Related papers: Learning From Free-Text Human Feedback -- Collect …
A well-designed interactive human-like dialogue system is expected to take actions (e.g. smiling) and respond in a pattern similar to humans. However, due to the limitation of single-modality (only speech) or small volume of currently…
The rapid advancement of large language models (LLMs) has led to growing interest in using synthetic data to train future models. However, this creates a self-consuming retraining loop, where models are trained on their own outputs and may…
While automatic dialogue tutors hold great potential in making education personalized and more accessible, research on such systems has been hampered by a lack of sufficiently large and high-quality datasets. Collecting such datasets…
Many machine learning systems today are trained on large amounts of human-annotated data. Data annotation tasks that require a high level of competency make data acquisition expensive, while the resulting labels are often subjective,…
Language generation models' democratization benefits many domains, from answering health-related questions to enhancing education by providing AI-driven tutoring services. However, language generation models' democratization also makes it…
Access to humanities research databases is often hindered by the limitations of traditional interaction formats, particularly in the methods of searching and response generation. This study introduces an LLM-based smart assistant designed…
Large Language Models have found application in various mundane and repetitive tasks including Human Resource (HR) support. We worked with the domain experts of SAP SE to develop an HR support chatbot as an efficient and effective tool for…
The remarkable multimodal capabilities demonstrated by OpenAI's GPT-4 have sparked significant interest in the development of multimodal Large Language Models (LLMs). A primary research objective of such models is to align visual and…
In Task-Oriented Dialogue (TOD) systems, correctly updating the system's understanding of the user's needs is key to a smooth interaction. Traditionally TOD systems are composed of several modules that interact with one another. While each…
Advances in text-to-speech (TTS) technology have significantly improved the quality of generated speech, closely matching the timbre and intonation of the target speaker. However, due to the inherent complexity of human emotional…
Recently emerged intelligent assistants on smartphones and home electronics (e.g., Siri and Alexa) can be seen as novel hybrids of domain-specific task-oriented spoken dialogue systems and open-domain non-task-oriented ones. To realize such…
Large crowdsourced datasets are widely used for training and evaluating neural models on natural language inference (NLI). Despite these efforts, neural models have a hard time capturing logical inferences, including those licensed by…
Identifying user preferences in dialogue systems is a pivotal aspect of providing satisfying services. Current research shows that using large language models (LLMs) to fine-tune a task-specific preference extractor yields excellent results…
MultiWOZ is one of the most popular multi-domain task-oriented dialog datasets, containing 10K+ annotated dialogs covering eight domains. It has been widely accepted as a benchmark for various dialog tasks, e.g., dialog state tracking…
Humor is a fundamental facet of human cognition and interaction. Yet, despite recent advances in natural language processing, humor detection remains a challenging task that is complicated by the scarcity of datasets that pair humorous…
Collecting human judgements is currently the most reliable evaluation method for natural language generation systems. Automatic metrics have reported flaws when applied to measure quality aspects of generated text and have been shown to…
Knowledge-based, open-domain dialogue generation aims to build chit-chat systems that talk to humans using mined support knowledge. Many types and sources of knowledge have previously been shown to be useful as support knowledge. Even in…
A series of datasets and models have been proposed for summaries generated for well-formatted documents such as news articles. Dialogue summaries, however, have been under explored. In this paper, we present the first dataset with…
Stylistic variation is critical to render the utterances generated by conversational agents natural and engaging. In this paper, we focus on sequence-to-sequence models for open-domain dialogue response generation and propose a new method…
The training of task-oriented dialogue systems is often confronted with the lack of annotated data. In contrast to previous work which augments training data through expensive crowd-sourcing efforts, we propose four different automatic…