Related papers: Deploying Lifelong Open-Domain Dialogue Learning

To train a statistical spoken dialogue system (SDS) it is essential that an accurate method for measuring task success is available. To date training has relied on presenting a task to either simulated or paid users and inferring the…

Current approaches to Natural Language Generation (NLG) for dialog mainly focus on domain-specific, task-oriented applications (e.g. restaurant booking) using limited ontologies (up to 20 slot types), usually without considering the…

Task-oriented dialogue systems are designed to achieve specific goals while conversing with humans. In practice, they may have to handle simultaneously several domains and tasks. The dialogue manager must therefore be able to take into…

Recently, various methods have been proposed to create open-domain conversational agents with Large Language Models (LLMs). These models are able to answer user queries, but in a one-way Q&A format rather than a true conversation.…

Pre-training on larger datasets with ever increasing model size is now a proven recipe for increased performance across almost all NLP tasks. A notable exception is information retrieval, where additional pre-training has so far failed to…

Many real-world open-domain conversation applications have specific goals to achieve during open-ended chats, such as recommendation, psychotherapy, education, etc. We study the problem of imposing conversational goals on open-domain chat…

The practical success of much of NLP depends on the availability of training data. However, in real-world scenarios, training data is often scarce, not least because many application domains are restricted and specific. In this work, we…

Artificially intelligent agents equipped with strategic skills that can negotiate during their interactions with other natural or artificial agents are still underdeveloped. This paper describes a successful application of Deep…

The ability of a machine to communicate with humans has long been associated with the general success of AI. This dates back to Alan Turing's epoch-making work in the early 1950s, which proposes that a machine's intelligence can be tested…

Transformer-based open-domain dialog models have become increasingly popular in recent years. These models typically represent context as a concatenation of a dialog history. However, there is no criterion to decide how many utterances…

We present a method for combining multi-agent communication and traditional data-driven approaches to natural language learning, with an end goal of teaching agents to communicate with humans in natural language. Our starting point is a…

As practitioners increasingly deploy machine learning models in critical domains such as health care, finance, and policy, it becomes vital to ensure that domain experts function effectively alongside these models. Explainability is one way…

Despite many recent advances for the design of dialogue systems, a true bottleneck remains the acquisition of data required to train its components. Unlike many other language processing applications, dialogue systems require interactions…

Conversational Spoken Language Models (SLMs) are emerging as a promising paradigm for real-time speech interaction. However, their capacity of temporal dynamics, including the ability to manage timing, tempo and simultaneous speaking,…

Dialog state tracking (DST) suffers from severe data sparsity. While many natural language processing (NLP) tasks benefit from transfer learning and multi-task learning, in dialog these methods are limited by the amount of available data…

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…

Human conversation is inherently complex, often spanning many different topics/domains. This makes policy learning for dialogue systems very challenging. Standard flat reinforcement learning methods do not provide an efficient framework for…

I propose a paradigm for scientific progress in NLP centered around developing scalable, data-driven theories of linguistic structure. The idea is to collect data in tightly scoped, carefully defined ways which allow for exhaustive…

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…

Dialogue-based human-AI collaboration can revolutionize collaborative problem-solving, creative exploration, and social support. To realize this goal, the development of automated agents proficient in skills such as negotiating, following…