Papers by Zhengkun Zhang

7 papers
Modeling Temporal-Modal Entity Graph for Procedural Multimodal Machine Comprehension (2022.acl-long)

Copied to clipboard

Challenge: Procedural Multimodal Documents organize textual instructions and corresponding images step by step.
Approach: They propose a novel temporal-modal entity Graph for comprehending PMDs . they propose encoding and reasoning modules to capture textual and visual entities .
Outcome: The proposed model can capture textual and visual entities and trace their temporal-modal evolution.
Licon: A Diverse, Controllable and Challenging Linguistic Concept Learning Benchmark (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for Concept Learning focus on visual information, but visual information cannot present abstract concepts exactly, which struggles the introduction of novel concepts related to known concepts.
Approach: They propose a benchmark where concepts in diverse forms are defined by linguistic descriptions and an entailment-based concept learning method to model the relationship among concepts.
Outcome: The proposed benchmark is based on the existing visual concepts learning benchmarks and will be released to the public soon.
Bypassing Neural Evaluations for Fast Audio Editing via Adaptive Trajectory Extrapolation (2026.findings-acl)

Copied to clipboard

Challenge: Recent advances in audio diffusion models have significantly improved text-to-audio editing via inversion techniques, but these models typically rely on dense, fixed-step sampling trajectories to maintain structural integrity.
Approach: They propose a model-agnostic Adaptive Trajectory Extrapolation framework that accelerates inversion-based editing process by dynamically evaluating only the most critical generative phases.
Outcome: The proposed framework achieves a 3.9 speedup with negligible loss in fidelity.
ACROSS: An Alignment-based Framework for Low-Resource Many-to-One Cross-Lingual Summarization (2023.findings-acl)

Copied to clipboard

Challenge: Existing studies ignore data imbalance in multilingual settings and do not utilize monolingual data.
Approach: They propose a cross-lingual summarization model that aligns cross-linguistic data with high-resource monolingual data via contrastive and consistency loss.
Outcome: The proposed model outperforms baseline models and consistently dominates on 45 language pairs.
Multi-Party Empathetic Dialogue Generation: A New Task for Dialog Systems (2022.acl-long)

Copied to clipboard

Challenge: Existing work on empathetic dialogues focused on the two-party scenario, but multi-party dialogues are pervasive in reality.
Approach: They propose a multi-party empathetic dialogue generation task that uses a static-dynamic model to explore emotion and sensibility.
Outcome: The proposed task is based on a model with static sensibility and dynamic emotion . it achieves state-of-the-art performance in multi-party empathetic dialogue learning .
HyperPELT: Unified Parameter-Efficient Language Model Tuning for Both Language and Vision-and-Language Tasks (2023.findings-acl)

Copied to clipboard

Challenge: Pretraining and fine-tuning are the dominant paradigms in natural language processing.
Approach: They propose a parameter-efficient multitask learning framework that takes trainable hyper-embeddings and visual modality as input and outputs weights for different modules in a pretrained language model.
Outcome: The proposed framework adds fewer trainable parameters in multi-task learning while achieving superior performances and transfer ability compared to state-of-the-art methods.
MelTrim: Coarse-to-Fine Data Pruning for Speech Classification (2026.findings-acl)

Copied to clipboard

Challenge: Unlike image or text classification, speech classification tasks are particularly challenging due to the difficulty in capturing the acoustic, semantic, and contextual representations.
Approach: They propose a dataset pruning method that coarsely filters redundant samples using DBSCAN clustering on Mel-Frequency Cepstral Coefficients (MFCC) features.
Outcome: The proposed method achieves 49.5% improvement in WA on the MEAD dataset and 41.9% reduction in EER on speaker identification tasks.

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