EMNLP 2022

Program

08:55 - 09:00 Opening Remarks

09:00 - 09:40 Keynote Talk 1

  • Measuring what matters for human-AI teams

Saleema Amershi, Microsoft Research

(virtual)

9:40 - 10:00 Invited Talk 1

  • Enabling domain experts to create their own NLP models: Notes from our journey

Yannis Katsis, IBM Research

(virtual)

10:00 – 10:20 Invited Talk 2

  • Understanding and Addressing Uncertainty in Crowd Annotation on Subjective Tasks

Amy Zhang, University of Washington

(virtual

10:20 - 10:40 Regular Papers Session 1

  • AVA-TMP: A Human-in-the-Loop Multi-layer Dynamic Topic Modeling Pipeline

Viseth Sean, Padideh Danaee, Yang Yang and Hakan Kardes

(virtual)

  • Cross-lingual Short-text Entity Linking: Generating Features for Neuro-Symbolic Methods

Qiuhao Lu, Sairam Gurajada, Prithviraj Sen, Lucian Popa, Dejing Dou and Thien Nguyen

(virtual)

10:40 - 11:00 Coffee Break

11:00 - 11:40 Keynote Talk 2

  • Decision-making in an uncertain world

Azza Abouzied, NYU Abu Dhabi

(in person)

11:40 - 12:10 Invited Papers

  • WANLI: Worker and AI Collaboration for Natural Language Inference Dataset Creation

Alisa Liu, Swabha Swayamdipta, Noah A. Smith and Yejin Choi.

(in person)

  • Cheater's Bowl: Human vs. Computer Search Strategies for Open-Domain QA

Wanrong He, Andrew Mao, and Jordan Boyd-Graber.

(in person)

  • Human-in-the-Loop Hate Speech Classification in a Multilingual Context

Ana Kotarcic, Dominik Hangartner, Fabrizio Gilardi, Selina Kurer and Karsten Donnay.

(in person)

12:10 - 12:40 Regular Papers Session 2

  • DoSA : A System to Accelerate Annotations on Business Documents with Human-in-the-Loop

Neelesh Shukla, Msp Raja, Raghu Katikeri and Amit Vaid

(virtual)


  • Partially Humanizing Weak Supervision: Towards a Better Low Resource Pipeline for Spoken Language Understanding

Ayush Kumar, Rishabh Kumar Tripathi and Jithendra Vepa

(virtual)


  • Guiding Generative Language Models for Data Augmentation in Few-Shot Text Classification

Aleksandra Edwards, Asahi Ushio, Jose Camacho-Collados, Helene de Ribaupierre and Alun Preece

(virtual)

14:00 - 14:30 Regular Paper Session 3

  • Improving Human Annotation Effectiveness for Fact Collection by Identifying the Most Relevant Answers

Pranav Kamath, Yiwen Sun, Thomas Semere, Adam Green, Scott Manley, Xiaoguang Qi, Kun Qian, Yunyao Li and Mina Farid

(in person)


  • MEGAnno: Exploratory Labeling for NLP in Computational Notebooks

Dan Zhang, Hannah Kim, Rafael Li Chen, Eser Kandogan and Estevam Hruschka

(in person)


  • A Gamified Approach to Frame Semantic Role Labeling

Emily Amspoker and Miriam R L Petruck

(in person)

14:30 - 15:00 Regular Paper Session 4

  • Improving Named Entity Recognition in Telephone Conversations via Effective Active Learning with Human in the Loop

Md Tahmid Rahman Laskar, Cheng Chen, Xue-Yong Fu and Shashi Bhushan TN

(in person)

  • Execution-based Evaluation for Data Science Code Generation Models

Junjie Huang, Chenglong Wang, Jipeng Zhang, cong yan, Haotian Cui, Jeevana Priya Inala, Colin Clement, Nan Duan and Jianfeng Gao.

(virtual, China time)

  • Crowdsourcing Preposition Sense Disambiguation with High Precision via a Priming Task

Shira Wein and Nathan Schneider

(virtual)

15:00 – 15:30 Regular Paper Session 5

  • A Comparative Analysis between Human-in-the-loop Systems and Large Language Models for Pattern Extraction Tasks

Maeda Hanafi, Yannis Katsis, Ishan Jindal and Lucian Popa

(virtual)


  • Interactively Uncovering Latent Arguments in Social Media Platforms: A Case Study on the Covid-19 Vaccine Debate

Maria Leonor Pacheco, Tunazzina Islam, Lyle Ungar, Ming Yin and Dan Goldwasser

(virtual)


  • User or Labor: An Interaction Framework for Human-Machine Relationships in NLP

Ruyuan Wan, Naome Etori, Karla Badillo-Urquiola and Dongyeop Kang

(virtual)

15:30 - 16:00 Coffee Break

16:00 - 16:40 Keynote Talk 3

  • Data Preparation with human in the loop - The Case for a commodity crowdsourcing system

Mourad Ouzzani, Qatar Computing Research Institute

(in person)

16:40 - 17:30 Panel Discussion

  • TBD – participants to be confirmed