Papers by Ranran Haoran Zhang

6 papers
COVID-19 Literature Knowledge Graph Construction and Drug Repurposing Report Generation (2021.naacl-demos)

Copied to clipboard

Challenge: a new framework to digest relevant biomedical knowledge is needed to combat COVID-19 . quantity of research results is a bottleneck, and false information promoted in publications .
Approach: a team of researchers has developed a framework to extract multimedia knowledge elements from scientific literature to combat COVID-19.
Outcome: a new framework extracts fine-grained multimedia knowledge elements from scientific literature . it provides detailed contextual sentences, subfigures, and knowledge subgraphs as evidence . the framework is based on a case study of drug repurposing .
Enhance Multimodal Consistency and Coherence for Text-Image Plan Generation (2025.findings-acl)

Copied to clipboard

Challenge: Existing studies on textual plan generation only focus on LLMs, enabling applications in robotics, virtual assistants, and instruc.
Approach: They propose a framework that generates and refines text-image plans step-by-step . they collect a new benchmark consisting of 1,100 tasks and their text- image pair solutions covering 11 daily topics.
Outcome: The proposed framework generates and refines text-image plans step-by-step and improves on existing models.
Efficient PRM Training Data Synthesis via Formal Verification (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches for constructing PRM training data rely on human annotation or sampling-based labeling methods that require repeated LLM calls.
Approach: They propose a framework that synthesizes PRM training data by annotating step-level error labels using formal verification tools such as Z3 and Isabelle.
Outcome: The proposed framework synthesizes PRM training data from formal logic and theorem proving tasks without human annotation or additional LLM calls.
Minimize Exposure Bias of Seq2Seq Models in Joint Entity and Relation Extraction (2020.findings-emnlp)

Copied to clipboard

Challenge: Existing methods to extract relation triplets from plain text introduce exposure bias . prior work has focused on pipeline methods that ignore intrinsic interactions between subtasks and propagate classification errors through the tasks.
Approach: They propose a model that reduces the decoding length to three within a triplet and removes the order among triplets.
Outcome: The proposed model overfits to both datasets while showing better generalization.
From Lazy to Prolific: Tackling Missing Labels in Open Vocabulary Extreme Classification by Positive-Unlabeled Sequence Learning (2025.findings-naacl)

Copied to clipboard

Challenge: Extreme multi-label classification (OXMC) is a challenging and critical task in natural language processing.
Approach: They propose to use PUSL to reframe OXMC as an infinite keyphrase generation task . they propose to adopt evaluation metrics to reliably assess OXML models with incomplete ground truths.
Outcome: The proposed approach improves on a highly imbalanced e-commerce dataset with missing labels . it generates 30% more unique labels and 72% of its predictions align with actual user queries .
ConEntail: An Entailment-based Framework for Universal Zero and Few Shot Classification with Supervised Contrastive Pretraining (2023.eacl-main)

Copied to clipboard

Challenge: Existing models for text classification are not universally applicable and lack annotated data.
Approach: They propose a framework for universal zero and few shot classification with supervised contrastive pretraining that can generalize to diverse classification tasks in both zero and many shot settings.
Outcome: The proposed framework outperforms baseline models in zero and few shot settings.

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