activity
20222024
most citedFew-shot Named Entity Recognition with Entity-level Prototypical Network Enhanced by Dispersedly Distributed Prototypes

16 citations · 18 across the 10 of their papers we have counts for

collaborators

10 papers

cs.CL2024

PTA: Enhancing Multimodal Sentiment Analysis through Pipelined Prediction and Translation-based Alignment

Shezheng Song, Shasha Li, Shan Zhao +8

Multimodal aspect-based sentiment analysis (MABSA) aims to understand opinions in a granular manner, advancing human-computer interaction and other fields. Traditionally, MABSA met…

cs.AI2024

Disentangling Instructive Information from Ranked Multiple Candidates for Multi-Document Scientific Summarization

Pancheng Wang, Shasha Li, Dong Li +3

Automatically condensing multiple topic-related scientific papers into a succinct and concise summary is referred to as Multi-Document Scientific Summarization (MDSS). Currently, w…

cs.AI2024

DWE+: Dual-Way Matching Enhanced Framework for Multimodal Entity Linking

Shezheng Song, Shasha Li, Shan Zhao +7

Multimodal entity linking (MEL) aims to utilize multimodal information (usually textual and visual information) to link ambiguous mentions to unambiguous entities in knowledge base…

cs.CL2023

Dynamic Multi-View Fusion Mechanism For Chinese Relation Extraction

Jing Yang, Bin Ji, Shasha Li +3

Recently, many studies incorporate external knowledge into character-level feature based models to improve the performance of Chinese relation extraction. However, these methods te…

cs.CL2022

A Two-Phase Paradigm for Joint Entity-Relation Extraction

Bin Ji, Hao Xu, Jie Yu +4

An exhaustive study has been conducted to investigate span-based models for the joint entity and relation extraction task. However, these models sample a large number of negative e…

cs.CL20221 cited

A Context-Aware Approach for Textual Adversarial Attack through Probability Difference Guided Beam Search

Huijun Liu, Jie Yu, Shasha Li +2

Textual adversarial attacks expose the vulnerabilities of text classifiers and can be used to improve their robustness. Existing context-aware methods solely consider the gold labe…