Related papers: Automatically Exposing Problems with Neural Dialog…

Neural text generation models conditioning on given input (e.g. machine translation and image captioning) are usually trained by maximum likelihood estimation of target text. However, the trained models suffer from various types of errors…

Investigating cooperativity of interlocutors is central in studying pragmatics of dialogue. Models of conversation that only assume cooperative agents fail to explain the dynamics of strategic conversations. Thus, we investigate the ability…

Complex, multi-task problems have proven to be difficult to solve efficiently in a sparse-reward reinforcement learning setting. In order to be sample efficient, multi-task learning requires reuse and sharing of low-level policies. To…

Consistency is one of the major challenges faced by dialogue agents. A human-like dialogue agent should not only respond naturally, but also maintain a consistent persona. In this paper, we exploit the advantages of natural language…

Open-domain dialog systems (also known as chatbots) have increasingly drawn attention in natural language processing. Some of the recent work aims at incorporating affect information into sequence-to-sequence neural dialog modeling, making…

Building a dialogue system that can communicate naturally with humans is a challenging yet interesting problem of agent-based computing. The rapid growth in this area is usually hindered by the long-standing problem of data scarcity as…

Collecting data for training dialog systems can be extremely expensive due to the involvement of human participants and need for extensive annotation. Especially in document-grounded dialog systems, human experts need to carefully read the…

We study emergent communication in a multi-agent reinforcement learning setting, where the agents solve cooperative tasks and have access to a communication channel. The communication channel may consist of either discrete symbols or…

Although deep learning models have brought tremendous advancements to the field of open-domain dialogue response generation, recent research results have revealed that the trained models have undesirable generation behaviors, such as…

The wave of pre-training language models has been continuously improving the quality of the machine-generated conversations, however, some of the generated responses still suffer from excessive repetition, sometimes repeating words from…

Socialbots are software-driven user accounts on social platforms, acting autonomously (mimicking human behavior), with the aims to influence the opinions of other users or spread targeted misinformation for particular goals. As socialbots…

Neural conversation models are attractive because one can train a model directly on dialog examples with minimal labeling. With a small amount of data, however, they often fail to generalize over test data since they tend to capture…

Autoregressive models used to generate responses in open-domain dialogue systems often struggle to take long-term context into account and to maintain consistency over a dialogue. Previous research in open-domain dialogue generation has…

The frustratingly fragile nature of neural network models make current natural language generation (NLG) systems prone to backdoor attacks and generate malicious sequences that could be sexist or offensive. Unfortunately, little effort has…

Dialogue policy learning for task-oriented dialogue systems has enjoyed great progress recently mostly through employing reinforcement learning methods. However, these approaches have become very sophisticated. It is time to re-evaluate it.…

Neural networks are among the most accurate supervised learning methods in use today. However, their opacity makes them difficult to trust in critical applications, especially when conditions in training may differ from those in practice.…

This paper introduces an adversarial method to stress-test trained metrics to evaluate conversational dialogue systems. The method leverages Reinforcement Learning to find response strategies that elicit optimal scores from the trained…

We propose an online, end-to-end, neural generative conversational model for open-domain dialogue. It is trained using a unique combination of offline two-phase supervised learning and online human-in-the-loop active learning. While most…

Natural language processing (NLP) systems have been proven to be vulnerable to backdoor attacks, whereby hidden features (backdoors) are trained into a language model and may only be activated by specific inputs (called triggers), to trick…

We present and evaluate a new model for Natural Language Generation (NLG) in Spoken Dialogue Systems, based on statistical planning, given noisy feedback from the current generation context (e.g. a user and a surface realiser). We study its…