NLP for Wikipedia (EMNLP 2024)/Program
| Home | Call for Papers |
|
WikiNLP: Advancing Natural Language Process for Wikipedia
Co-located with EMNLP 2024
|
Attending
[edit]Workshop registration is handled through the main EMNLP conference. Early registration ends 21 October and there are virtual and in-person options. Details may be found here: https://2024.emnlp.org/registration/
Invited Speakers
[edit]- Jess Wade (Imperial College London and Wikimedia community member)
- Scott A. Hale (Oxford Internet Institute, Meedan, and the Alan Turing Institute)
- David Adelani (Masakhane)
- Isabelle Augenstein (University of Copenhagen)
- Hsuvas Borkakoty (Cardiff University)
- Yucheng Jiang (Stanford University)
- Ilyas Lebleu (École Normale Supérieure and WikiProject AI-Cleanup)
- Andreas Vlachos (University of Cambridge)
- Leila Zia (Wikimedia Foundation)
Program
[edit]All aspects of the workshop will occur on Saturday 16 November 2024. The workshop is based in Miami but remote participation is available via EMNLP. If you are remote, click on the times in the table to see them in your local timezone. Additional details can be found on EMNLP's Underline platform for registered attendees: https://underline.io/events/470/sessions?searchGroup=lecture&eventSessionId=18629.
| Miami (US-EST) | UTC-time | Session | Notes |
|---|---|---|---|
| 09:00 | 14:00 UTC | Opening remarks | Isaac/Lucie introducing the workshop |
| 09:05 | 14:05 UTC | Keynote by Jess Wade | 30-min talk (remote) + Joint Q&A |
| 09:50 | 14:50 UTC | 2-minute paper lightning talks | Pre-recorded |
| 10:30 | 15:30 UTC | Coffee break | |
| 11:00 | 16:00 UTC | Poster session | In-person or virtual on Gather |
| 12:00 | 17:00 UTC | Lunch | |
| 12:45 | 17:45 UTC | Keynote by Scott A. Hale | 30-min talk (remote) + Joint Q&A |
| 13:30 | 18:30 UTC | Panel: Misinformation + Wikipedia Isabelle Augenstein, Hsuvas Borkakoty, Andreas Vlachos |
|
| 14:15 | 19:15 UTC | Panel: Impact of LLMs on Wikipedia David Adelani, Yucheng Jiang, Ilyas Lebleu |
|
| 15:00 | 20:00 UTC | Closing (30-minutes) | Statements by Leila Zia |
Accepted Papers
[edit]Track 1: Novel Works (archival)
[edit]See also online proceedings
- BordIRlines: A Dataset for Evaluating Cross-lingual Retrieval Augmented Generation.
Bryan Li, Samar Haider, Fiona Luo, Adwait Agashe, Chris Callison-Burch. - Multi-Label Field Classification for Scientific Documents using Expert and Crowd-sourced Knowledge.
Rebecca Gelles, James Dunham. - Uncovering Differences in Persuasive Language in Russian versus English Wikipedia.
Bryan Li, Aleksey Panasyuk, Chris Callison-Burch. - Retrieval Evaluation for Long-Form and Knowledge-Intensive Image–Text Article Composition.
Jheng-Hong Yang, Carlos Lassance, Rafael Sampaio de Rezende, Krishna Srinivasan, Stéphane Clinchant, Jimmy Lin. - WikiBias as an Extrapolation Corpus for Bias Detection.
Karla Salas-Jimenez, Francisco López-Ponce, Sergio-Luis Ojeda-Trueba, Gemma Bel-Enguix. - HOAXPEDIA: A Unified Wikipedia Hoax Articles Dataset.
Hsuvas Borkakoty, Luis Espinosa-Anke. - The Rise of AI-Generated Content in Wikipedia.
Creston Brooks, Samuel Eggert, Denis Peskoff. - Embedded Topic Models Enhanced by Wikification.
Takashi Shibuya, Takehito Utsuro. - Wikimedia data for AI: a review of Wikimedia datasets for NLP tasks and AI-assisted editing.
Isaac Johnson, Lucie-Aimée Kaffee, Miriam Redi. - Blocks Architecture (BloArk): Efficient, Cost-Effective, and Incremental Dataset Architecture for Wikipedia Revision History.
Lingxi Li, Zonghai Yao, Sunjae Kwon, Hong Yu. - ARMADA: Attribute-Based Multimodal Data Augmentation.
Xiaomeng Jin, Jeonghwan Kim, Yu Zhou, Kuan-Hao Huang, Te-Lin Wu, Nanyun Peng, Heng Ji. - Summarization-Based Document IDs for Generative Retrieval with Language Models.
Alan Li, Daniel Cheng, Phillip Keung, Jungo Kasai, Noah A. Smith.
Track 2: Published Works (non-archival)
[edit]- Low-Resourced Languages and Online Knowledge Repositories: A Need-Finding Study. PDF
Hellina Hailu Nigatu, John Canny, Sarah E. Chasins. - Leveraging Corpus Metadata to Detect Template-based Translation: An Exploratory Case Study of the Egyptian Arabic Wikipedia Edition. PDF
Saied Alshahrani, Hesham Haroon, Ali Elfilali, Mariama Njie, Jeanna Matthews. - Leveraging Grammatical Framework and WordNet for Natural Language Generation from Wikidata. PDF
Krasimir Angelov, Andrea Carrión del Fresno, Ekaterina Voloshina, Aarne Ranta. - Entity Retrieval for Answering Entity-Centric Questions. PDF
Hassan S. Shavarani, Anoop Sarkar. - Best of Both Worlds: Towards Improving Temporal Knowledge Base Question Answering via Targeted Fact Extraction. PDF
Nithish Kannen, Udit Sharma, Sumit Neelam, Dinesh Khandelwal, Shajith Ikbal, Hima Karanam, L Subramaniam. - Edisum: Summarizing and Explaining Wikipedia Edits at Scale. PDF
Marija Šakota, Isaac Johnson, Guosheng Feng, Robert West. - Omnipedia: using the manual of style to automate article review. PDF, poster
Samuel J Klein, Michael Zargham, Sayer Tindall, Alex Andonian. - Into the Unknown Unknowns: Engaged Human Learning through Participation in Language Model Agent Conversations. PDF
Yucheng Jiang, Yijia Shao, Dekun Ma, Sina J. Semnani, Monica S. Lam.