Papers by Chun Zhou

4 papers
Aerial Vision-and-Dialog Navigation (2023.findings-acl)

Copied to clipboard

Challenge: Aerial visionand-dialling navigation (AVDN) is a new approach to autonomous drones that can converse with humans and follow natural language commands to complete tasks.
Approach: They propose to use Aerial Visionand-Dialog Navigation (AVDN) to navigate a drone via natural language conversation by collecting a dataset of over 3k recorded navigation trajectories with asynchronous human-human dialogs between commanders and followers.
Outcome: The proposed system can converse with humans and follow natural language commands to fly to the expected destination.
COAS2W: A Chinese Older-Adults Spoken-to-Written Transformation Corpus with Context Awareness (2025.emnlp-main)

Copied to clipboard

Challenge: Existing work on spoken-to-written transformations from older adults' language is limited by omission, disordered syntax, constituent errors, and redundancy.
Approach: They propose to combine a spoken-to-written corpus of 10,004 utterances from older adults with a written version, fine-grained error labels, and four-sentence context.
Outcome: The proposed model outperforms closed-source models on Chinese spoken-to-written corpus and shows that multi-sentence input is more efficient.
Probabilistic Graph Reasoning for Natural Proof Generation (2021.findings-acl)

Copied to clipboard

Challenge: Existing approaches to reasoning over formal representations do not explicitly consider inter-dependency between answers and proofs.
Approach: They propose a novel approach for joint answer prediction and proof generation using an induced graphical model.
Outcome: The proposed approach achieves 10%-30% improvement on QA accuracy in evaluations under diverse conditions.
Vocabulary Learning via Optimal Transport for Neural Machine Translation (2021.acl-long)

Copied to clipboard

Challenge: Empirical results show that VOLT beats widely-used vocabularies in diverse scenarios, including WMT-14 English-German translation, TED bilingual translation, and TED multilingual translation.
Approach: They propose a token dictionary solution that can be used without trial training to find the best dictionary with a proper size.
Outcome: The proposed solution beats widely-used vocabularies in English-German translation, TED bilingual translation, and TED multilingual translation.

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