Papers by Carla Viegas

2 papers
Entheos: A Multimodal Dataset for Studying Enthusiasm (2021.findings-acl)

Copied to clipboard

Challenge: Enthusiasm is an important part of engaging communication.
Approach: They propose a multimodal dataset for studying enthusiasm composed of video, audio, and text.
Outcome: The proposed model shows that pitch, loudness, and discourse relation parsing are important in distinguishing enthusiastic communication.
Including Facial Expressions in Contextual Embeddings for Sign Language Generation (2023.starsem-1)

Copied to clipboard

Challenge: State-of-the-art sign language generation frameworks lack expressivity and naturalness . current systems focus on manual signs, neglecting affective, grammatical and semantic functions of facial expressions . communication between the Deaf and Hard of Hearing (DHH) individuals may be facilitated by emerging language technologies .
Approach: They propose a Dual Encoder Transformer capable of generating manual signs and facial expressions by capturing similarities and differences found in text and sign gloss annotations.
Outcome: The proposed model improves the quality of automatically generated sign language.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations