Papers with Deep NLP models

2 papers
Towards Dynamic Computation Graphs via Sparse Latent Structure (D18-1)

Copied to clipboard

Challenge: Existing approaches to learn latent structure are limited by factorization assumptions or end-to-end differentiability.
Approach: They propose a method that allows for end-to-end learning of latent structure predictors jointly with a downstream predictor.
Outcome: The proposed method allows for unrestricted dynamic graph construction from the global latent structure while maintaining differentiability.
Retrieval-guided Counterfactual Generation for QA (2022.acl-long)

Copied to clipboard

Challenge: Recent work shows that data augmentation using counterfactuals can help ameliorate this weakness.
Approach: They propose a Retrieve-Generate-Filter technique to generate counterfactuals using QA framework and question generation model trained on original task data.
Outcome: The proposed method improves performance on out-of-domain and challenging evaluation sets over and above existing 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