Papers by James Allen

4 papers
A Broad-Coverage Deep Semantic Lexicon for Verbs (2020.lrec-1)

Copied to clipboard

Challenge: a lack of a broad-coverage deep semantic lexicon hinders deep language understanding . we have developed a resource for verbs with the coverage of WordNet and syntactic and semantic details .
Approach: They propose a deep lexical resource for verbs with the coverage of WordNet and syntactic and semantic details that meet or exceed existing resources.
Outcome: The proposed resource has the coverage of WordNet and syntactic and semantic details that exceed existing resources.
The Role of Semantic Parsing in Understanding Procedural Text (2023.findings-eacl)

Copied to clipboard

Challenge: Inferring actions and their impact on entities involved in a procedural text can be challenging in various aspects.
Approach: They propose a symbolic parser and semantic role labeling as two sources of semantic parsing knowledge.
Outcome: The proposed framework integrates semantic parsing knowledge into state-of-the-art neural models and shows that it improves procedural understanding.
DMRetriever: A Family of Models for Improved Text Retrieval in Disaster Management (2026.acl-long)

Copied to clipboard

Challenge: Existing models fail to handle the varied search intents inherent to disaster management scenarios, resulting in inconsistent and unreliable performance.
Approach: They propose a new series of dense retrieval models tailored for disaster management that train on a three-stage framework with unsupervised contrastive pre-training and difficulty-aware progressive instruction fine-tuning.
Outcome: The proposed model outperforms baseline models by 13.3 times and 33 times over baselines with only 7.6% of their parameters.
Tackling the Story Ending Biases in The Story Cloze Test (P18-2)

Copied to clipboard

Challenge: Story Cloze Test (SCT) is a recent framework for evaluating story comprehension and script learning.
Approach: They propose to use a crowdsourcing scheme to create a new SCT dataset to overcome some of the biases discovered in the original SCT.
Outcome: The proposed model performs better than the baselines on the SCT dataset, despite human-authorship biases.

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