Related papers: Speaker Sensitive Response Evaluation Model

Endowing dialogue systems with personas is essential to deliver more human-like conversations. However, this problem is still far from well explored due to the difficulties of both embodying personalities in natural languages and the…

We study knowledge-grounded dialogue generation with pre-trained language models. Instead of pursuing new state-of-the-art on benchmarks, we try to understand if the knowledge stored in parameters of the pre-trained models is already enough…

Models trained on large unlabeled corpora of human interactions will learn patterns and mimic behaviors therein, which include offensive or otherwise toxic behavior and unwanted biases. We investigate a variety of methods to mitigate these…

The article proposes a system for knowledge-based conversation designed for Social Robots and other conversational agents. The proposed system relies on an Ontology for the description of all concepts that may be relevant conversation…

Generating responses that are consistent with the dialogue context is one of the central challenges in building engaging conversational agents. We demonstrate that neural conversation models can be geared towards generating consistent…

Recent work on speech representation models jointly pre-trained with text has demonstrated the potential of improving speech representations by encoding speech and text in a shared space. In this paper, we leverage such shared…

During the past decade, several areas of speech and language understanding have witnessed substantial breakthroughs from the use of data-driven models. In the area of dialogue systems, the trend is less obvious, and most practical systems…

The ability of a dialog system to express consistent language style during conversations has a direct, positive impact on its usability and on user satisfaction. Although previous studies have demonstrated that style transfer is feasible…

Endowing a chatbot with personality or an identity is quite challenging but critical to deliver more realistic and natural conversations. In this paper, we address the issue of generating responses that are coherent to a pre-specified agent…

Twitter is a well-known microblogging social site where users express their views and opinions in real-time. As a result, tweets tend to contain valuable information. With the advancements of deep learning in the domain of natural language…

Effective evaluation methods remain a significant challenge for research on open-domain conversational dialogue systems. Explicit satisfaction ratings can be elicited from users, but users often do not provide ratings when asked, and those…

We investigate the task of building open domain, conversational dialogue systems based on large dialogue corpora using generative models. Generative models produce system responses that are autonomously generated word-by-word, opening up…

We introduce Generative Spoken Language Modeling, the task of learning the acoustic and linguistic characteristics of a language from raw audio (no text, no labels), and a set of metrics to automatically evaluate the learned representations…

This paper presents an automatic method to evaluate the naturalness of natural language generation in dialogue systems. While this task was previously rendered through expensive and time-consuming human labor, we present this novel task of…

Automatic Speech Scoring (ASS) is the computer-assisted evaluation of a candidate's speaking proficiency in a language. ASS systems face many challenges like open grammar, variable pronunciations, and unstructured or semi-structured…

At the heart of improving conversational AI is the open problem of how to evaluate conversations. Issues with automatic metrics are well known (Liu et al., 2016, arXiv:1603.08023), with human evaluations still considered the gold standard.…

Humans' perception system closely monitors audio-visual cues during multiparty interactions to react timely and naturally. Learning to predict timing and type of reaction responses during human-human interactions may help us to enrich…

In communication, a human would recognize the emotion of an interlocutor and respond with an appropriate emotion, such as empathy and comfort. Toward developing a dialogue system with such a human-like ability, we propose a method to build…

The natural language generation (NLG) component of a spoken dialogue system (SDS) usually needs a substantial amount of handcrafting or a well-labeled dataset to be trained on. These limitations add significantly to development costs and…

Statistical spoken dialogue systems usually rely on a single- or multi-domain dialogue model that is restricted in its capabilities of modelling complex dialogue structures, e.g., relations. In this work, we propose a novel dialogue model…