We propose Neural Responding Machine (NRM), a neural network-based response generator for Short-Text Conversation. NRM takes the general encoderdecoder framework: it formalizes the generation of response as a decoding process based on the latent representation of the input text, while both encoding and decoding are realized with recurrent neural networks (RNN). The NRM is trained with a large amount of one-round conversation data collected from a microblogging service. Empirical study shows that NRM can generate grammatically correct and content-wise appropriate responses to over 75% of the input text, outperforming stateof-the-arts in the same setting, including retrieval-based and SMT-based models.

http://www.hangli-hl.com/uploads/3/4/4/6/34465961/shang_et_al.__acl_2015.pdf

Neural Responding Machine for Short-Text Conversation

http://mi.eng.cam.ac.uk/~sjy/papers/wiyo07.pdf

Partially observable Markov decision processes for spoken dialog systems

Statistical dialog systems (SDSs) are motivated by the need for a data-driven framework that reduces the cost of laboriously handcrafting complex dialog managers and that provides robustness against the errors created by speech recognizers operating in noisy environments. By including an explicit Bayesian model of uncertainty and by optimizing the policy via a reward-driven process, partially observable Markov decision processes (POMDPs) provide such a framework. However, exact model representation and optimization is computationally intractable. Hence, the practical application of POMDP-based systems requires efficient algorithms and carefully constructed approximations. This review article provides an overview of the current state of the art in the development of POMDP-based spoken dialog systems.

/pdf/pomdp-based-statistical-spoken-dialog-systems-a-review-52td9wfczr.pdf

POMDP-Based Statistical Spoken Dialog Systems: A Review

Recent neural models of dialogue generation offer great promise for generating responses for conversational agents, but tend to be shortsighted, predicting utterances one at a time while ignoring their influence on future outcomes. Modeling the future direction of a dialogue is crucial to generating coherent, interesting dialogues, a need which led traditional NLP models of dialogue to draw on reinforcement learning. In this paper, we show how to integrate these goals, applying deep reinforcement learning to model future reward in chatbot dialogue. The model simulates dialogues between two virtual agents, using policy gradient methods to reward sequences that display three useful conversational properties: informativity, coherence, and ease of answering (related to forward-looking function). We evaluate our model on diversity, length as well as with human judges, showing that the proposed algorithm generates more interactive responses and manages to foster a more sustained conversation in dialogue simulation. This work marks a first step towards learning a neural conversational model based on the long-term success of dialogues.

/pdf/deep-reinforcement-learning-for-dialogue-generation-4ibyymy1c2.pdf

Deep Reinforcement Learning for Dialogue Generation

We present persona-based models for handling the issue of speaker consistency in neural response generation. A speaker model encodes personas in distributed embeddings that capture individual characteristics such as background information and speaking style. A dyadic speaker-addressee model captures properties of interactions between two interlocutors. Our models yield qualitative performance improvements in both perplexity and BLEU scores over baseline sequence-to-sequence models, with similar gains in speaker consistency as measured by human judges.

A Persona-Based Neural Conversation Model

Within the broad field of spoken dialogue systems, the application of machine-learning approaches to dialogue management strategy design is a rapidly growing research area. The main motivation is the hope of building systems that learn through trial-and-error interaction what constitutes a good dialogue strategy. Training of such systems could in theory be done using human users or using corpora of human–computer dialogue, but in practice the typically vast space of possible dialogue states and strategies cannot be explored without the use of automatic user simulation tools.This requirement for training statistical dialogue models has created an interesting new application area for predictive statistical user modelling and a variety of different techniques for simulating user behaviour have been presented in the literature ranging from simple Markov models to Bayesian networks. The development of reliable user simulation tools is critical to further progress on automatic dialogue management design but it holds many challenges, some of which have been encountered in other areas of current research on statistical user modelling, such as the problem of ‘concept drift’, the problem of combining content-based and collaboration-based modelling techniques, and user model evaluation. The latter topic is of particular interest, because simulation-based learning is currently one of the few applications of statistical user modelling that employs both direct ‘accuracy-based’ and indirect ‘utility-based’ evaluation techniques.In this paper, we briefly summarize the role of the dialogue manager in a spoken dialogue system, give a short introduction to reinforcement-learning of dialogue management strategies and review the literature on user modelling for simulation-based strategy learning. We further describe recent work on user model evaluation and discuss some of the current research issues in simulation-based learning from a user modelling perspective.

/pdf/a-survey-of-statistical-user-simulation-techniques-for-vxrq5a2bd4.pdf

A survey of statistical user simulation techniques for reinforcement-learning of dialogue management strategies

This paper investigates the problem of bootstrapping a statistical dialogue manager without access to training data and proposes a new probabilistic agenda-based method for simulating user behaviour. In experiments with a statistical POMDP dialogue system, the simulator was realistic enough to successfully test the prototype system and train a dialogue policy. An extensive study with human subjects showed that the learned policy was highly competitive, with task completion rates above 90%.

/pdf/agenda-based-user-simulation-for-bootstrapping-a-pomdp-57ofr2umhl.pdf

Agenda-Based User Simulation for Bootstrapping a POMDP Dialogue System

Partially observable Markov decision processes (POMDPs) provide a principled mathematical framework for modelling the uncertainty inherent in spoken dialog systems. However, conventional POMDPs scale poorly with the size of state and observation space. This paper describes a variation of the classic POMDP called the hidden information state (HIS) model in which belief distributions are represented efficiently by grouping states together into partitions and policy optimisation is made tractable by using a master to summary space mapping. An implementation of the HIS model is described for a Tourist Information application and aspects of its training and operation are illustrated.

The Hidden Information State Approach to Dialog Management

Over the past decade, a variety of user models have been proposed for user simulation-based reinforcement-learning of dialogue strategies. However, the strategies learned with these models are rarely evaluated in actual user trials and it remains unclear how the choice of user model affects the quality of the learned strategy. In particular, the degree to which strategies learned with a user model generalise to real user populations has not be investigated. This paper presents a series of experiments that qualitatively and quantitatively examine the effect of the user model on the learned strategy. Our results show that the performance and characteristics of the strategy are in fact highly dependent on the user model. Furthermore, a policy trained with a poor user model may appear to perform well when tested with the same model, but fail when tested with a more sophisticated user model. This raises significant doubts about the current practice of learning and evaluating strategies with the same user model. The paper further investigates a new technique for testing and comparing strategies directly on real human-machine dialogues, thereby avoiding any evaluation bias introduced by the user model

Effects of the user model on simulation-based learning of dialogue strategies

Most spoken language resources are produced and disseminated together with symbolic information relating to the speech signal. These are for instance orthographic transcripts, labeling and segmentation on the phonologic, phonetic, prosodic, phrasal level. Most of the known formats for these symbolic data are defined in a closed form that is not flexible enough to allow simple and platform-independent processing and easy extensions. At the Bavarian Archive for Speech Signals (BAS) a new format has been developed and used over the last few years that shows some significant advantages over other existing formats. This paper describes the basic principles behind this format, discusses briefly the advantages and gives detailed definitions of the description levels used so far

Karl Weilhammer

Papers

A survey of statistical user simulation techniques for reinforcement-learning of dialogue management strategies

Agenda-Based User Simulation for Bootstrapping a POMDP Dialogue System

The Hidden Information State Approach to Dialog Management

Effects of the user model on simulation-based learning of dialogue strategies

The partitur format at BAS.