Papers by Ghazaleh Kazeminejad

5 papers
A Graphical Interface for Curating Schemas (2021.acl-demo)

Copied to clipboard

Challenge: Existing work on analyzing information extracted from documents has focused on examining the model understanding of complex schemas.
Approach: They propose a curation interface that takes an IE system’s output in a pre-defined format and generates a graphical representation of its elements.
Outcome: The proposed interface can be used to edit and prune schemas for complex events like Improvised Explosive Device (IED) based scenarios.
Learning Semantic Role Labeling from Compatible Label Sequences (2023.findings-emnlp)

Copied to clipboard

Challenge: Prior work has shown that cross-task interaction helps, but only explored multitask learning so far.
Approach: They propose a framework that jointly models VerbNet and PropBank labels as one sequence and enforcing Semlink constraints during decoding improves the overall F1 .
Outcome: The proposed model outperforms the prior best in-domain model by 3.5 (VerbNet) and 0.8 (PropBank).
Event Semantic Knowledge in Procedural Text Understanding (2023.starsem-1)

Copied to clipboard

Challenge: Annotators’ reliance on commonsense knowledge to annotate implicit state information is a challenge for entity state tracking.
Approach: They propose a method for entity state tracking that incorporates commonsense entity-centric knowledge from ConceptNet into a BERT-based neural-symbolic architecture.
Outcome: The proposed model outperforms existing models on the ProPara dataset and is domain-agnostic.
Automatically Extracting Qualia Relations for the Rich Event Ontology (C18-1)

Copied to clipboard

Challenge: a new study uses qualia relations extracted from the Suggested Upper Merged Ontology to extract information about entities . human annotators find qualia relationships and origins of the information to be reasonable .
Approach: They propose to extract qualia from the Generative Lexicon to extract quealia . they assume the theoretical framework of the Generative Lexicons .
Outcome: The proposed method extracts information from the Suggested Upper Merged Ontology (SUMO) human annotators find the extracted information to be reasonable, the authors show .

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