Papers with generation method

4 papers
Competence-based Question Generation (2022.coling-1)

Copied to clipboard

Challenge: Existing models of natural language understanding rely on question answering and logical inference benchmark challenges to evaluate performance of systems.
Approach: They propose a method to generate CB questions using English cooking recipes . they argue that a broader effort needs to be put on measuring linguistic competencies .
Outcome: The proposed method performs poorly on large pretrained language models until they are provided with additional contextualized semantic information.
HypoGen: Hyperbole Generation with Commonsense and Counterfactual Knowledge (2021.findings-emnlp)

Copied to clipboard

Challenge: despite its abundance, the computational explorations of hyperboles remain under-explored.
Approach: They propose a sentence-level hyperbole generation method that leverages commonsense and counterfactual inference to generate hyperbolic candidates based on the results.
Outcome: The proposed method generates hyperboles with high success rate, intensity, funniness, and creativity.
Generation and Extraction Combined Dialogue State Tracking with Hierarchical Ontology Integration (2021.emnlp-main)

Copied to clipboard

Challenge: Current models are not satisfactory for solving out-of-vocabulary problems . current models assume that the task ontology is well defined in advance .
Approach: They propose to enhance the interrelation between slots with masked hierarchical attention.
Outcome: The proposed model yields a significant performance gain over current state-of-the-art model and is more robust to out-ofvocabulary problem compared with other methods.
Exploring Pre-trained Language Models for Event Extraction and Generation (P19-1)

Copied to clipboard

Challenge: Existing methods to extract event data are laborious to create and limited in size.
Approach: They propose an event extraction model to overcome the roles overlap problem by separating the argument prediction in terms of roles.
Outcome: The proposed method surpasses existing methods on the ACE2005 dataset and improves on the previous methods.

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