Related papers: Structuring Latent Spaces for Stylized Response Ge…
Recent advances in pre-trained language models have significantly improved neural response generation. However, existing methods usually view the dialogue context as a linear sequence of tokens and learn to generate the next word through…
A multi-turn dialogue always follows a specific topic thread, and topic shift at the discourse level occurs naturally as the conversation progresses, necessitating the model's ability to capture different topics and generate topic-aware…
End-to-end neural approaches are becoming increasingly common in conversational scenarios due to their promising performances when provided with sufficient amount of data. In this paper, we present a novel methodology to address the…
Latent diffusion models offer an attractive alternative to discrete diffusion for non-autoregressive text generation by operating on continuous text representations and denoising entire sequences in parallel. The major challenge in latent…
Large language models (LLMs) have increased the demand for personalized and stylish content generation. However, closed-source models like GPT-4 present limitations in optimization opportunities, while the substantial training costs and…
Discourse coherence is strongly associated with text quality, making it important to natural language generation and understanding. Yet existing models of coherence focus on measuring individual aspects of coherence (lexical overlap,…
Sequence-to-Sequence (Seq2Seq) models have witnessed a notable success in generating natural conversational exchanges. Notwithstanding the syntactically well-formed responses generated by these neural network models, they are prone to be…
Non-parallel text style transfer is an important task in natural language generation. However, previous studies concentrate on the token or sentence level, such as sentence sentiment and formality transfer, but neglect long style transfer…
The spontaneous behavior that often occurs in conversations makes speech more human-like compared to reading-style. However, synthesizing spontaneous-style speech is challenging due to the lack of high-quality spontaneous datasets and the…
This work investigates style and topic aspects of language in online communities: looking at both utility as an identifier of the community and correlation with community reception of content. Style is characterized using a hybrid word and…
Latent space based GAN methods and attention based sequence to sequence models have achieved impressive results in text generation and unsupervised machine translation respectively. Leveraging the two domains, we propose an adversarial…
Thanks to their generative capabilities, large language models (LLMs) have become an invaluable tool for creative processes. These models have the capacity to produce hundreds and thousands of visual and textual outputs, offering abundant…
While many recent any-to-any voice conversion models succeed in transferring some target speech's style information to the converted speech, they still lack the ability to faithfully reproduce the speaking style of the target speaker. In…
Arbitrary Style Transfer (AST) aims to transform images by adopting the style from any selected artwork. Nonetheless, the need to accommodate diverse and subjective user preferences poses a significant challenge. While some users wish to…
We present a joint modeling approach to identify salient discussion points in spoken meetings as well as to label the discourse relations between speaker turns. A variation of our model is also discussed when discourse relations are treated…
As a means of modern communication tools, online discussion forums have become an increasingly popular platform that allows asynchronous online interactions. People share thoughts and opinions through posting threads and replies, which form…
With rapid progress in neural text-to-speech (TTS) models, personalized speech generation is now in high demand for many applications. For practical applicability, a TTS model should generate high-quality speech with only a few audio…
Generative Adversarial Networks (GANs) with style-based generators (e.g. StyleGAN) successfully enable semantic control over image synthesis, and recent studies have also revealed that interpretable image translations could be obtained by…
This paper proposes a novel end-to-end architecture for task-oriented dialogue systems. It is based on a simple and practical yet very effective sequence-to-sequence approach, where language understanding and state tracking tasks are…
Generating a long, coherent text such as a paragraph requires a high-level control of different levels of relations between sentences (e.g., tense, coreference). We call such a logical connection between sentences as a (paragraph) flow. In…