Related papers: A BiRGAT Model for Multi-intent Spoken Language Un…

Most popular goal-oriented dialogue agents are capable of understanding the conversational context. However, with the surge of virtual assistants with screen, the next generation of agents are required to also understand screen context in…

Language-guided segmentation transcends the scope limitations of traditional semantic segmentation, enabling models to segment arbitrary target regions based on natural language instructions. Existing approaches typically adopt a two-stage…

Spoken Language Understanding (SLU) is an essential part of the spoken dialogue system, which typically consists of intent detection (ID) and slot filling (SF) tasks. Recently, recurrent neural networks (RNNs) based methods achieved the…

Large Language Models (LLM) and Vision Language Models (VLM) enable robots to ground natural language prompts into control actions to achieve tasks in an open world. However, when applied to a long-horizon collaborative task, this…

Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated remarkable progress in visual understanding. This impressive leap raises a compelling question: how can language models, initially trained solely on…

Existing research for image text retrieval mainly relies on sentence-level supervision to distinguish matched and mismatched sentences for a query image. However, semantic mismatch between an image and sentences usually happens in finer…

Prompt learning has become a prevalent strategy for adapting vision-language foundation models to downstream tasks. As large language models (LLMs) have emerged, recent studies have explored the use of category-related descriptions as input…

Speaker intent detection and semantic slot filling are two critical tasks in spoken language understanding (SLU) for dialogue systems. In this paper, we describe a recurrent neural network (RNN) model that jointly performs intent detection,…

Analyzing how human beings resolve syntactic ambiguity has long been an issue of interest in the field of linguistics. It is, at the same time, one of the most challenging issues for spoken language understanding (SLU) systems as well. As…

Prompt learning has become a prevalent strategy for adapting vision-language foundation models (VLMs) such as CLIP to downstream tasks. With the emergence of large language models (LLMs), recent studies have explored the potential of using…

Even as pre-trained language models share a semantic encoder, natural language understanding suffers from a diversity of output schemas. In this paper, we propose UBERT, a unified bidirectional language understanding model based on BERT…

Multilingual intent classification is central to customer-service systems on global logistics platforms, where models must process noisy user queries across languages and hierarchical label spaces. Yet most existing multilingual benchmarks…

This work shows how to improve and interpret the commonly used dual encoder model for response suggestion in dialogue. We present an attentive dual encoder model that includes an attention mechanism on top of the extracted word-level…

Intent classification is a task in spoken language understanding. An intent classification system is usually implemented as a pipeline process, with a speech recognition module followed by text processing that classifies the intents. There…

Intent-based recommender systems have garnered significant attention for uncovering latent fine-grained preferences. Intents, as underlying factors of interactions, are crucial for improving recommendation interpretability. Most methods…

Language exhibits structure at different scales, ranging from subwords to words, sentences, paragraphs, and documents. To what extent do deep models capture information at these scales, and can we force them to better capture structure…

At the heart of all automated driving systems is the ability to sense the surroundings, e.g., through semantic segmentation of LiDAR sequences, which experienced a remarkable progress due to the release of large datasets such as…

Semantic communication has recently attracted significant interest from both industry and academia due to its potential to transform the existing data-focused communication architecture towards a more generally intelligent and goal-oriented…

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…

Recent efforts of multimodal Transformers have improved Visually Rich Document Understanding (VrDU) tasks via incorporating visual and textual information. However, existing approaches mainly focus on fine-grained elements such as words and…