Inspired by recent work in meta-learning and generative teaching networks, we propose a framework called Generative Conversational Networks, in which conversational agents learn to generate their own labelled training data (given some seed data) and then train themselves from that data to perform a given task. We use reinforcement learning to optimize the data generation process where the reward signal is the agent’s performance on the task. The task can be any language-related task, from intent detection to full task-oriented conversations. In this work, we show that our approach is able to generalise from seed data and performs well in limited data and limited computation settings, with significant gains for intent detection and slot tagging across multiple datasets: ATIS, TOD, SNIPS, and Restaurants8k. We show an average improvement of 35% in intent detection and 21% in slot tagging over a baseline model trained from the seed data. We also conduct an analysis of the novelty of the generated data and provide generated examples for intent detection, slot tagging, and non-goal oriented conversations.
This work introduces Focused-Variation Network (FVN), a novel model to control language generation. The main problems in previous controlled language generation models range from the difficulty of generating text according to the given attributes, to the lack of diversity of the generated texts. FVN addresses these issues by learning disjoint discrete latent spaces for each attribute inside codebooks, which allows for both controllability and diversity, while at the same time generating fluent text. We evaluate FVN on two text generation datasets with annotated content and style, and show state-of-the-art performance as assessed by automatic and human evaluations.
Some of the major challenges in training conversational agents include the lack of large-scale data of real-world complexity, defining appropriate evaluation measures, and managing meaningful conversations across many topics over long periods of time. Moreover, most works tend to assume that the conversational agent’s environment is stationary, a somewhat strong assumption. To remove this assumption and overcome the lack of data, we take a step away from the traditional training pipeline and model the conversation as a stochastic collaborative game. Each agent (player) has a role (“assistant”, “tourist”, “eater”, etc.) and their own objectives, and can only interact via language they generate. Each agent, therefore, needs to learn to operate optimally in an environment with multiple sources of uncertainty (its own LU and LG, the other agent’s LU, Policy, and LG). In this work, we present the first complete attempt at concurrently training conversational agents that communicate only via self-generated language and show that they outperform supervised and deep learning baselines.
Aiming to expand the current research paradigm for training conversational AI agents that can address real-world challenges, we take a step away from traditional slot-filling goal-oriented spoken dialogue systems (SDS) and model the dialogue in a way that allows users to be more expressive in describing their needs. The goal is to help users make informed decisions rather than being fed matching items. To this end, we describe the Linked-Data SDS (LD-SDS), a system that exploits semantic knowledge bases that connect to linked data, and supports complex constraints and preferences. We describe the required changes in language understanding and state tracking, and the need for mined features, and we report the promising results (in terms of semantic errors, effort, etc) of a preliminary evaluation after training two statistical dialogue managers in various conditions.
The number of applied Dialogue Systems is ever increasing in several service providing and other applications as a way to efficiently and inexpensively serve large numbers of customers. A DS that employs some form of adaptation to the environment and its users is called an Adaptive Dialogue System (ADS). A significant part of the research community has lately focused on ADS and many existing or novel techniques are being applied to this problem. One of the most promising techniques is Reinforcement Learning (RL) and especially online RL. This paper focuses on online RL techniques used to achieve adaptation in Dialogue Management and provides an evaluation of various such methods in an effort to aid the designers of ADS in deciding which method to use. To the best of our knowledge there is no other work to compare online RL techniques on the dialogue management problem.