Papers by Lingyu Li

7 papers
How does Attention Affect the Model? (2021.findings-acl)

Copied to clipboard

Challenge: Existing studies on the effectiveness of attention in NLP do not consider changes in semantic capability of different components.
Approach: They propose a framework that exploits a convex hull representation of sequence semantics in an n-dimensional Semantic Euclidean Space and defines indicators to capture the impact of attention on sequence semantic.
Outcome: The proposed framework exploits a convex hull representation of sequence semantics in an n-dimensional Semantic Euclidean Space and defines indicators to capture the impact of attention on sequence semantic.
MMAC: A Multilingual, Multimodal Alignment Framework for Cultural Grounding Evaluation (2026.acl-long)

Copied to clipboard

Challenge: Existing models lack cultural alignment across modalities and languages . a new framework to assess cultural awareness across linguistics and languages is needed .
Approach: They propose a framework that integrates tri-modally aligned cultural benchmarks and a five-dimensional evaluation protocol to assess cross-country awareness disparities.
Outcome: The proposed framework assesses cultural awareness disparities across modalities and languages . it is the first dataset aligned at the input level across text, image, and speech .
Keep Meeting Summaries on Topic: Abstractive Multi-Modal Meeting Summarization (P19-1)

Copied to clipboard

Challenge: Existing models for extractive summarization of meetings are unfocused and lack content coverage.
Approach: They propose a multi-modal hierarchical attention model that prioritizes segmentation and summarization . they propose to use multi-level hierarchies to narrow down the focus into topically-relevant segments .
Outcome: The proposed model outperforms the state-of-the-art with BLEU and ROUGE measures.
LET: Leveraging Error Type Information for Grammatical Error Correction (2023.findings-acl)

Copied to clipboard

Challenge: Existing methods for grammatical error correction (GEC) are mainly divided into detection-based and end-to-end generative models.
Approach: They propose an end-to-end framework which Leverages Error Type (LET) information in the generation process to introduce more convincing error type information.
Outcome: The proposed framework outperforms existing methods on various datasets by a clear margin.
ESC-Eval: Evaluating Emotion Support Conversations in Large Language Models (2024.emnlp-main)

Copied to clipboard

Challenge: Emotion Support Conversation (ESC) is a crucial application for reducing stress and providing emotional guidance.
Approach: They re-organize 2,801 role-playing cards to define roles of role-players . they train a specific role- playing model called ESC-Role which behaves more like a confused person than GPT-4 .
Outcome: The proposed model behaves more like a confused person than GPT-4, and the model performs better than GPLs.
Generating Attribution Reports for Manipulated Facial Images: A Dataset and Baseline (2026.acl-long)

Copied to clipboard

Challenge: Existing facial forgery detection methods focus on binary classification or pixel-level localization, providing little semantic insight into the nature of the manipulation.
Approach: They propose a multimodal task that localizes forged regions and generates natural language explanations grounded in editing process.
Outcome: The proposed task localizes forged regions and generates natural language explanations grounded in editing process.
Uni-Dubbing: Zero-Shot Speech Synthesis from Visual Articulation (2024.acl-long)

Copied to clipboard

Challenge: Multimodal speech synthesis is a key challenge due to the scarcity of datasets that pair audio with corresponding video.
Approach: They propose a method that incorporates modality alignment during the pre-training phase on multimodal datasets and freezes the video modality extraction component and the encoder module within the pretrained weights.
Outcome: The proposed method achieves a reduced word error rate (WER) of 31.73%, surpassing the previous best of 33.9% with single-modality audio.

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