Papers by Kejun Zhang

6 papers
TeleMelody: Lyric-to-Melody Generation with a Template-Based Two-Stage Method (2022.emnlp-main)

Copied to clipboard

Challenge: a new lyric-to-melody generation system bridges the gap between lyrics and melodies . previous generation systems lack paired data and lack of control on generated melodie.
Approach: They develop a lyric-to-melody generation system with music template to bridge the gap between lyrics and melodies.
Outcome: The proposed system bridges the gap between lyrics and melodies by using music template.
Learning Language-guided Adaptive Hyper-modality Representation for Multimodal Sentiment Analysis (2023.emnlp-main)

Copied to clipboard

Challenge: Multimodal Sentiment Analysis (MSA) is effective when using rich information from multiple sources, but the potential sentiment-irrelevant information across modalities may hinder the performance from being further improved.
Approach: They propose an Adaptive Language-guided Multimodal Transformer (ALMT) that learns an irrelevance/conflict-suppressing representation from visual and audio features under guidance of language features at different scales.
Outcome: The proposed model achieves state-of-the-art on several popular datasets and an abundance of ablation shows the effectiveness of the proposed model.
Generative Music Models’ Alignment with Professional and Amateur Users’ Expectations (2025.findings-acl)

Copied to clipboard

Challenge: Recent years have witnessed rapid advances in text-to-music generation using large language models.
Approach: They propose a task to align AI-generated music with human expressions . they use a dataset of over 1.5 million songs to analyze their content .
Outcome: The proposed framework outperforms baseline models and facilitates end-to-end generation of songs audio.
Automatic Song Translation for Tonal Languages (2022.findings-acl)

Copied to clipboard

Challenge: Existing automatic song translation systems for tonal languages do not match the number of notes and beat the original rhythm of the song.
Approach: They propose three criteria for effective AST: preserving meaning, singability and intelligibility.
Outcome: The proposed system balances semantics and singability with human evaluations.
From Past To Path: Masked History Learning for Next-Item Prediction in Generative Recommendation (2026.acl-long)

Copied to clipboard

Challenge: Generative recommendation models inherently bias towards local contexts, failing to capture deeper historical dependencies necessary for understanding complex user intents.
Approach: They propose a training framework that shifts the objective from simple next-step prediction to deep comprehension of history by entropy-guided masking policy and a curriculum learning scheduler to enhance the framework.
Outcome: The proposed framework outperforms state-of-the-art generative models on three public datasets and shows that it is more accurate than current models.
CaDRL: Document-level Relation Extraction via Context-aware Differentiable Rule Learning (2025.coling-main)

Copied to clipboard

Challenge: Existing methods for document-level relation extraction (DocRE) lack logic and transparency.
Approach: They propose a Context-aware differentiable rule learning framework that learns the doc-specific logical rule to avoid suboptimal constraints.
Outcome: The proposed framework outperforms existing rule-based frameworks on three DocRE datasets.

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