Search Results for author:
Found 12 papers, 9 papers with code
CoMPM: Context Modeling with Speaker’s Pre-trained Memory Tracking for Emotion Recognition in Conversation
We introduce CoMPM, which combines the speaker’s pre-trained memory with the context model, and find that the pre-trained memory significantly improves the performance of the context model.
Enhanced Facet Generation with LLM Editing
The second strategy is to enhance the facets by combining Large Language Model (LLM) and the small model.
P5: Plug-and-Play Persona Prompting for Personalized Response Selection
Our system can function as a standard open-domain chatbot if persona information is not available.
PK-ICR: Persona-Knowledge Interactive Context Retrieval for Grounded Dialogue
Identifying relevant persona or knowledge for conversational systems is critical to grounded dialogue response generation.
The Emotion is Not One-hot Encoding: Learning with Grayscale Label for Emotion Recognition in Conversation
That is, instead of using a given label as a one-hot encoding, we construct a grayscale label by measuring scores for different emotions.
Ranked #4 on
Emotion Recognition in Conversation
on DailyDialog
Multimodal Interactions Using Pretrained Unimodal Models for SIMMC 2.0
This paper presents our work on the Situated Interactive MultiModal Conversations 2. 0 challenge held at Dialog State Tracking Challenge 10.
An Evaluation Dataset and Strategy for Building Robust Multi-turn Response Selection Model
Multi-turn response selection models have recently shown comparable performance to humans in several benchmark datasets.
CoMPM: Context Modeling with Speaker's Pre-trained Memory Tracking for Emotion Recognition in Conversation
We introduce CoMPM, which combines the speaker's pre-trained memory with the context model, and find that the pre-trained memory significantly improves the performance of the context model.
Ranked #5 on
Emotion Recognition in Conversation
on DailyDialog
Paraphrasing via Ranking Many Candidates
We present a simple and effective way to generate a variety of paraphrases and find a good quality paraphrase among them.
Transforming Multi-Conditioned Generation from Meaning Representation
Our study focuses on language generation by considering various information representing the meaning of utterances as multiple conditions of generation.
AD-VO: Scale-Resilient Visual Odometry Using Attentive Disparity Map
Visual odometry is an essential key for a localization module in SLAM systems.
