Papers by Ziran Li

4 papers
Integrating User History into Heterogeneous Graph for Dialogue Act Recognition (2020.coling-main)

Copied to clipboard

Challenge: Existing models cannot fully recognize the specific expressions given by users due to the informality and diversity of natural language expressions.
Approach: They propose a Heterogeneous User History graph convolution network which utilizes the user’s historical answers grouped by DA labels as additional clues to recognize the DA label of utterances.
Outcome: The proposed model outperforms the state-of-the-art methods on two benchmark datasets and shows that it integrates user’s historical answers.
Chinese Relation Extraction with Multi-Grained Information and External Linguistic Knowledge (P19-1)

Copied to clipboard

Challenge: Existing methods for Chinese relation extraction suffer from segmentation errors and ambiguity of polysemy.
Approach: They propose a multi-grained lattice framework for Chinese relation extraction . they incorporate word-level information into character sequence inputs to avoid segmentation errors .
Outcome: The proposed model outperforms existing models on three real-world datasets in distinct domains.
Event Detection with Trigger-Aware Lattice Neural Network (D19-1)

Copied to clipboard

Challenge: Event detection is a key part of event extraction, but there are two issues with word-based models in languages without natural delimiters, such as Chinese.
Approach: They propose a framework that can solve the problem of word- trigger mismatch . they also use an external knowledge base to model polysemous characters and words .
Outcome: The proposed model outperforms state-of-the-art methods on two benchmark datasets and outperformed previous state- of-the art methods significantly.
Fusion or Defusion? Flexible Vision-and-Language Pre-Training (2023.findings-acl)

Copied to clipboard

Challenge: Existing approaches to vision-and-language pretraining (VLP) lack effectiveness and efficiency in downstream multimodal tasks.
Approach: They propose a flexible vision-and-language pre-training model by incorporating cross-modal fusions into a dual-encoder architecture and a cross-module knowledge transfer strategy to guide the training process.
Outcome: The proposed model is well-equipped with effectiveness and efficiency compared with other strong VLP models.

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