Papers by Xiaomin Chu

8 papers
Building a Macro Chinese Discourse Treebank (L18-1)

Copied to clipboard

Challenge: Discourse structure analysis is an important research topic in natural language processing.
Approach: They propose to construct a macro discourse structure framework and annotate 147 Newswire articles.
Outcome: The proposed framework can lay the foundation for further analysis of macro discourse structure.
Automated Chinese Essay Scoring from Multiple Traits (2022.coling-1)

Copied to clipboard

Challenge: Current research on AES focuses on scoring the overall quality or single trait of prompt-specific essays.
Approach: They propose a hierarchical multi-task trait scorer to evaluate quality of writing . they propose an inter-sequence attention mechanism to enhance information interaction .
Outcome: The proposed model outperforms several strong models on ACEA and outperformed other models.
Chinese Paragraph-level Discourse Parsing with Global Backward and Local Reverse Reading (2020.coling-main)

Copied to clipboard

Challenge: Existing methods on discourse parsing in English suffer from long discourse units and fewer explicit connectives.
Approach: They propose to use two reading modes to construct Chinese paragraph level discourse trees.
Outcome: The proposed model outperforms baselines on Chinese discourse trees.
Factual Relation Discrimination for Factuality-oriented Abstractive Summarization (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing factuality-oriented abstractive summarization models only consider the integration of factual information and ignore the causes of factuual errors.
Approach: They propose a factuality-oriented abstractive summarization model that can identify the causes of factual errors.
Outcome: The proposed model outperforms state-of-the-art models in factual metrics.
MCDTB: A Macro-level Chinese Discourse TreeBank (C18-1)

Copied to clipboard

Challenge: Discourse analysis is becoming increasingly important in the field of natural language processing.
Approach: They propose to annotate macro discourse information and additional discourse information to make annotation more objective and accurate.
Outcome: The results show that the annotations are more objective and accurate than the previous ones.
Advancing Topic Segmentation and Outline Generation in Chinese Texts: The Paragraph-level Topic Representation, Corpus, and Benchmark (2024.lrec-main)

Copied to clipboard

Challenge: Compared with sentence-level topic structure, paragraph-level topics can grasp and understand the context of a document from a higher level.
Approach: They propose a hierarchical paragraph-level topic structure representation with three layers to guide corpus construction.
Outcome: The proposed method achieves the largest Chinese paragraph-level topic structure corpus, achieving high quality.
Joint Modeling of Structure Identification and Nuclearity Recognition in Macro Chinese Discourse Treebank (C18-1)

Copied to clipboard

Challenge: Discourse parsing is a challenging task and plays a critical role in discourse analysis.
Approach: They propose a macro discourse structure presentation schema to present the macro level discourse structure analysis.
Outcome: The proposed corpus is based on two tasks of macro discourse structure analysis, including structure identification and nuclearity recognition.
Not Just Classification: Recognizing Implicit Discourse Relation on Joint Modeling of Classification and Generation (2021.emnlp-main)

Copied to clipboard

Challenge: Existing methods of implicit discourse relation recognition (IDRR) focus on three aspects: enhancing discourse units representation, enhancing semantic interaction, and joint learning with other tasks.
Approach: They propose a joint model to recognize the relation label and generate the target sentence containing the meaning of relations simultaneously.
Outcome: The proposed model achieves the best performance against several state-of-the-art systems on Chinese and English datasets.

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