Related papers: Trainable Referring Expression Generation using Ov…
Retrieval-Augmented Generation (RAG) has emerged as the dominant technique to provide \emph{Large Language Models} (LLM) with fresh and relevant context, mitigating the risk of hallucinations and improving the overall quality of responses…
Ephemeral group recommendation (EGR) aims to suggest items for a group of users who come together for the first time. Existing work typically consider individual preferences as the sole factor in aggregating group preferences. However, they…
Speakers' referential expressions often depart from communicative ideals in ways that help illuminate the nature of pragmatic language use. Patterns of overmodification, in which a speaker uses a modifier that is redundant given their…
We present and evaluate a new model for Natural Language Generation (NLG) in Spoken Dialogue Systems, based on statistical planning, given noisy feedback from the current generation context (e.g. a user and a surface realiser). We study its…
Speaker recognition, recognizing speaker identities based on voice alone, enables important downstream applications, such as personalization and authentication. Learning speaker representations, in the context of supervised learning,…
Transfer learning has proven to be crucial in advancing the state of speech and natural language processing research in recent years. In speech, a model pre-trained by self-supervised learning transfers remarkably well on multiple tasks.…
Guidance techniques are simple yet effective for improving conditional generation in diffusion models. Albeit their empirical success, the practical implementation of guidance diverges significantly from its theoretical motivation. In this…
Retrieval-Augmented Generation (RAG) has demonstrated strong effectiveness in knowledge-intensive tasks by grounding language generation in external evidence. Despite its success, many existing RAG systems are built based on a…
One common approach for question answering over speech data is to first transcribe speech using automatic speech recognition (ASR) and then employ text-based retrieval-augmented generation (RAG) on the transcriptions. While this cascaded…
Personalized text generation aims to infer users' writing style preferences from their historical texts and generate outputs that faithfully reflect these stylistic characteristics. Existing solutions primarily adopt two paradigms:…
Referring Expression Comprehension (REC) aims to identify a particular object in a scene by a natural language expression, and is an important topic in visual language understanding. State-of-the-art methods for this task are based on deep…
The prediction of valence from speech is an important, but challenging problem. The externalization of valence in speech has speaker-dependent cues, which contribute to performances that are often significantly lower than the prediction of…
While Retrieval-Augmented Generation (RAG) has exhibited promise in utilizing external knowledge, its generation process heavily depends on the quality and accuracy of the retrieved context. Large language models (LLMs) struggle to evaluate…
Data augmentation techniques have been widely used to improve machine learning performance as they enhance the generalization capability of models. In this work, to generate high quality synthetic data for low-resource tagging tasks, we…
Retrieval-augmented generation (RAG) systems rely on retrieval models for identifying relevant contexts and answer generation models for utilizing those contexts. However, retrievers exhibit imperfect recall and precision, limiting…
REPA and its variants effectively mitigate training challenges in diffusion models by incorporating external visual representations from pretrained models, through alignment between the noisy hidden projections of denoising networks and…
One of the biggest challenges in the development and deployment of spoken dialogue systems is the design of the spoken language generation module. This challenge arises from the need for the generator to adapt to many features of the…
Conversational recommender systems have attracted immense attention recently. The most recent approaches rely on neural models trained on recorded dialogs between humans, implementing an end-to-end learning process. These systems are…
Large Language Models (LLMs) have been integrated into recommendation systems to enhance user behavior comprehension. The Retrieval Augmented Generation (RAG) technique is further incorporated into these systems to retrieve more relevant…
Referring Expression Segmentation (RES) aims to generate a segmentation mask for the object described by a given language expression. Existing classic RES datasets and methods commonly support single-target expressions only, i.e., one…