Related papers: Contrast and Generation Make BART a Good Dialogue …

Dialogue systems play an increasingly important role in various aspects of our daily life. It is evident from recent research that dialogue systems trained on human conversation data are biased. In particular, they can produce responses…

Recently, generative adversarial networks have gained a lot of popularity for image generation tasks. However, such models are associated with complex learning mechanisms and demand very large relevant datasets. This work borrows concepts…

Cross-domain sentiment analysis aims to predict the sentiment of texts in the target domain using the model trained on the source domain to cope with the scarcity of labeled data. Previous studies are mostly cross-entropy-based methods for…

Lexically constrained text generation aims to control the generated text by incorporating some pre-specified keywords into the output. Previous work injects lexical constraints into the output by controlling the decoding process or refining…

Previous works on emotion recognition in conversation (ERC) follow a two-step paradigm, which can be summarized as first producing context-independent features via fine-tuning pretrained language models (PLMs) and then analyzing contextual…

Speech Emotion Recognition (SER) is fundamental to affective computing and human-computer interaction, yet existing models struggle to generalize across diverse acoustic conditions. While Contrastive Language-Audio Pretraining (CLAP)…

Empathetic dialog generation aims at generating coherent responses following previous dialog turns and, more importantly, showing a sense of caring and a desire to help. Existing models either rely on pre-defined emotion labels to guide the…

Despite strong recent progress in Emotion Recognition in Conversation (ERC), two gaps remain: we lack clear understanding of which modeling choices materially affect performance, and we have limited linguistic analysis linking recognition…

We propose some extensions to semi-parametric models based on Bayesian additive regression trees (BART). In the semi-parametric BART paradigm, the response variable is approximated by a linear predictor and a BART model, where the linear…

Each utterance in multi-turn empathetic dialogues has features such as emotion, keywords, and utterance-level meaning. Feature transitions between utterances occur naturally. However, existing approaches fail to perceive the transitions…

For the task of conversation emotion recognition, recent works focus on speaker relationship modeling but ignore the role of utterance's emotional tendency.In this paper, we propose a new expression paradigm of sentence-level emotion…

Retrieval-based conversational systems learn to rank response candidates for a given dialogue context by computing the similarity between their vector representations. However, training on a single textual form of the multi-turn context…

The majority of current systems for end-to-end dialog generation focus on response quality without an explicit control over the affective content of the responses. In this paper, we present an affect-driven dialog system, which generates…

We present a novel natural language generation system for spoken dialogue systems capable of entraining (adapting) to users' way of speaking, providing contextually appropriate responses. The generator is based on recurrent neural networks…

Multimodal emotion recognition in conversations aims to infer utterance-level emotions by jointly modeling textual, acoustic, and visual cues within context. Despite recent progress, key challenges remain, including redundant cross-modal…

Emotion recognition in conversation, which aims to predict the emotion for all utterances, has attracted considerable research attention in recent years. It is a challenging task since the recognition of the emotion in one utterance…

Emotion recognition plays a crucial role in various domains of human-robot interaction. In long-term interactions with humans, robots need to respond continuously and accurately, however, the mainstream emotion recognition methods mostly…

While pre-trained language models excel at semantic understanding, they often struggle to capture nuanced affective information critical for affective recognition tasks. To address these limitations, we propose a novel framework for…

Messages in human conversations inherently convey emotions. The task of detecting emotions in textual conversations leads to a wide range of applications such as opinion mining in social networks. However, enabling machines to analyze…

Existing work on probing of pretrained language models (LMs) has predominantly focused on sentence-level syntactic tasks. In this paper, we introduce document-level discourse probing to evaluate the ability of pretrained LMs to capture…