Papers by Shuang Zeng

11 papers
SIRE: Separate Intra- and Inter-sentential Reasoning for Document-level Relation Extraction (2021.findings-acl)

Copied to clipboard

Challenge: Document-level relation extraction (doc-level RE) is a classification problem that predicts relations for all entity pairs in a document.
Approach: They propose a document-level relation extraction architecture to represent intra- and inter-sentential relations in different ways.
Outcome: The proposed architecture outperforms the state-of-the-art methods on the public datasets.
Double Graph Based Reasoning for Document-level Relation Extraction (2020.emnlp-main)

Copied to clipboard

Challenge: Existing methods for document-level relation extraction fail to recognize relations between entities across sentences.
Approach: They propose a method to recognize relations for long paragraphs by a Graph Aggregation-and-Inference Network (GAIN) they propose to use a heterogeneous mention-level graph and an entity-level EG graph to analyze the relationships.
Outcome: The proposed method achieves a significant performance improvement (2.85 on F1) over the previous state-of-the-art.
Evaluating Text Coherence at Sentence and Paragraph Levels (2020.lrec-1)

Copied to clipboard

Challenge: Existing text ordering models have been used to test coherence in NLP for a long time.
Approach: They propose to perform paragraph ordering task and sentence ordering by using four corpora from different domains.
Outcome: The proposed model performs better under certain extreme conditions than the most prevalent metric used before.
Mining Clues from Incomplete Utterance: A Query-enhanced Network for Incomplete Utterance Rewriting (2022.naacl-main)

Copied to clipboard

Challenge: Existing studies do not consider semantic information between incomplete utterance and rewritten utterant or model the semantic structure implicitly and insufficiently.
Approach: They propose a query-Enhanced network to bring semantic structural knowledge between incomplete utterance and rewritten utteras . they adopt a fast and effective edit operation scoring network to model the relation between two tokens based on extra information and the well-designed network .
Outcome: The proposed query template explicitly brings semantic structural knowledge between the incomplete utterance and the rewritten utterant making model perceive where to refer back to or recover omitted tokens.
SCL-RAI: Span-based Contrastive Learning with Retrieval Augmented Inference for Unlabeled Entity Problem in NER (2022.coling-1)

Copied to clipboard

Challenge: Existing methods to solve Unlabeled Entity Problem (UEP) in Named Entities Recognition datasets are not effective in real-world datasets.
Approach: They propose to decrease the distance of span representations with the same label while increasing it for different ones via span-based contrastive learning.
Outcome: The proposed method outperforms the previous method on two real-world datasets.
Type-enriched Hierarchical Contrastive Strategy for Fine-Grained Entity Typing (2022.coling-1)

Copied to clipboard

Challenge: Experimental results show that fine-grained entity typing (FET) can be used to deduce specific semantic types of entities.
Approach: They propose a type-enriched hierarchical contrastive strategy to model type differences . their method can make type information directly perceptible and improve distinguishability .
Outcome: The proposed method can model the differences between hierarchical types and distinguish multi-grained similar types at different granularities.
A Two-Stream AMR-enhanced Model for Document-level Event Argument Extraction (2022.naacl-main)

Copied to clipboard

Challenge: Existing studies aim at extracting event arguments from a single sentence . document-level event extraction still remains under-explored .
Approach: They propose a two-stream abstract meaning representation enhanced extraction model to extract event arguments from an entire document.
Outcome: The proposed model outperforms state-of-the-art in extracting event arguments from documents by 2.54 F1 and 5.13 F1 on public RAMS and WikiEvents datasets.
SANTA: Separate Strategies for Inaccurate and Incomplete Annotation Noise in Distantly-Supervised Named Entity Recognition (2023.findings-acl)

Copied to clipboard

Challenge: Distantly-Supervised Named Entity Recognition (DS-NER) is widely used in the supervised setting, but the context-free matching process and the limited coverage of knowledge bases introduce inaccurate and incomplete annotation noise respectively.
Approach: They propose to handle two types of noise separately with Memory-smoothed Focal Loss and Entity-aware KNN to relieve the entity ambiguity problem caused by inaccurate annotation and a noise-tolerant loss to improve the model’s robustness.
Outcome: The proposed model achieves a new state-of-the-art on five public datasets.
DISK: Domain-constrained Instance Sketch for Math Word Problem Generation (2022.coling-1)

Copied to clipboard

Challenge: Existing methods for generating MWP text from equations are inflexible and require pre-defined templates.
Approach: They propose a neural model which generates MWPs from equations by constructing a Quantity Cell Graph from the retrieved MWp instance and reasoning over it.
Outcome: The proposed model performs impressively on educational MWP set and on human evaluation metrics.
Improving the Robustness of Distantly-Supervised Named Entity Recognition via Uncertainty-Aware Teacher Learning and Student-Student Collaborative Learning (2024.findings-acl)

Copied to clipboard

Challenge: Named Entity Recognition (NER) methods require a substantial quantity of high-quality annotation for training models.
Approach: They propose a method to reduce the number of incorrect pseudo labels in self-training . they propose 'uncertainty-aware teacher learning' and 'student-student collaboration'
Outcome: The proposed method is superior to state-of-the-art DS-NER denoising methods.
MetaBench: A Multi-task Benchmark for Assessing LLMs in Metabolomics (2026.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) have demonstrated remarkable capabilities on general text, but their proficiency in specialized scientific domains remains uncharacterized.
Approach: They evaluate the capabilities of large language models in metabolomics research using MetaBench . they found that models perform well on text generation tasks, but cross-database identifier grounding remains challenging .
Outcome: The evaluation of 25 open- and closed-source LLMs reveals distinct performance patterns across metabolomics tasks.

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