Related papers: GenTUS: Simulating User Behaviour and Language in …
Speech synthesis is used in a wide variety of industries. Nonetheless, it always sounds flat or robotic. The state of the art methods that allow for prosody control are very cumbersome to use and do not allow easy tuning. To tackle some of…
Recent advancements in large language models (LLMs) have led to significant progress in text-based dialogue systems. These systems can now generate high-quality responses that are accurate and coherent across a wide range of topics and…
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…
Large language models (LLMs) are increasingly seen as assistants, copilots, and consultants, capable of supporting a wide range of tasks through natural conversation. However, most systems remain constrained by a linear request-response…
Along with the development of systems for natural language understanding and generation, dialog systems have been widely adopted for language learning and practicing. Many current educational dialog systems perform chitchat, where the…
Cross-domain natural language generation (NLG) is still a difficult task within spoken dialogue modelling. Given a semantic representation provided by the dialogue manager, the language generator should generate sentences that convey…
Early work on narrative modeling used explicit plans and goals to generate stories, but the language generation itself was restricted and inflexible. Modern methods use language models for more robust generation, but often lack an explicit…
User Simulators play a pivotal role in training and evaluating task-oriented dialogue systems. Traditional user simulators typically rely on human-engineered agendas, resulting in generated responses that often lack diversity and…
During speech, people spontaneously gesticulate, which plays a key role in conveying information. Similarly, realistic co-speech gestures are crucial to enable natural and smooth interactions with social agents. Current end-to-end co-speech…
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…
Task-oriented dialogue systems (TDSs) are assessed mainly in an offline setting or through human evaluation. The evaluation is often limited to single-turn or is very time-intensive. As an alternative, user simulators that mimic user…
With the development of pre-trained language models, remarkable success has been witnessed in dialogue understanding (DU). However, current DU approaches usually employ independent models for each distinct DU task without considering shared…
Generic generation and manipulation of text is challenging and has limited success compared to recent deep generative modeling in visual domain. This paper aims at generating plausible natural language sentences, whose attributes are…
The GPT (Generative Pre-trained Transformer) language models are an artificial intelligence and natural language processing technology that enables automatic text generation. There is a growing interest in applying GPT language models to…
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…
Natural language generators (NLGs) for task-oriented dialogue typically take a meaning representation (MR) as input. They are trained end-to-end with a corpus of MR/utterance pairs, where the MRs cover a specific set of dialogue acts and…
Recent advancements in reasoning abilities of Large Language Models (LLM) has promoted their usage in problems that require high-level planning for robots and artificial agents. However, current techniques that utilize LLMs for such…
Inspired by recent work in meta-learning and generative teaching networks, we propose a framework called Generative Conversational Networks, in which conversational agents learn to generate their own labelled training data (given some seed…
An effective multi-turn instruction-following assistant can be developed by creating a simulator that can generate useful interaction data. Apart from relying on its intrinsic weights, an ideal user simulator should also be able to…
In this report we describe the implementation and approach developed during the GENIUS Project. The GENIUS project is about the generation of usable user interfaces. It tries to cope with issues related to automatic generation where,…