Related papers: Modeling and Utilizing User's Internal State in Mo…
Building dialog agents that can converse naturally with humans is a challenging yet intriguing problem of artificial intelligence. In open-domain human-computer conversation, where the conversational agent is expected to respond to human…
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…
Dialogue Systems are tools designed for various practical purposes concerning human-machine interaction. These systems should be built on ethical foundations because their behavior may heavily influence a user (think especially about…
How do we communicate with others to achieve our goals? We use our prior experience or advice from others, or construct a candidate utterance by predicting how it will be received. However, our experiences are limited and biased, and…
We present "AutoJudge", an automated evaluation method for conversational dialogue systems. The method works by first generating dialogues based on self-talk, i.e. dialogue systems talking to itself. Then, it uses human ratings on these…
When two people pay attention to each other and are interested in what the other has to say or write, they almost instantly adapt their writing/speaking style to match the other. For a successful interaction with a user, chatbots and…
We study open domain dialogue generation with dialogue acts designed to explain how people engage in social chat. To imitate human behavior, we propose managing the flow of human-machine interactions with the dialogue acts as policies. The…
The performance of a task-completion dialogue agent usually affects the user experience: when the conversation system yields an unreasonable response, users may feel dissatisfied. Besides, early termination often occurs in disappointing…
We introduce end-to-end neural network based models for simulating users of task-oriented dialogue systems. User simulation in dialogue systems is crucial from two different perspectives: (i) automatic evaluation of different dialogue…
In this paper we explain how contextual expectations are generated and used in the task-oriented spoken language understanding system Dialogos. The hard task of recognizing spontaneous speech on the telephone may greatly benefit from the…
In this work, we present a hybrid learning method for training task-oriented dialogue systems through online user interactions. Popular methods for learning task-oriented dialogues include applying reinforcement learning with user feedback…
While language models (LMs) offer great potential for conversational recommender systems (CRSs), the paucity of public CRS data makes fine-tuning LMs for CRSs challenging. In response, LMs as user simulators qua data generators can be used…
Spoken dialogue systems (SDSs) utilize automatic speech recognition (ASR) at the front end of their pipeline. The role of ASR in SDSs is to recognize information in user speech related to response generation appropriately. Examining…
The concept of a Human-AI team has gained increasing attention in recent years. For effective collaboration between humans and AI teammates, proactivity is crucial for close coordination and effective communication. However, the design of…
We present an automated evaluation method to measure fluidity in conversational dialogue systems. The method combines various state of the art Natural Language tools into a classifier, and human ratings on these dialogues to train an…
Task-oriented dialogue systems (TODS) are continuing to rise in popularity as various industries find ways to effectively harness their capabilities, saving both time and money. However, even state-of-the-art TODS are not yet reaching their…
Most task-oriented dialogue (TOD) benchmarks assume users that know exactly how to use the system by constraining the user behaviors within the system's capabilities via strict user goals, namely "user familiarity" bias. This data bias…
Traditional recommendation systems produce static rather than interactive recommendations invariant to a user's specific requests, clarifications, or current mood, and can suffer from the cold-start problem if their tastes are unknown.…
Language models are often used as the backbone of modern dialogue systems. These models are pre-trained on large amounts of written fluent language. Repetition is typically penalised when evaluating language model generations. However, it…
Frozen models trained to mimic static datasets can never improve their performance. Models that can employ internet-retrieval for up-to-date information and obtain feedback from humans during deployment provide the promise of both adapting…