 publications

Data Augmentation for Neural Online Chats Response Selection

Data Augmentation for Neural Online Chats Response Selection

Question Generation from SQL Queries Improves Neural Semantic Parsing

An Empirical Comparison on Imitation Learning and Reinforcement Learning for Paraphrase Generation

Contact Info

Product

Resources

About