Adobe Research at ACL-IJCNLP 2021

August 2, 2021

In this ACL 2021 paper, Adobe Research and university collaborators propose a new method which enhances entity and relation extraction by joining a system-generated draft entity graph and a prior knowledge graph.

The Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP 2021) will be held virtually from August 2 to 4, 2021. ACL-IJCNLP is one of the top research conferences on natural language processing. In recent years, deep learning approaches have been prominently featured in the papers presented at this conference.

Adobe Research will present a total of 7 papers at the main conference, 5 papers in the Findings category, and 1 workshop paper on research topics including question answering, information extraction, machine learning, natural language processing, computational argumentation, image captioning, common-sense reasoning, machine learning fairness, dependency parsing, and many more. 

Nearly all of Adobe’s papers are the results of student internships or other collaborations with university students and faculty. Check out the Adobe Research internships and full-time careers pages to learn more about opportunities to work with us. 

Main conference papers

A Gradually Soft Multi-Task and Data-Augmented Approach to Medical Question Understanding
Khalil Mrini, Franck Dernoncourt, David Seunghyun Yoon, Trung Bui, Walter Chang, Emilia Farcas, Ndapa Nakashole
 
Counterfactuals to Control Latent Disentangled Text Representations for Style Transfer
Sharmila Reddy Nangi, Niyati Chhaya, Sopan Khosla, Nikhil Kaushik, Harshit Nyati
 
Joint Biomedical Entity and Relation Extraction with Knowledge-Enhanced Collective Inference
Tuan Lai, Heng Ji, ChengXiang Zhai, Quan Hung Tran
 
Syntopical Graphs for Computational Argumentation Tasks
Joe Barrow, Rajiv Jain, Nedim Lipka, Franck Dernoncourt, Vlad Morariu, Varun Manjunatha, Douglas Oard, Philip Resnik, Henning Wachsmuth
 
TIMERS: Document-level Temporal Relation Extraction
Puneet Mathur, Rajiv Jain, Franck Dernoncourt, Vlad Morariu, Quan Hung Tran, Dinesh Manocha
 
UMIC: An Unreferenced Metric for Image Captioning via Contrastive Learning
Hwanhee Lee, David Seunghyun Yoon, Franck Dernoncourt, Trung Bui, Kyomin Jung
 
Unleash GPT-2 Power for Event Detection
Amir Pouran Ben Veyseh, Viet Dac Lai, Franck Dernoncourt, Thien Huu Nguyen

Findings papers

Domain-Aware Dependency Parsing for Questions
Aparna Garimella, Laura Chiticariu, Yunyao Li
 
He is very intelligent, she is very beautiful? On Mitigating Social Biases in Language Modelling and Generation
Aparna Garimella, Akhash Amarnath, Kiran Kumar, Akash Pramod Yalla, Anandhavelu N, Niyati Chhaya, Balaji Vasan Srinivasan
 
Learning Contextualized Knowledge Structures for Commonsense Reasoning
Jun Yan, Mrigank Raman, Aaron Chan, Tianyu Zhang, Ryan Rossi, Handong Zhao, Sungchul Kim, Nedim Lipka and Xiang Ren
 
Out of Order: How important is the sequential order of words in a sentence in Natural Language Understanding tasks?
Thang Pham, Trung Bui, Long Mai, Anh Nguyen
 
PSED: A Dataset for Selecting Emphasis in Presentation Slides
Amirreza Shirani, Giai Tran, Hieu Trinh, Franck Dernoncourt, Nedim Lipka, Jose Echevarria, Thamar Solorio, Paul Asente

Workshop paper (SemEval) 

Dynamic Path Reasoning for Measurement Relation Extraction
Amir Pouran Ben Veyseh, Franck Dernoncourt, Thien Huu Nguyen

Related Posts