Papers by Xurui Zhang

4 papers
Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer (2021.emnlp-main)

Copied to clipboard

Challenge: Experimental results show that popular NLP models are vulnerable to both adversarial and backdoor attacks based on text style transfer.
Approach: They propose to conduct adversarial and backdoor attacks based on text style transfer . the authors propose to use text style to alter the style of a sentence .
Outcome: The proposed methods show that popular models are vulnerable to both attacks based on text style transfer . the results show that the proposed methods perform better than baselines in many aspects .
MERMAID: Metaphor Generation with Symbolism and Discriminative Decoding (2021.naacl-main)

Copied to clipboard

Challenge: a new method for generating metaphors is proposed to generate literal sentences . human evaluations show that our best model generates metaphors better than three well-crafted baselines 66% of the time on average.
Approach: They propose a method to automatically construct a parallel corpus by transforming literal sentences to metaphorical ones using commonsense inference and masked language modeling.
Outcome: The proposed method generates metaphors better than baselines 66% of the time on average.
Try to Substitute: An Unsupervised Chinese Word Sense Disambiguation Method Based on HowNet (2020.coling-main)

Copied to clipboard

Challenge: Existing unsupervised methods for word sense disambiguation cannot work for HowNet-based WSD because of its uniqueness.
Approach: They propose a method which exploits the masked language model task of pre-trained language models to conduct word sense disambiguation using a lexical knowledge base as the sense inventory.
Outcome: The proposed method achieves significantly better performance than baseline methods.
Knowledge Triplets Derivation from Scientific Publications via Dual-Graph Resonance (2024.lrec-main)

Copied to clipboard

Challenge: Existing relation extraction methods aim to extract explicit triplet knowledge from documents, but they can hardly perceive unobserved factual relations.
Approach: They propose a novel Extraction-Contextualization-Derivation strategy to generate a document-specific dynamic graph from a shared static knowledge graph.
Outcome: The proposed method can generate richer explicit and implicit relations under the guidance of static and dynamic knowledge topologies.

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