Papers by Zhenxi Lin

14 papers
Hierarchy-aware Label Semantics Matching Network for Hierarchical Text Classification (2021.acl-long)

Copied to clipboard

Challenge: Existing methods ignore the semantic relationship between text and labels, so they cannot make full use of hierarchical information.
Approach: They propose a hierarchy-aware label semantics matching network to model the semantic relationship between text and labels in a semantic matching problem.
Outcome: The proposed model captures the text-label semantics matching relationship among coarse-grained labels and fine-grain labels in a hierarchy-aware manner.
Mitigating Hallucinations of Large Language Models in Medical Information Extraction via Contrastive Decoding (2024.findings-emnlp)

Copied to clipboard

Challenge: Medical Information Extraction (MIE) tasks are a fundamental component of medical NLP.
Approach: They propose an alternative adaptive constraint strategy to adjust the scale and scope of contrastive tokens.
Outcome: The proposed approach selectively enhances the identification and classification capabilities while minimizing the influence of other inherent abilities in LLMs.
OntoEA: Ontology-guided Entity Alignment via Joint Knowledge Graph Embedding (2021.findings-acl)

Copied to clipboard

Challenge: Existing methods for aligning knowledge graph entities ignore the ontology which contains critical meta information such as classes and membership relationships with entities.
Approach: They propose an ontology-guided method where KGs and ontologies are jointly embedded.
Outcome: Extensive experiments on seven public and industrial benchmarks show the ontology-guided method performs well and is cost-effective.
AdapTime: Enabling Adaptive Temporal Reasoning in Large Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods for temporal reasoning are limited and apply a fixed pipeline to all questions.
Approach: They propose an adaptive temporal reasoning method that dynamically executes reasoning steps based on context and task requirements.
Outcome: Experiments on two temporal QA benchmarks show the proposed method works.
CATE: A Contrastive Pre-trained Model for Metaphor Detection with Semi-supervised Learning (2021.emnlp-main)

Copied to clipboard

Challenge: Existing models for metaphor detection require a large amount of labeled data and are not linguistically-based.
Approach: They propose a ContrAstive pre-Trained modEl (CATE) for metaphor detection with semi-supervised learning using a pre-trained model to obtain a contextual representation of target words.
Outcome: The proposed model outperforms existing models on several benchmark datasets and achieves better performance against state-of-the-art models.
A Span-based Dynamic Local Attention Model for Sequential Sentence Classification (2021.acl-short)

Copied to clipboard

Challenge: Existing methods for sentence classification ignore latent segment structure of document, in which contiguous sentences have coherent semantics.
Approach: They propose a span-based dynamic local attention model that captures structural information by supervised dynamic local focus.
Outcome: The proposed model outperforms state-of-the-art models on two benchmark datasets.
Relation-aware Ensemble Learning for Knowledge Graph Embedding (2023.emnlp-main)

Copied to clipboard

Challenge: Existing methods to explore semantics of knowledge graphs have been proposed to explore these semantics in distinct ways.
Approach: They propose to leverage existing methods in relation-aware manner to learn an ensemble by leveraging existing methods.
Outcome: The proposed method has the same computation cost as general ensemble methods but with much better performance on benchmark datasets.
Multi-modal Contrastive Representation Learning for Entity Alignment (2022.coling-1)

Copied to clipboard

Challenge: Existing studies focus on how to utilize information from different modalities, but it is not trivial to leverage multi-modal knowledge in entity alignment because of the modality heterogeneity.
Approach: They propose a Multi-modal Contrastive Learning based Entity Alignment model which learns multiple individual representations from multiple modalities and performs contrastive learning to jointly model inter-modal and inter-modal interactions.
Outcome: The proposed model outperforms state-of-the-art models on public datasets under both supervised and unsupervised conditions.
MultiDx: A Multi-Source Knowledge Integration Framework towards Diagnostic Reasoning (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches focus on diagnostic reasoning based on internal model knowledge or static knowledge bases.
Approach: They propose a two-stage diagnostic reasoning framework that integrates multi-perspective evidence to generate a diagnostic prediction.
Outcome: The proposed method generates suspected diagnoses and reasoning traces from web search, SOAP-formatted case, and clinical case database.
MODE-LSTM: A Parameter-efficient Recurrent Network with Multi-Scale for Sentence Classification (2020.emnlp-main)

Copied to clipboard

Challenge: Existing models for sentence classification use linear convolution, which may not be sufficient to model the non-consecutive dependency of the phrase and may overfit the sequential information.
Approach: They propose a model that extracts multi-scale n-gram features for understanding the semantic meaning of sentences by some key-phrases located at different positions.
Outcome: The proposed model outperforms existing models on eight benchmark datasets and is competitive against state-of-the-art models.
Guiding Large Language Models for Biomedical Entity Linking via Restrictive and Contrastive Decoding (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing attempts to apply large language models to BioEL have revealed difficulties .
Approach: They propose a framework that enables large language models to adapt well to BioEL . they employ restrictive decoding to ensure the generation of valid entities .
Outcome: Extensive experiments show that the framework outperforms existing LLMs.
Biomedical Entity Linking as Multiple Choice Question Answering (2024.lrec-main)

Copied to clipboard

Challenge: Existing methods for biomedical entity linking are discriminative and disambiguative . Existing models for bioMEDical entity linking use a BERT-based encoder to encode mentions and entities into the same embedding space and dissociate mentions by nearest neighbors.
Approach: They propose a model that treats biomedical entity linking as Multiple Choice Question Answering.
Outcome: The proposed model outperforms state-of-the-art models on several datasets.
A Survey on Foundation Language Models for Single-cell Biology (2025.acl-long)

Copied to clipboard

Challenge: Existing single-cell foundation language models are based on pre-trained and large language models.
Approach: They review the development of single-cell foundation language models . they discuss data tokenization strategies and pre-training paradigms .
Outcome: The proposed models have shown remarkable performance in a variety of single-cell data analysis tasks.
Multi-perspective Improvement of Knowledge Graph Completion with Large Language Models (2024.lrec-main)

Copied to clipboard

Challenge: Knowledge graph completion (KGC) is a widely used method to tackle incompleteness in knowledge graphs (KGs).
Approach: They propose a general framework to compensate for the deficiency of contextualized knowledge by querying large language models from various perspectives.
Outcome: The proposed framework improves knowledge graph completion (KGC) by querying large language models from various perspectives.

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