Related papers: Seen to Unseen: Exploring Compositional Generaliza…
Recent advancements in large language models have revolutionized text generation with their remarkable capabilities. These models can produce controlled texts that closely adhere to specific requirements when prompted appropriately.…
Existing work on controlled text generation (CTG) assumes a control interface of categorical attributes. In this work, we propose a natural language (NL) interface, where we craft a PCFG to embed the control attributes into natural language…
Prompt learning with immensely large Casual Language Models (CLMs) has been shown promising for attribute-controllable text generation (CTG). However, vanilla prompt tuning tends to imitate training corpus characteristics beyond the control…
Large text-guided diffusion models, such as DALLE-2, are able to generate stunning photorealistic images given natural language descriptions. While such models are highly flexible, they struggle to understand the composition of certain…
Knowledge-grounded dialogue systems are intended to convey information that is based on evidence provided in a given source text. We discuss the challenges of training a generative neural dialogue model for such systems that is controlled…
Generalized compositional zero-shot learning means to learn composed concepts of attribute-object pairs in a zero-shot fashion, where a model is trained on a set of seen concepts and tested on a combined set of seen and unseen concepts.…
Dialogue systems need to produce responses that realize multiple types of dialogue acts (DAs) with high semantic fidelity. In the past, natural language generators (NLGs) for dialogue were trained on large parallel corpora that map from a…
Mixed-initiative dialogue tasks involve repeated exchanges of information and conversational control. Conversational agents gain control by generating responses that follow particular dialogue intents or strategies, prescribed by a policy…
Domain generalization (DG) attempts to generalize a model trained on single or multiple source domains to the unseen target domain. Benefiting from the success of Visual-and-Language Pre-trained models in recent years, we argue that it is…
Deep learning models struggle with compositional generalization, i.e. the ability to recognize or generate novel combinations of observed elementary concepts. In hopes of enabling compositional generalization, various unsupervised learning…
Diffusion-based generative models have exhibited powerful generative performance in recent years. However, as many attributes exist in the data distribution and owing to several limitations of sharing the model parameters across all levels…
Visual text recognition is undoubtedly one of the most extensively researched topics in computer vision. Great progress have been made to date, with the latest models starting to focus on the more practical "in-the-wild" setting. However, a…
There is a growing interest in improving the conversational ability of models by filtering the raw dialogue corpora. Previous filtering strategies usually rely on a scoring method to assess and discard samples from one perspective, enabling…
In this work, we propose a composition/decomposition framework for adversarially training generative models on composed data - data where each sample can be thought of as being constructed from a fixed number of components. In our…
Controlled Text Generation (CTG) aims to produce texts that exhibit specific desired attributes. In this study, we introduce a pluggable CTG framework for Large Language Models (LLMs) named Dynamic Attribute Graphs-based controlled text…
Motivated by the following two observations: 1) people are aging differently under different conditions for changeable facial attributes, e.g., skin color may become darker when working outside, and 2) it needs to keep some unchanged facial…
Composition-the ability to generate myriad variations from finite means-is believed to underlie powerful generalization. However, compositional generalization remains a key challenge for deep learning. A widely held assumption is that…
Target-guided response generation enables dialogue systems to smoothly transition a conversation from a dialogue context toward a target sentence. Such control is useful for designing dialogue systems that direct a conversation toward…
Leveraging the compositional nature of our world to expedite learning and facilitate generalization is a hallmark of human perception. In machine learning, on the other hand, achieving compositional generalization has proven to be an…
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…