Related papers: DiscoFuse: A Large-Scale Dataset for Discourse-Bas…

NLP models that compare or consolidate information across multiple documents often struggle when challenged with recognizing substantial information redundancies across the texts. For example, in multi-document summarization it is crucial…

Currently, no large-scale training data is available for the task of scientific paper summarization. In this paper, we propose a novel method that automatically generates summaries for scientific papers, by utilizing videos of talks at…

The automatic co-speech gesture generation draws much attention in computer animation. Previous works designed network structures on individual datasets, which resulted in a lack of data volume and generalizability across different motion…

Expressive speech synthesis requires vibrant prosody and well-timed pauses. We propose an effective strategy to augment a small dataset to train an expressive end-to-end Text-to-Speech model. We merge audios of emotionally congruent text…

In this paper, we address the task of learning novel visual concepts, and their interactions with other concepts, from a few images with sentence descriptions. Using linguistic context and visual features, our method is able to efficiently…

Dialogue state tracking (DST) aims at estimating the current dialogue state given all the preceding conversation. For multi-domain DST, the data sparsity problem is a major obstacle due to increased numbers of state candidates and dialogue…

Conversational assistants often require a question rewriting algorithm that leverages a subset of past interactions to provide a more meaningful (accurate) answer to the user's question or request. However, the exact rewriting approach may…

Despite advancements in conversational AI, language models encounter challenges to handle diverse conversational tasks, and existing dialogue dataset collections often lack diversity and comprehensiveness. To tackle these issues, we…

Most Reading Comprehension methods limit themselves to queries which can be answered using a single sentence, paragraph, or document. Enabling models to combine disjoint pieces of textual evidence would extend the scope of machine…

With the rapid development of large language models, researchers have created increasingly advanced spoken dialogue systems that can naturally converse with humans. However, these systems still struggle to handle the full complexity of…

Dialogue segmentation is a crucial task for dialogue systems allowing a better understanding of conversational texts. Despite recent progress in unsupervised dialogue segmentation methods, their performances are limited by the lack of…

Given the prevalence of crowd sourced labor in creating Natural Language processing datasets, these aforementioned sets have become increasingly large. For instance, the SQUAD dataset currently sits at over 80,000 records. However, because…

Large Language Models (LLMs) are increasingly employed in multi-turn conversational tasks, yet their pre-training data predominantly consists of continuous prose, creating a potential mismatch between required capabilities and training…

In this paper, we investigate the use of diffusion models which are pre-trained on large-scale image-caption pairs for open-vocabulary 3D semantic understanding. We propose a novel method, namely Diff2Scene, which leverages frozen…

Diffusion-based scene text synthesis has progressed rapidly, yet existing methods commonly rely on additional visual conditioning modules and require large-scale annotated data to support multilingual generation. In this work, we revisit…

The increased interest in diffusion models has opened up opportunities for advancements in generative text modeling. These models can produce impressive images when given a well-crafted prompt, but creating a powerful or meaningful prompt…

Nowadays, open-domain dialogue models can generate acceptable responses according to the historical context based on the large-scale pre-trained language models. However, they generally concatenate the dialogue history directly as the model…

Conversational search provides a natural interface for information retrieval (IR). Recent approaches have demonstrated promising results in applying dense retrieval to conversational IR. However, training dense retrievers requires large…

Retrieval-Augmented Generation (RAG) has emerged as an important means of enhancing the performance of large language models (LLMs) in knowledge-intensive tasks. However, most existing RAG strategies treat retrieved passages in a flat and…

This work introduces Sample-Efficient Speech Diffusion (SESD), an algorithm for effective speech synthesis in modest data regimes through latent diffusion. It is based on a novel diffusion architecture, that we call U-Audio Transformer…