Adobe at EMNLP 2022

December 8, 2022

Tags: Conferences

This EMNLP 2022 workshop paper presents a novel process for stock price movement and volatility prediction. The prediction system combines the text transcripts and audio call recording input to a neural model with tabular text from semi-structured financial documents.

Adobe has co-authored a total of ten main conference papers, four papers in the Findings category, and five workshop papers for this year’s Empirical Methods in Natural Language Processing conference (EMNLP 2022), which is being held from December 7 to 11, 2022, as a hybrid event in Abu Dhabi. One of the workshop papers received the best paper runner-up award.

EMNLP is one of the top research conferences on natural language processing. In recent years, deep learning approaches have made a significant impact at this conference. This year, the Adobe co-authored papers cover research topics ranging from text simplification, information extraction, summarization, multilingual representations, event understanding, and much more.

Papers in the Findings category, a separate acceptance category at the conference, will be published in a companion conference proceedings titled Findings of the ACL: EMNLP 2022.

Many of the papers are the outcome of research internships. Please check out the Adobe Research careers page to learn more about internships and full-time career opportunities.

EMNLP 2022 conference – Adobe co-authored papers

Main conference papers

Entity Extraction in Low Resource Domains with Selective Pre-training of Large Language Models
Aniruddha Mahapatra, Sharmila Reddy Nangi, Aparna Garimella, Anandhavelu N

Robustness of Demonstration-based Learning Under Limited Data Scenario
Hongxin Zhang, Yanzhe Zhang, Ruiyi Zhang, Diyi Yang

Robustness of Fusion-based Multimodal Classifiers to Cross-Modal Content Dilutions
Gaurav Verma, Vishwa Vinay, Ryan Rossi, Srijan Kumar

Agent-specific Deontic Modality Detection in Legal Language
Abhilasha Sancheti, Aparna Garimella, Balaji Vasan Srinivasan, Rachel Rudinger

Discovering Low-rank Subspaces for Language-agnostic Multilingual Representations
Zhihui Xie, Handong Zhao, Tong Yu, Shuai Li

Learning Cross-Task Dependencies for Joint Extraction of Entities, Events, Event Arguments, and Relations
Minh Van Nguyen, Bonan Min, Franck Dernoncourt, Thien Huu Nguyen

MEE: A Novel Multilingual Event Extraction Dataset
Amir Pouran Ben Veyseh, Javid Ebrahimi, Franck Dernoncourt, Thien Huu Nguyen

MGDoc: Pre-training with Multi-granular Hierarchy for Document Image Understanding
Zilong Wang, Jiuxiang Gu, Chris Tensmeyer, Nikolaos Barmpalios, Ani Nenkova, Tong Sun, Jingbo Shang, Vlad I. Morariu

Offer a Different Perspective: Modeling the Belief Alignment of Arguments in Multi-party Debates
Suzanna Sia, Kokil Jaidka, Hansin Ahuja, Niyati Chhaya, Kevin Duh

Simple Questions Generate Named Entity Recognition Datasets
Hyunjae Kim, Jaehyo Yoo, Seunghyun Yoon, Jinhyuk Lee, Jaewoo Kang

Findings papers

Context-aware Information-theoretic Causal De-biasing for Interactive Sequence Labeling
Junda Wu, Rui Wang, Tong Yu, Ruiyi Zhang, Handong Zhao, Shuai Li, Ricardo Henao, Ani Nenkova

DocFin: Multimodal Financial Prediction and Bias Mitigation using Semi-structured Documents
Puneet Mathur, Mihir Goyal, Ramit Sawhney, Ritik Mathur, Jochen Leidner, Franck Dernoncourt, Dinesh Manocha

Influence Functions for Sequence Tagging Models
Sarthak Jain, Varun Manjunatha, Byron Wallace, Ani Nenkova

Multilingual SubEvent Relation Extraction: A Novel Dataset and Structure Induction Method
Viet Dac Lai, Hieu Man, Linh Ngo, Franck Dernoncourt, Thien Huu Nguyen

Workshop papers

Curriculum-guided Abstractive Summarization for Mental Health Online Posts
Sajad Sotudeh, Nazli Goharian, Hanieh Deilamsalehy, Franck Dernoncourt
Presented at the Health Text Mining and Information Analysis workshop

Factual Error Correction for Abstractive Summaries Using Entity Retrieval
Hwanhee Lee, Cheoneum Park, Seunghyun Yoon, Trung Bui, Franck Dernoncourt, Juae Kim, Kyomin Jung
Presented at the Natural Language Generation, Evaluation, and Metrics workshop

Text Simplification for Legal Domain: Insights and Challenges
Aparna Garimella, Abhilasha Sancheti, Vinay Aggarwal, Ananya Ganesh, Niyati Chhaya, Nandakishore Kambhatla
Presented at the Natural Legal Language Processing workshop

Graph-based Keyword Planning for Legal Clause Generation from Topics
Sagar Joshi, Sumanth Balaji, Aparna Garimella, Vasudeva Varma
Presented at the Natural Legal Language Processing workshop

Few-Shot Cross-Lingual Learning for Event Detection
Luis Guzman Nateras, Viet Lai, Franck Dernoncourt and Thien Nguyen
Presented at the Multilingual Representation Learning workshop
Best paper runner-up

Related Posts