Papers by Zhixing Li

7 papers
Towards Linear Time Neural Machine Translation with Capsule Networks (D19-1)

Copied to clipboard

Challenge: Neural Machine Translation (NMT) is an endto-end learning approach to machine translation.
Approach: They propose a capsule network with dynamic routing for linear time Neural Machine Translation . they map the source sentence into a matrix with pre-determined size and apply a deep LSTM network to decode the target sequence from the source representation.
Outcome: The proposed network achieves comparable results with the Transformer system on English-German and English-French tasks.
Re-TASK: Revisiting LLM Tasks from Capability, Skill, and Knowledge Perspectives (2025.findings-acl)

Copied to clipboard

Challenge: Existing approaches to solving complex tasks with large language models (LLMs) fail to decompose tasks accurately or execute subtasks effectively.
Approach: They propose a Chain-of-Learning (CoL) paradigm that highlights task dependencies on specific capability items, further broken down into their constituent knowledge and skill components.
Outcome: The proposed model improves Yi-1.5-9B and Llama3-Chinese-8B for legal tasks by 45.00% and 24.50% on different domains.
CL2GEC: A Multi-Discipline Benchmark for Continual Learning in Chinese Literature Grammatical Error Correction (2026.acl-long)

Copied to clipboard

Challenge: Existing CGEC benchmarks for multi-disciplinary writing are limited . continual learning (CL) is a promising solution to handle domain-specific linguistic variation and prevent catastrophic forgetting.
Approach: They propose a Chinese Literature Continual Learning benchmark to evaluate adaptive CGEC across disciplines.
Outcome: The proposed benchmark includes 10,000 human-annotated sentences spanning 10 disciplines, each exhibiting distinct linguistic styles and error patterns.
Enhancing Multiple-choice Machine Reading Comprehension by Punishing Illogical Interpretations (2021.emnlp-main)

Copied to clipboard

Challenge: Multiple-choice MRC is one of the most studied tasks in MRC due to the convenience of evaluation and the flexibility of answer format.
Approach: They propose to use multiple-choice MRC to explain a trained model and reveal how it arrives at the prediction by punishing illogical attributions.
Outcome: The proposed method improves model performance without external information and model structure change without any external information.
Align-smatch: A Novel Evaluation Method for Chinese Abstract Meaning Representation Parsing based on Alignment of Concept and Relation (2022.lrec-1)

Copied to clipboard

Challenge: Abstract Meaning Representation abstracts the meaning of sentences into a single-rooted, acyclic and directed graph.
Approach: They propose to use a metric to evaluate concept alignment and relation alignment to improve Chinese AMR parsing evaluation methods.
Outcome: The proposed method is more robust and compatible with concept alignment and relation alignment and more robust in evaluating arcs.
LLM×MapReduce: Simplified Long-Sequence Processing using Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: Existing studies have focused on extending the context length of large language models (LLMs) due to their quadratic computational complexity and a lack of high-quality long training examples, most LLMs are trained with a limited window size.
Approach: They propose a training-free framework that enables large language models to effectively process long texts using a divide-and-conquer strategy for comprehensive document understanding.
Outcome: The proposed framework outperforms open-source and commercial long-context LLMs and is compatible with several models.
A Template-based Method for Constrained Neural Machine Translation (2022.emnlp-main)

Copied to clipboard

Challenge: Existing methods to solve this problem can not satisfy the following three desiderata: (1) high translation quality, (2) high match accuracy, and (3) low latency.
Approach: They propose a template-based method that can provide high translation quality and match accuracy and a low latency inference.
Outcome: The proposed method outperforms baselines in lexically and structurally constrained translation tasks and can be used in a variety of applications.

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