A bird's-eye view on coherence, and a worm's-eye view on cohesion

Generating coherent and cohesive long-form texts is a challenging problem in natural language generation. Previous works relied on a large amount of human-generated texts to train language models, however, few attempted to explicitly model the desired linguistic properties of natural language text, such as coherence and cohesion. In this work, we train two expert discriminators for coherence and cohesion, respectively, to provide hierarchical feedback for text generation. We also propose a simple variant of policy gradient, called 'negative-critical sequence training', using margin rewards, in which the 'baseline' is constructed from randomly generated negative samples. We demonstrate the effectiveness of our approach through empirical studies, showing significant improvements over the strong baseline -- attention-based bidirectional MLE-trained neural language model -- in a number of automated metrics. The proposed discriminators can serve as baseline architectures to promote further research to better extract, encode essential linguistic qualities, such as coherence and cohesion.

[1]  William C. Mann,et al.  Rhetorical Structure Theory: Toward a functional theory of text organization , 1988 .

[2]  Yoon Kim,et al.  Convolutional Neural Networks for Sentence Classification , 2014, EMNLP.

[3]  Xiaogang Wang,et al.  StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Yong Yu,et al.  Long Text Generation via Adversarial Training with Leaked Information , 2017, AAAI.

[5]  Quoc V. Le,et al.  A Neural Conversational Model , 2015, ArXiv.

[6]  Ruslan Salakhutdinov,et al.  Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models , 2014, ArXiv.

[7]  Jianfeng Gao,et al.  Deep Reinforcement Learning for Dialogue Generation , 2016, EMNLP.

[8]  Rabab Kreidieh Ward,et al.  Deep Sentence Embedding Using Long Short-Term Memory Networks: Analysis and Application to Information Retrieval , 2015, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[9]  Alexei A. Efros,et al.  Image-to-Image Translation with Conditional Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Eduard H. Hovy,et al.  Automatic Evaluation of Summaries Using N-gram Co-occurrence Statistics , 2003, NAACL.

[11]  Vaibhava Goel,et al.  Self-Critical Sequence Training for Image Captioning , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Hector J. Levesque,et al.  Speech Acts and Rationality , 1985, ACL.

[13]  Kevin Gimpel,et al.  Towards Universal Paraphrastic Sentence Embeddings , 2015, ICLR.

[14]  R. J. Williams,et al.  Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning , 2004, Machine Learning.

[15]  Yishay Mansour,et al.  Policy Gradient Methods for Reinforcement Learning with Function Approximation , 1999, NIPS.

[16]  J. Hobbs.  On the coherence and structure of discourse , 1985 .

[17]  Po-Sen Huang,et al.  Discourse-Aware Neural Rewards for Coherent Text Generation , 2018, NAACL.

[18]  David J. Fleet,et al.  VSE++: Improved Visual-Semantic Embeddings , 2017, ArXiv.

[19]  Eduard H. Hovy,et al.  Planning Coherent Multisentential Text , 1988, ACL.

[20]  Eric P. Xing,et al.  Unsupervised Text Style Transfer using Language Models as Discriminators , 2018, NeurIPS.

[21]  Xiaodong Gu,et al.  DialogWAE: Multimodal Response Generation with Conditional Wasserstein Auto-Encoder , 2018, ICLR.

[22]  Alex Graves,et al.  Generating Sequences With Recurrent Neural Networks , 2013, ArXiv.

[23]  Kevin Lin,et al.  Adversarial Ranking for Language Generation , 2017, NIPS.

[24]  Jianfeng Gao,et al.  Modeling Interestingness with Deep Neural Networks , 2014, EMNLP.

[25]  Marc'Aurelio Ranzato,et al.  Sequence Level Training with Recurrent Neural Networks , 2015, ICLR.

[26]  Zhe Gan,et al.  Generating Informative and Diverse Conversational Responses via Adversarial Information Maximization , 2018, NeurIPS.

[27]  Yue Lu,et al.  Latent aspect rating analysis on review text data: a rating regression approach , 2010, KDD.

[28]  H. P. Edmundson,et al.  New Methods in Automatic Extracting , 1969, JACM.

[29]  Joelle Pineau,et al.  An Actor-Critic Algorithm for Sequence Prediction , 2016, ICLR.

[30]  William C. Mann,et al.  Natural Language Generation in Artificial Intelligence and Computational Linguistics , 1990 .

[31]  Yejin Choi,et al.  Learning to Write with Cooperative Discriminators , 2018, ACL.

[32]  Lantao Yu,et al.  SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient , 2016, AAAI.

[33]  Jianfeng Gao,et al.  A Persona-Based Neural Conversation Model , 2016, ACL.

[34]  John Langford,et al.  Search-based structured prediction , 2009, Machine Learning.

[35]  Elizabeth Du,et al.  The discourse-level structure of empirical abstracts: an exploratory study , 1991, Inf. Process. Manag..

[36]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[37]  Dimitris N. Metaxas,et al.  StackGAN: Text to Photo-Realistic Image Synthesis with Stacked Generative Adversarial Networks , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

[38]  Ian H. Witten,et al.  An Adaptive Optimal Controller for Discrete-Time Markov Environments , 1977, Inf. Control..

[39]  Andrew M. Dai,et al.  MaskGAN: Better Text Generation via Filling in the ______ , 2018, ICLR.

[40]  Salim Roukos,et al.  Bleu: a Method for Automatic Evaluation of Machine Translation , 2002, ACL.

[41]  Yangqing Jia,et al.  Deep Convolutional Ranking for Multilabel Image Annotation , 2013, ICLR.

[42]  Alan Ritter,et al.  Adversarial Learning for Neural Dialogue Generation , 2017, EMNLP.

[43]  Lihong Li,et al.  Neural Approaches to Conversational AI , 2019, Found. Trends Inf. Retr..

[44]  Kathleen McKeown,et al.  Discourse Strategies for Generating Natural-Language Text , 1985, Artif. Intell..

[45]  Nancy Ide,et al.  Veins Theory: A Model of Global Discourse Cohesion and Coherence , 1998, ACL.

[46]  Richard Socher,et al.  A Deep Reinforced Model for Abstractive Summarization , 2017, ICLR.

[47]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[48]  George Kurian,et al.  Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation , 2016, ArXiv.

[49]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[50]  Richard S. Sutton,et al.  Neuronlike adaptive elements that can solve difficult learning control problems , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[51]  Mirella Lapata,et al.  Modeling Local Coherence: An Entity-Based Approach , 2005, ACL.

[52]  Michael Halliday,et al.  Cohesion in English , 1976 .

[53]  Zhi Chen,et al.  Adversarial Feature Matching for Text Generation , 2017, ICML.

[54]  T. V. Dijk.  News as Discourse , 1990 .

[55]  Jason Weston,et al.  Natural Language Processing (Almost) from Scratch , 2011, J. Mach. Learn. Res..

[56]  Inderjeet Mani,et al.  Using Cohesion and Coherence Models for Text Summarization , 1998 .

[57]  Larry P. Heck,et al.  Learning deep structured semantic models for web search using clickthrough data , 2013, CIKM.

[58]  Zhe Gan,et al.  AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[59]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

[60]  Jianfeng Gao,et al.  A Diversity-Promoting Objective Function for Neural Conversation Models , 2015, NAACL.

[61]  Hang Li,et al.  Neural Responding Machine for Short-Text Conversation , 2015, ACL.

[62]  Yang Song,et al.  Learning Fine-Grained Image Similarity with Deep Ranking , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[63]  Yann Dauphin,et al.  Deal or No Deal? End-to-End Learning of Negotiation Dialogues , 2017, EMNLP.

[64]  Hal Daumé,et al.  Reinforcement Learning for Bandit Neural Machine Translation with Simulated Human Feedback , 2017, EMNLP.

[65]  Sanjeev Arora,et al.  A Simple but Tough-to-Beat Baseline for Sentence Embeddings , 2017, ICLR.

[66]  Jeffrey Pennington,et al.  GloVe: Global Vectors for Word Representation , 2014, EMNLP.

[67]  Pratik Rane,et al.  Self-Critical Sequence Training for Image Captioning , 2018 .

[68]  Jianfeng Gao,et al.  A Neural Network Approach to Context-Sensitive Generation of Conversational Responses , 2015, NAACL.

[69]  Gregory G. Colomb,et al.  Style: Toward Clarity and Grace , 1990 .