Search Results for author: Mahtab Ahmed

Found 6 papers, 0 papers with code

Domain Specific Fine-tuning of Denoising Sequence-to-Sequence Models for Natural Language Summarization

no code implementations6 Apr 2022 Brydon Parker, Alik Sokolov, Mahtab Ahmed, Matt Kalebic, Sedef Akinli Kocak, Ofer Shai

Summarization of long-form text data is a problem especially pertinent in knowledge economy jobs such as medicine and finance, that require continuously remaining informed on a sophisticated and evolving body of knowledge.

Data Augmentation Denoising

You Only Need Attention to Traverse Trees

no code implementations ACL 2019 Mahtab Ahmed, Muhammad Rifayat Samee, Robert E. Mercer

To this end, we propose Tree Transformer, a model that captures phrase level syntax for constituency trees as well as word-level dependencies for dependency trees by doing recursive traversal only with attention.

Improving Tree-LSTM with Tree Attention

no code implementations1 Jan 2019 Mahtab Ahmed, Muhammad Rifayat Samee, Robert E. Mercer

In Natural Language Processing (NLP), we often need to extract information from tree topology.

Cannot find the paper you are looking for? You can Submit a new open access paper.