Conditional Generative Adversarial Networks for Commonsense Machine Comprehension

By Bingning Wang, Kang Liu, Jun Zhao. 2017

36 citations recorded by the source corpus.

Recently proposed Story Cloze Test [Mostafazadeh et al. , 2016] is a commonsense machine comprehension application to deal with natural language understanding problem. This dataset contains a lot of story tests which require commonsense inference ability. Unfortunately, the training data is almost unsupervised where each context document followed with only one positive sentence that can be inferred from the context. However, in the testing period, we must make inference from two candidate sentences. To tackle this problem, we employ the generative adversarial networks (GANs) to generate fake sentence. We proposed a C onditional GAN s (CGANs) in which the generator is conditioned by the context. Our experiments show the advantage of the CGANs in discriminating sentence and achieve state-of-the-art results in commonsense story reading comprehension task compared with previous feature engineering and deep learning methods.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Generative Models, Question Answering & Reading Comprehension

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Minlie Huang
2. Zhuosheng Zhang
3. Xiaoyan Zhu
4. Hai Zhao
5. Zhao Hai
6. Tom Young
7. Ting-Wei Liu
8. Xiao Ding

In Computer Vision and Pattern Recognition

1. Minlie Huang
2. Zhuosheng Zhang
3. Xiaoyan Zhu
4. Zhao Hai
5. Yafang Huang
6. Hai Zhao
7. Ting-Wei Liu
8. Xiao Ding

In Generative Models

1. Xiaoyan Zhu
2. Minlie Huang
3. Tom Young
4. Yafang Huang
5. Hao Zhou
6. Zhuosheng Zhang
7. Zhao Hai

In Question Answering & Reading Comprehension

1. Zhuosheng Zhang
2. Xiao Ding
3. Yafang Huang
4. Zhongyang Li
5. Zhao Hai
6. Ting-Wei Liu
7. Hai Zhao

Citations in the corpus

• Story Ending Prediction by Transferable BERT (2019, neutral): “DSSM [Huang et al. , 2013] 58.5 CGAN [Wang et al. , 2017] 60.9 HBiLSTM [Cai et al. , 2017] 74.7 Msap [Schwartz et al. , 2017] 75.2 HCM [Chaturvedi et al. , 2017] 77.6 HintNet [Zhou et al. , 2019] 79.2 SeqMANN [Li et al. , 2018a] 84.7 GPT [Radford et al. , 2018] 86.5 ISCK [Chen et al. , 2019] 87…”
• Commonsense Knowledge Aware Conversation Generation with Graph Attention (2018, background): “…understanding, particularly when facilitated by commonsense knowledge or world facts, is essential to many natural language processing tasks [Wang et al. , 2017; Lin et al. , 2017], and undoubtedly, it is a key factor to the success of dialogue or conversational systems, as conversational…”
• Generating Reasonable and Diversified Story Ending Using Sequence to Sequence Model with Adversarial Training (2018, background): “(cid:15) Conditional Generative Adversarial Networks (CGAN) : The Conditional GAN model proposed in (Wang et al., 2017), in which the discriminator is used to choose the correct story ending.”
• Story Ending Selection by Finding Hints From Pairwise Candidate Endings (2019, unknown): “CGAN [25] encodes each ending and the story by GRUs and computes an entail score.”
• Subword-augmented Embedding for Cloze Reading Comprehension (2018, methodology): “Meanwhile, a number of deep learning models are designed to take up the challenges, most of which focus on attention mechanism (Wang et al., 2017b; Seo et al., 2017; Cui et al., 2017a; Kadlec et al., 2016; Dhingra et al., 2017; Zhang and Zhao, 2018).”
• A Multi-Attention based Neural Network with External Knowledge for Story Ending Predicting Task (2018, background): “…Schwartz (Schwartz et al., 2017) 75.2% HCM (Chaturvedi et al., 2017) 77.6% Neural Network Algorithm DSSM (Mostafazadeh et al., 2016) 58.5% CGAN (Wang et al., 2017) 60.9% Lin (Lin et al., 2017) 67.0% LSTM (Mihaylov and Frank, 2017) 72.8% Cai (Cai et al., 2017) 74.7% MANN 78.3% SeqMANN 84.7%…”
• Effective Character-Augmented Word Embedding for Machine Reading Comprehension (2018, background): “Machine reading comprehension has been witnessed rapid progress in recent years [26,27,29,22,28,8,33,35,31].”