Papers by Xi Xiangyu

8 papers
Capturing Event Argument Interaction via A Bi-Directional Entity-Level Recurrent Decoder (2021.acl-long)

Copied to clipboard

Challenge: Existing efforts to capture event argument interactions are limited by the argument role type information of contextual entities.
Approach: They propose to capture event argument interactions as a Seq2Seq-like learning problem where a sentence with a specific event trigger is mapped to a sequence of event argument roles.
Outcome: The proposed neural architecture generates argument roles by incorporating contextual entities’ argument role predictions, like a word-by-word text generation process, thereby distinguishing implicit argument distribution patterns within an event more accurately.
DESED: Dialogue-based Explanation for Sentence-level Event Detection (2022.coling-1)

Copied to clipboard

Challenge: Existing methods for sentence-level event detection depend on manual annotations or domain expertise to design sophisticated templates and rules.
Approach: They propose a dialogue-based explanation paradigm to enhance sentence semantics for event detection.
Outcome: The proposed method can be applied to two event detection datasets.
Improving Embedding-based Large-scale Retrieval via Label Enhancement (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for large-scale retrieval are trained with 0-1 hard labels that indicate whether a query is relevant to a document, ignoring rich information of the relevance degree.
Approach: They propose to introduce label enhancement for the first time to characterize query-document relevance degree by embedding label distribution into contextual embeddables.
Outcome: The proposed method significantly outperforms existing retrieval models and its counterparts equipped with two alternative methods on English and Chinese large-scale retrieval tasks.
Graph Enhanced Dual Attention Network for Document-Level Relation Extraction (2020.coling-main)

Copied to clipboard

Challenge: Document-level relation extraction requires inter-sentence reasoning capabilities to capture local and global contextual information for multiple relation facts.
Approach: They propose to characterize the interaction between sentences and potential relation instances via a Graph Enhanced Dual Attention network (GEDA) . they also propose a simple yet effective regularizer based on the natural duality of the S2R and R2S attentions, whose weights are also supervised by the supporting evidence of relation instances during training.
Outcome: The proposed model achieves competitive performance on an existing large-scale dataset while the predictions can be interpretable and easily observed.
Enhancing Efficiency and Exploration in Reinforcement Learning for LLMs (2025.emnlp-main)

Copied to clipboard

Challenge: Existing approaches allocate an equal number of rollouts to all questions during the RL process, which is inefficient.
Approach: They propose a mechanism for dynamically allocating rollout budgets based on the difficulty of the problems, enabling more efficient RL training.
Outcome: The proposed model improves response precision while preserving exploratory ability to uncover potential correct pathways.
Label Smoothing for Text Mining (2022.coling-1)

Copied to clipboard

Challenge: Existing text mining models are trained with 0-1 hard label that indicates whether an instance belongs to a class, ignoring rich information of the relevance degree.
Approach: They propose a keyword-based method to automatically generate soft labels from hard labels . they exploit relevance between labels and instances to incorporate them into models .
Outcome: The proposed method improves models under balanced and unbalanced conditions.
MUSIED: A Benchmark for Event Detection from Multi-Source Heterogeneous Informal Texts (2022.emnlp-main)

Copied to clipboard

Challenge: Recent efforts to classify unstructured texts into specific types have been limited in practical scenarios.
Approach: They propose to use Chinese text conversations and phone conversations to expand event detection to the scenarios involving informal and heterogeneous texts.
Outcome: The proposed dataset is based on user reviews, text conversations, and phone conversations in a leading e-commerce platform for food service.
SampleMix: A Sample-wise Pre-training Data Mixing Strategy by Coordinating Data Quality and Diversity (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for pretraining data mixing for large language models neglect significant inter-domain overlaps and commonalities, failing to control the global diversity of the constructed training dataset.
Approach: They propose a sample-wise data mixture approach that performs global cross-domain sampling by systematically evaluating the quality and diversity of each sample.
Outcome: The proposed method exceeds existing domain-based methods in multiple downstream tasks and perplexity assessments.

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