Papers by Zhengtao Liu

11 papers
Leveraging Unit Language Guidance to Advance Speech Modeling in Textless Speech-to-Speech Translation (2025.findings-acl)

Copied to clipboard

Challenge: Existing textless speech-to-speech translation models have two main challenges: 1) learning cross-modal features and 2) learning alignment of difference languages in long sequences.
Approach: They propose a unit language to overcome two main modeling challenges . they propose task prompt modeling to utilize the unit language in guiding the modeling process.
Outcome: The proposed language improves over a strong baseline and achieves comparable performance to models trained with text.
SiMFy: A Simple Yet Effective Approach for Temporal Knowledge Graph Reasoning (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing models for temporal knowledge graph reasoning suffer from low training efficiency and insufficient generalization ability.
Approach: They propose a temporal knowledge graph reasoning approach that uses multilayer perceptron to model the structural dependencies of events and adopts a fixed-frequency strategy to incorporate historical frequency during inference.
Outcome: The proposed model achieves state-of-the-art performance with faster convergence speed and better generalization ability.
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.
On the Emotion Understanding of Synthesized Speech (2026.acl-long)

Copied to clipboard

Challenge: Existing models for emotion understanding do not capture fundamental features of synthesized speech.
Approach: They evaluate emotion recognition models on synthesized speech using SER models and generative models.
Outcome: The proposed model can't generalize to synthesized speech because of speech token prediction . generative models tend to infer emotion from textual semantics while ignoring paralinguistic cues.
Memory-enhanced Large Language Model for Cross-lingual Dependency Parsing via Deep Hierarchical Syntax Understanding (2025.findings-emnlp)

Copied to clipboard

Challenge: Experimental results show that our approach can significantly improve the parsing accuracy of all baseline models, leading to new state-of-the-art results.
Approach: They propose a deep hierarchical syntax understanding approach to improve the cross-lingual semantic memory capability of large language models by implicitly aligning linguistic knowledge between source and target languages.
Outcome: The proposed approach improves the cross-lingual semantic memory capability of large language models by combining implicit multi-task fine-tuning and explicit label bank guiding.
Decoupling Mixture-of-Graphs: Unseen Relational Learning for Knowledge Graph Completion by Fusing Ontology and Textual Experts (2022.coling-1)

Copied to clipboard

Challenge: Existing methods for knowledge Graph Completion (KGC) fail in unseen relation representations.
Approach: They propose to use three kinds of graphs to obtain unseen relation representations . they propose to decouple mixture-of-graph experts (DMoG) for unseened relations learning .
Outcome: The proposed method outperforms the state-of-the-art methods on unseen relation representations.
Does Large Language Model Contain Task-Specific Neurons? (2024.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) have demonstrated remarkable capabilities in comprehensively handling various types of natural language processing (NLP) tasks.
Approach: They propose a method for task-specific neuron localization based on Causal Gradient Variation with Special Tokens (CGVST) this method identifies task- specific neurons by concentrating on the most significant tokens during task processing, eliminating redundant tokens and minimizing interference from non-essential neurons.
Outcome: The proposed method can locate task-specific neurons across eight public tasks.
SPS: Steering Probability Squeezing for Better Exploration in Reinforcement Learning for Large Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Reinforcement learning (RL) training typically improves single-sample success rates but limited exploration of diverse reasoning trajectories.
Approach: They propose a training paradigm that interleaves conventional RL with inverse reinforcement learning (IRL) they propose 'Steering Probability Squeezing' to enhance exploration without external supervision .
Outcome: The proposed training paradigm improves Pass@k and improves exploration of diverse reasoning trajectories without external supervision.
Multilingual Knowledge Graph Completion from Pretrained Language Models with Knowledge Constraints (2023.findings-acl)

Copied to clipboard

Challenge: Existing methods for multilingual knowledge graph completion do not align with mKGC tasks because of their English-centric bias.
Approach: They propose to use multilingual pretrained language models to solve queries in different languages by reasoning a tail entity.
Outcome: The proposed method outperforms the previous SOTA on Hits@1 and Hits @10 by 12.32% and 16.03% on public datasets.
Representation Alignment and Adversarial Networks for Cross-lingual Dependency Parsing (2024.findings-emnlp)

Copied to clipboard

Challenge: Pre-trained language models have improved dependency parsing accuracy in resource-rich languages . however, the accuracy drops sharply when the model is transferred to low-resource language .
Approach: They propose a representation alignment and adversarial model to filter out useful knowledge from rich-resource language and ignore useless ones.
Outcome: The proposed model outperforms baseline models on the benchmark datasets by 1.37 LAS and 1.34 UAS.
Multilingual Knowledge Graph Completion via Efficient Multilingual Knowledge Sharing (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing MKGC research ignores the shareability of cross-lingual knowledge.
Approach: They propose a multilingual knowledge Graph Completion framework that leverages multilingual shared knowledge to significantly enhance performance through two components: Knowledge-level Grouped Mixture of Experts (KL-GMoE) and Iterative Entity Reranking (IER).
Outcome: The proposed framework achieves improvements of 5.47%, 3.27%, and 1.01% in the Hits@1, Hits @3, and Hits_10 metrics, respectively, compared with existing state-of-the-art (SOTA) MKGC method.

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