Related papers: DARER: Dual-task Temporal Relational Recurrent Rea…

The human brain constructs emotional percepts not by processing facial expressions in isolation, but through a dynamic, hierarchical integration of sensory input with semantic and contextual knowledge. However, existing vision-based dynamic…

We propose a novel multi-task pre-training method for Speech Emotion Recognition (SER). We pre-train SER model simultaneously on Automatic Speech Recognition (ASR) and sentiment classification tasks to make the acoustic ASR model more…

Graph-based temporal classification (GTC), a generalized form of the connectionist temporal classification loss, was recently proposed to improve automatic speech recognition (ASR) systems using graph-based supervision. For example, GTC was…

Previous data-driven work investigating the types and distributions of discourse relation signals, including discourse markers such as 'however' or phrases such as 'as a result' has focused on the relative frequencies of signal words within…

Dialogue meaning representation formulates natural language utterance semantics in their conversational context in an explicit and machine-readable form. Previous work typically follows the intent-slot framework, which is easy for…

An effective understanding of the environment and accurate trajectory prediction of surrounding dynamic obstacles are indispensable for intelligent mobile systems (e.g. autonomous vehicles and social robots) to achieve safe and high-quality…

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…

Recent advances in deep forecasting models have achieved remarkable performance, yet most approaches still struggle to provide both accurate predictions and interpretable insights into temporal dynamics. This paper proposes CaReTS, a novel…

Emotion detection is a critical technology extensively employed in diverse fields. While the incorporation of commonsense knowledge has proven beneficial for existing emotion detection methods, dialogue-based emotion detection encounters…

Human dialogue contains evolving concepts, and speakers naturally associate multiple concepts to compose a response. However, current dialogue models with the seq2seq framework lack the ability to effectively manage concept transitions and…

Cross-domain sentiment classification (CDSC) is an importance task in domain adaptation and sentiment classification. Due to the domain discrepancy, a sentiment classifier trained on source domain data may not works well on target domain…

Speech emotion recognition (SER) models typically rely on costly human-labeled data for training, making scaling methods to large speech datasets and nuanced emotion taxonomies difficult. We present LanSER, a method that enables the use of…

Retrieval-Augmented Generation (RAG) utilizes external knowledge to augment Large Language Models' (LLMs) reliability. For flexibility, agentic RAG employs autonomous, multi-round retrieval and reasoning to resolve queries. Although recent…

Existing deep learning-enabled semantic communication systems often rely on shared background knowledge between the transmitter and receiver that includes empirical data and their associated semantic information. In practice, the semantic…

Complex dialog systems often use retrieved evidence to facilitate factual responses. Such RAG (Retrieval Augmented Generation) systems retrieve from massive heterogeneous data stores that are usually architected as multiple indexes or APIs…

Transformer-based pre-trained language models such as BERT have achieved remarkable results in Semantic Sentence Matching. However, existing models still suffer from insufficient ability to capture subtle differences. Minor noise like word…

Emotion Recognition in Conversation (ERC) is a more challenging task than conventional text emotion recognition. It can be regarded as a personalized and interactive emotion recognition task, which is supposed to consider not only the…

Dynamic Facial Expression Recognition (DFER) facilitates the understanding of psychological intentions through non-verbal communication. Existing methods struggle to manage irrelevant information, such as background noise and redundant…

Without discourse connectives, classifying implicit discourse relations is a challenging task and a bottleneck for building a practical discourse parser. Previous research usually makes use of one kind of discourse framework such as PDTB or…

Depression is a serious mental illness that impacts the way people communicate, especially through their emotions, and, allegedly, the way they interact with others. This work examines depression signals in dialogs, a less studied setting…