Related papers: Predict and Use Latent Patterns for Short-Text Con…

This paper presents a deep learning architecture for the semantic decoder component of a Statistical Spoken Dialogue System. In a slot-filling dialogue, the semantic decoder predicts the dialogue act and a set of slot-value pairs from a set…

Current approaches for controlling dialogue response generation are primarily focused on high-level attributes like style, sentiment, or topic. In this work, we focus on constrained long-term dialogue generation, which involves more…

Recent advances in neural-based generative modeling have reignited the hopes of having computer systems capable of conversing with humans and able to understand natural language. The employment of deep neural architectures has been largely…

This thesis advances semantic representation learning to render language representations or models more semantically and geometrically interpretable, and to enable localised, quasi-symbolic, compositional control through deliberate shaping…

Conventional topic models are ineffective for topic extraction from microblog messages, because the data sparseness exhibited in short messages lacking structure and contexts results in poor message-level word co-occurrence patterns. To…

Conversational modeling is an important task in natural language understanding and machine intelligence. Although previous approaches exist, they are often restricted to specific domains (e.g., booking an airline ticket) and require…

We propose a generative model for a sentence that uses two latent variables, with one intended to represent the syntax of the sentence and the other to represent its semantics. We show we can achieve better disentanglement between semantic…

Structured sentences are important expressions in human writings and dialogues. Previous works on neural text generation fused semantic and structural information by encoding the entire sentence into a mixed hidden representation. However,…

Prior work on controllable text generation usually assumes that the controlled attribute can take on one of a small set of values known a priori. In this work, we propose a novel task, where the syntax of a generated sentence is controlled…

This paper develops an edge-device collaborative Generative Semantic Communications (Gen SemCom) framework leveraging pre-trained Multi-modal/Vision Language Models (M/VLMs) for ultra-low-rate semantic communication via textual prompts. The…

Recent advances in neural sequence-to-sequence models have led to promising results for several language generation-based tasks, including dialogue response generation, summarization, and machine translation. However, these models are known…

Whereas the recent emergence of large language models (LLMs) like ChatGPT has exhibited impressive general performance, it still has a large gap with fully-supervised models on specific tasks such as multi-span question answering. Previous…

We present a generative model for multitask conditional language generation. Our guiding hypothesis is that a shared set of latent skills underlies many disparate language generation tasks, and that explicitly modelling these skills in a…

To model diverse responses for a given post, one promising way is to introduce a latent variable into Seq2Seq models. The latent variable is supposed to capture the discourse-level information and encourage the informativeness of target…

Controlling the behavior of language models (LMs) without re-training is a major open problem in natural language generation. While recent works have demonstrated successes on controlling simple sentence attributes (e.g., sentiment), there…

Translation into morphologically-rich languages challenges neural machine translation (NMT) models with extremely sparse vocabularies where atomic treatment of surface forms is unrealistic. This problem is typically addressed by either…

Language models trained on large text corpora encode rich distributional information about real-world environments and action sequences. This information plays a crucial role in current approaches to language processing tasks like question…

Prompt engineering is widely used to shape large language model behavior, yet it is often treated as a practical heuristic rather than as a form of natural-language control. This paper develops a cognitive-semantic account in which prompts…

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…

Recently, utilizing deep neural networks to build the opendomain dialogue models has become a hot topic. However, the responses generated by these models suffer from many problems such as responses not being contextualized and tend to…