Papers by Tiejun Liu

10 papers
Cross Copy Network for Dialogue Generation (2020.emnlp-main)

Copied to clipboard

Challenge: Despite the success of sequence-to-sequence models, dialogue logics are often ignored.
Approach: They propose a network architecture to explore the current dialog context and similar dialogue instances’ logical structure simultaneously.
Outcome: The proposed network architecture is superior to existing state-of-the-art models.
Make Imagination Clearer! Stable Diffusion-based Visual Imagination for Multimodal Machine Translation (2025.acl-long)

Copied to clipboard

Challenge: Experimental results show that our model significantly outperforms existing multimodal MT and text-only MT.
Approach: They propose a stable diffusion-based imagination network into a multimodal large language model to generate an image for each source sentence.
Outcome: The proposed model outperforms existing multimodal and text-only MT and achieves an average improvement of 14 BLEU points on Multi30K and MSCOCO multimodal MT benchmarks.
A Chain-of-Task Framework for Instruction Tuning of LLMs Based on Chinese Grammatical Error Correction (2025.coling-main)

Copied to clipboard

Challenge: Existing approaches to address Grammatical Error Correction (GEC) tasks are based on large scale labeled data, which leads to extremely high data annotation costs.
Approach: They propose a Chain-of-Task framework to reduce over-correction in large language models . they propose supervised fine-tuning strategy and an algorithm for automatic dataset annotation .
Outcome: The proposed framework achieves state-of-the-art on both FCGEC (in-domain) and NaCGEC (out-of domain) test sets.
An Empirical Study of LLM-as-a-Judge for LLM Evaluation: Fine-tuned Judge Model is not a General Substitute for GPT-4 (2025.findings-acl)

Copied to clipboard

Challenge: Recent studies have fine-tuned judge models based on open-source LLMs to evaluate the quality of other LLM.
Approach: They propose to use open-source LLMs to evaluate Large Language Models (LLMs) their empirical results show that the models underperform GPT-4 in several dimensions .
Outcome: The proposed models outperform GPT-4 on several dimensions including generalizability, fairness and adaptability.
Learning to Decouple Relations: Few-Shot Relation Classification with Entity-Guided Attention and Confusion-Aware Training (2020.coling-main)

Copied to clipboard

Challenge: Existing few-shot relation classifiers struggle to distinguish them with few annotated instances due to high co-occurrence of some relations .
Approach: They propose a few-shot relation classification model with two mechanisms to decouple easily-confused relations.
Outcome: The proposed model achieves comparable and even better results to strong baselines in terms of accuracy.
Landmark-Guided Cross-Speaker Lip Reading with Mutual Information Regularization (2024.lrec-main)

Copied to clipboard

Challenge: Lip reading is a process of interpreting silent speech from visual lip movements . but lip reading in cross-speaker scenarios poses a challenging problem due to inter-speech variability .
Approach: They propose to exploit lip landmark-guided visual clues instead of mouth-cropped images as input features.
Outcome: Experimental results show that the proposed approach reduces speaker-specific appearance characteristics in cross-speaker scenarios.
MuSC: Improving Complex Instruction Following with Multi-granularity Self-Contrastive Training (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for complex instruction-following with elaborate constraints rely on a weaker model, especially GPT-4, limiting their application.
Approach: They propose a Multi-granularity Self-Contrastive Training framework to improve instruction alignment without relying on a stronger model.
Outcome: The proposed framework improves instruction-following with elaborate constraints without external supervision on coarse and fine granularity.
Understanding and Improving Hidden Representations for Neural Machine Translation (N19-1)

Copied to clipboard

Challenge: Existing studies have explored some methods for understanding hidden representations, but they have not sought to improve the translation quality rationally according to their understanding.
Approach: They propose to construct a sequence of nested relative tasks and measure the feature generalization ability of the learned hidden representation over these tasks.
Outcome: The proposed methods achieve consistent improvements (up to +1.3 BLEU) on two widely-used datasets.
Self-Evaluation of Large Language Model based on Glass-box Features (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing evaluation methods rely on external evaluators, focusing on training and prompting strategies, but model-aware glass-box features are overlooked.
Approach: They propose to use model-aware glass-box features to evaluate an LLM's output.
Outcome: The proposed model-aware features are reliable quality indicators for self-evaluation on public benchmarks.
Understanding Data Augmentation in Neural Machine Translation: Two Perspectives towards Generalization (D19-1)

Copied to clipboard

Challenge: Existing studies measure the superiority of DA methods in terms of their performance on a specific test set, but some do not exhibit consistent improvements across translation tasks.
Approach: They propose to evaluate DA methods from two perspectives to determine their generalization ability . they find that DA method's test performance does not exhibit consistent improvements across translation tasks .
Outcome: The proposed methods do not exhibit consistent improvements across translation 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