Search Results for author:
Found 8 papers, 4 papers with code
ConText at WASSA 2024 Empathy and Personality Shared Task: History-Dependent Embedding Utterance Representations for Empathy and Emotion Prediction in Conversations
In our submissions, we model empathy, emotion polarity and emotion intensity of each utterance in a conversation by feeding the utterance to be classified together with its conversational context, i. e., a certain number of previous conversational turns, as input to an encoder Pre-trained Language Model, to which we append a regression head for prediction.
Dialogue Quality and Emotion Annotations for Customer Support Conversations
Task-oriented conversational datasets often lack topic variability and linguistic diversity.
Fuzzy Fingerprinting Transformer Language-Models for Emotion Recognition in Conversations
Fuzzy Fingerprints have been successfully used as an interpretable text classification technique, but, like most other techniques, have been largely surpassed in performance by Large Pre-trained Language Models, such as BERT or RoBERTa.
Simple LLM Prompting is State-of-the-Art for Robust and Multilingual Dialogue Evaluation
Despite significant research effort in the development of automatic dialogue evaluation metrics, little thought is given to evaluating dialogues other than in English.
Context-Dependent Embedding Utterance Representations for Emotion Recognition in Conversations
The usual approach to model the conversational context has been to produce context-independent representations of each utterance and subsequently perform contextual modeling of these.
Ranked #1 on
Emotion Recognition in Conversation
on EmoWoz
(Macro F1 metric)
Deep Emotion Recognition in Textual Conversations: A Survey
This is followed by descriptions of the most prominent works in ERC with explanations of the Deep Learning architectures employed.
Towards a Sentiment-Aware Conversational Agent
In this paper, we propose an end-to-end sentiment-aware conversational agent based on two models: a reply sentiment prediction model, which leverages the context of the dialogue to predict an appropriate sentiment for the agent to express in its reply; and a text generation model, which is conditioned on the predicted sentiment and the context of the dialogue, to produce a reply that is both context and sentiment appropriate.
Retrieval Augmentation for Deep Neural Networks
Despite the use of large training datasets, most models are trained by iterating over single input-output pairs, discarding the remaining examples for the current prediction.
