Adaptive Parameterization for Neural Dialogue Generation

Neural conversation systems generate responses based on the sequence-to-sequence (SEQ2SEQ) paradigm. Typically, the model is equipped with a single set of learned parameters to generate responses for given input contexts. When confronting diverse conversations, its adaptability is rather limited and the model is hence prone to generate generic responses. In this work, we propose an {\bf Ada}ptive {\bf N}eural {\bf D}ialogue generation model, \textsc{AdaND}, which manages various conversations with conversation-specific parameterization. For each conversation, the model generates parameters of the encoder-decoder by referring to the input context. In particular, we propose two adaptive parameterization mechanisms: a context-aware and a topic-aware parameterization mechanism. The context-aware parameterization directly generates the parameters by capturing local semantics of the given context. The topic-aware parameterization enables parameter sharing among conversations with similar topics by first inferring the latent topics of the given context and then generating the parameters with respect to the distributional topics. Extensive experiments conducted on a large-scale real-world conversational dataset show that our model achieves superior performance in terms of both quantitative metrics and human evaluations.

[1]  Yang Zhao,et al.  A Conditional Variational Framework for Dialog Generation , 2017, ACL.

[2]  Jason Weston,et al.  ParlAI: A Dialog Research Software Platform , 2017, EMNLP.

[3]  Joelle Pineau,et al.  How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation , 2016, EMNLP.

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

[5]  Quoc V. Le,et al.  HyperNetworks , 2016, ICLR.

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

[7]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[8]  Phil Blunsom,et al.  Discovering Discrete Latent Topics with Neural Variational Inference , 2017, ICML.

[9]  Wei-Ying Ma,et al.  Topic Aware Neural Response Generation , 2016, AAAI.

[10]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[11]  Nebojsa Jojic,et al.  Steering Output Style and Topic in Neural Response Generation , 2017, EMNLP.

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

[13]  Stephen Clark,et al.  Latent Variable Dialogue Models and their Diversity , 2017, EACL.

[14]  Luca Bertinetto,et al.  Learning feed-forward one-shot learners , 2016, NIPS.

[15]  Douglas Eck,et al.  A Neural Representation of Sketch Drawings , 2017, ICLR.

[16]  Tom M. Mitchell,et al.  Contextual Parameter Generation for Universal Neural Machine Translation , 2018, EMNLP.

[17]  Maxine Eskénazi,et al.  Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders , 2017, ACL.

[18]  Xiang Zhang,et al.  Evaluating Prerequisite Qualities for Learning End-to-End Dialog Systems , 2015, ICLR.

[19]  Joseph Suarez,et al.  Character-Level Language Modeling with Recurrent Highway Hypernetworks , 2017 .

[20]  Hujun Yin,et al.  Breaking the Activation Function Bottleneck through Adaptive Parameterization , 2018, NeurIPS.

[21]  Lyle H. Ungar,et al.  Domain Aware Neural Dialog System , 2017, ArXiv.

[22]  Manaal Faruqui,et al.  Text Generation with Exemplar-based Adaptive Decoding , 2019, NAACL.

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

[24]  Samy Bengio,et al.  Generating Sentences from a Continuous Space , 2015, CoNLL.

[25]  Joelle Pineau,et al.  Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models , 2015, AAAI.

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

[27]  Joelle Pineau,et al.  The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systems , 2015, SIGDIAL Conference.

[28]  Zhaochun Ren,et al.  Hierarchical Variational Memory Network for Dialogue Generation , 2018, WWW.

[29]  Jason Weston,et al.  Personalizing Dialogue Agents: I have a dog, do you have pets too? , 2018, ACL.

[30]  Maxine Eskénazi,et al.  Unsupervised Discrete Sentence Representation Learning for Interpretable Neural Dialog Generation , 2018, ACL.

[31]  Fumin Shen,et al.  Chat More: Deepening and Widening the Chatting Topic via A Deep Model , 2018, SIGIR.

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

[33]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[34]  Joelle Pineau,et al.  A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues , 2016, AAAI.

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

[36]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[37]  Dongyan Zhao,et al.  Towards Implicit Content-Introducing for Generative Short-Text Conversation Systems , 2017, EMNLP.