CRAC 2023
Sixth Workshop on Computational Models of Reference, Anaphora and Coreference
CRAC 2023, the Sixth Workshop on Computational Models of Reference, Anaphora and Coreference, was held at EMNLP 2023 in Singapore (December 6–7).
Topics
The workshop welcomes submissions describing theoretical and applied computational work on anaphora/coreference resolution. Topics of interest include but are not limited to:
coreference resolution for less-researched languages
annotation and interpretation of anaphoric relations, including relations other than identity coreference (e.g., bridging references)
investigation of difficult cases of anaphora and their resolution
coreference resolution in noisy data (e.g. in social media)
new applications of coreference resolution
About the workshop series
Background: Since 2016, the yearly CRAC (and its predecessor, CORBON) workshop has become the primary forum for researchers interested in the computational modeling of reference, anaphora, and coreference to discuss and publish their results. Over the years, this workshop series has successfully organized five shared tasks, which stimulated interest in new problems in this area of research, facilitated the discussion and dissemination of results on new problems/directions (e.g., multimodal reference resolution), and helped expand the coreference community that used to be dominated by European researchers to include young researchers from the Americas.
Objectives: The aim of the workshop is to provide a forum where work on all aspects of computational work on anaphora resolution and annotation, including both coreference and types of anaphora such as bridging references resolution and discourse deixis, can be presented.
Previous editions: CRAC started as CORBON 2016, co-located with NAACL and in 2017 with EACL. In 2018 the focus of the workshop was broadened to cover all cases of computational modelling of reference, anaphora, and coreference and it was renamed to CRAC. CRAC 2018 and 2019 were held at NAACL, CRAC 2020 at COLING, CRAC 2021 at EMNLP and CRAC 2022 again at COLING.
Our workshop in ACL Anthology: Please take a look at the proceedings of CORBON and CRAC in ACL Anthology.
CRAC 2023 Shared Task on Multilingual Coreference Resolution
CRAC 2023 also featured presentation of the results of the Shared Task on Multilingual Coreference Resolution and an invited talk by Milan Straka on Recent Computational Approaches to Coreference Resolution.
Shared Task papers
Findings of the Second Shared Task on Multilingual Coreference Resolution (Zdeněk Žabokrtský, Miloslav Konopik, Anna Nedoluzhko, Michal Novák, Maciej Ogrodniczuk, Martin Popel, Ondrej Prazak, Jakub Sido, Daniel Zeman)
Multilingual coreference resolution: Adapt and Generate (Natalia Skachkova, Tatiana Anikina and Anna Mokhova)
Neural End-to-End Coreference Resolution using Morphological Information (Tuğba Pamay Arslan, Kutay Acar and Gülşen Eryiğit)
ÚFAL CorPipe at CRAC 2023: Larger Context Improves Multilingual Coreference Resolution (Milan Straka) – Shared Task Winner
McGill at CRAC 2023: Multilingual Generalization of Entity-Ranking Coreference Resolution Models (Ian Porada and Jackie Chi Kit Cheung)
Important dates
Workshop papers due: September 15, 2023
Notification of acceptance: October 6, 2023
Camera-ready papers due: October 18, 2023
Workshop date: December 6–7, 2023
Accepted papers
Long papers
Investigating Failures to Generalize for Coreference Resolution Models (Ian Porada, Alexandra Olteanu, Kaheer Suleman, Adam Trischler and Jackie Chi Kit Cheung)
Scalar Anaphora: Annotating Degrees of Coreference in Text (Bingyang Ye, Jingxuan Tu and James Pustejovsky)
Towards Transparency in Coreference Resolution: A Quantum-Inspired Approach (Hadi Wazni and Mehrnoosh Sadrzadeh)
Towards Harmful Erotic Content Detection through Coreference-Driven Contextual Analysis (Inez Okulska and Emilia Wiśnios)
Short papers
Better Handling Coreference Resolution in Aspect Level Sentiment Classification by Fine-Tuning Language Models (Dhruv Mullick, Bilal Ghanem and Alona Fyshe) – Best Paper Award
CAW-coref: Conjunction-Aware Word-level Coreference Resolution (Karel D'Oosterlinck, Semere Kiros Bitew, Brandon Papineau, Christopher Potts, Thomas Demeester and Chris Develder)
Filling in the Gaps: Efficient Event Coreference Resolution using Graph Autoencoder Networks (Loic De Langhe, Orphee De Clercq and Veronique Hoste)
MARRS: Multimodal Reference Resolution System (Halim Cagri Ates, Shruti Bhargava, Site Li, Jiarui Lu, Siddhardha Maddula, Joel Ruben Antony Moniz, Anil kumar Nalamalapu, Roman Hoang nguyen, Melis Ozyildirim, Alkesh Patel, Dhivya Piraviperumal, Vincent Renkens, Ankit Samal, Thy Tran, Bo-Hsiang Tseng, Hong Yu, Yuan Zhang and Rong Zou)
Demo papers and Extended abstracts
Integrated Annotation of Event Structure, Object States, and Entity Coreference (Kyeongmin Rim and James Pustejovsky)
The pragmatics of characters' mental perspectives in pronominal reference resolution (Tiana Simovic and Craig Chambers)
Invited Talks
Bernd Bohnet: Multilingual Coreference Resolution with Innovative seq2seq Models
In this talk, we explore advancements in coreference resolution systems, focusing on our novel approach that leverages a text-to-text (seq2seq) paradigm of modern LLMs. We utilize multilingual T5 (mT5) as the foundational language model. Traditional coreference systems primarily employ search algorithms across possible spans. In contrast, our method jointly predicts mentions and links, achieving superior accuracy on the CoNLL-2012 datasets. Notably, our system recorded an 83.3 F1-score for English, surpassing previous research. Further evaluations on multilingual datasets, particularly Arabic and Chinese, yielded improvements over prior works, showcasing the multilingual transfer abilities of our model across many languages. Additionally, our experiments with the SemEval-2010 datasets in various settings—including zero-shot and low resource transfer—reveal significant performance improvements for other languages. We will discuss the capabilities of LLMs to provide a more streamlined, effective, and unified approach to coreference resolution.
Bernd Bohnet is a researcher in Natural Language Processing (NLP). He earned his Ph.D. with a specialization in text generation. Subsequently, he served as an tenured Assistant Professor at the University of Birmingham. For the past nine years, Dr. Bohnet carried out research with Google and Google DeepMind. His expertise encompasses a broad range of topics in natural language understanding, including tagging, parsing, coreference resolution, and reading comprehension. In recent years, he has turned his attention to Large Language Models (LLMs), focusing on their capabilities in factual accuracy, question answering, and the integration techniques into LLMs.
Milan Straka: Recent Computational Approaches to Coreference Resolution
In a manner consistent with development in various domains of natural language processing, the performance of coreference resolution systems has been exhibiting a consistent improvement over recent years. With coreference resolution being a complex structured prediction problem, quite a few approaches have been put forth, encompassing auto-/non-autoregressive decoding, diverse mention representation, and pretrained language models of varying size and kind. In this talk, I seek to offer a review of prominent approaches and assess and compare them with a high degree of independence. Furthermore, owing to the CorefUD initiative providing datasets in many languages, I aim to empirically quantify the impact of multilingual and crosslingual transfer on the performance of the best system of the CRAC 2023 Shared Task on Multilingual Coreference Resolution.
Milan Straka is an assistant professor at the Institute of Formal and Applied Linguistics at the Faculty of Mathematics and Physics, Charles University, Prague, Czech Republic. He is the (co-)author of several shared-task-winning NLP tools like UDPipe, a morphosyntactic analyzer for currently 72 languages; PERIN, a semantic parser; and CorPipe, the winner of CRAC 2022 and 2023 shared tasks on multilingual coreference resolution. His further research interests include named entity recognition, named entity linking, grammar error correction, and multilingual models in general.
Workshop schedule
December 6: CRAC 2023
Opening remarks
9:00 – 9:15: Opening and welcome (Vincent Ng, Maciej Ogrodniczuk and Sameer Pradhan)
Invited talk
9:15 – 10:30: Multilingual Coreference Resolution with Innovative seq2seq Models (Bernd Bohnet)
Coffee break
Paper session 1
11:00 – 11:10: MARRS: Multimodal Reference Resolution System (Halim Cagri Ates, Shruti Bhargava, Site Li, Jiarui Lu, Siddhardha Maddula, Joel Ruben Antony Moniz, Anil kumar Nalamalapu, Roman Hoang nguyen, Melis Ozyildirim, Alkesh Patel, Dhivya Piraviperumal, Vincent Renkens, Ankit Samal, Thy Tran, Bo-Hsiang Tseng, Hong Yu, Yuan Zhang and Rong Zou)
11:10 – 11:20: CAW-coref: Conjunction-Aware Word-level Coreference Resolution (Karel D'Oosterlinck, Semere Kiros Bitew, Brandon Papineau, Christopher Potts, Thomas Demeester and Chris Develder)
11:20 – 11:40: Towards Transparency in Coreference Resolution: A Quantum-Inspired Approach (Hadi Wazni and Mehrnoosh Sadrzadeh)
11:40 – 12:00: Scalar Anaphora: Annotating Degrees of Coreference in Text (Bingyang Ye, Jingxuan Tu and James Pustejovsky)
12:00 – 12:20: Investigating Failures to Generalize for Coreference Resolution Models (Ian Porada, Alexandra Olteanu, Kaheer Suleman, Adam Trischler and Jackie Chi Kit Cheung)
12:20 – 12:30: Better Handling Coreference Resolution in Aspect Level Sentiment Classification by Fine-Tuning Language Models (Dhruv Mullick, Bilal Ghanem and Alona Fyshe) – Best Paper Award
12:30 – 12:40: The pragmatics of characters' mental perspectives in pronominal reference resolution (Tiana Simovic and Craig Chambers)
Lunch break
Paper session 2
14:00 – 14:10: Filling in the Gaps: Efficient Event Coreference Resolution using Graph Autoencoder Networks (Loic De Langhe, Orphee De Clercq and Veronique Hoste)
14:10 – 14:30: Towards Harmful Erotic Content Detection through Coreference-Driven Contextual Analysis (Inez Okulska and Emilia Wiśnios)
14:30 – 14:40: Integrated Annotation of Event Structure, Object States, and Entity Coreference (Kyeongmin Rim and James Pustejovsky)
Findings paper session
14:40 – 14:50: The Coreference under Transformation Labeling Dataset: Entity Tracking in Procedural Texts Using Event Models (Kyeongmin Rim, Jingxuan Tu, Bingyang Ye, Marc Verhagen, Eben Holderness and James Pustejovsky)
14:50 – 15:00: ezCoref: Towards Unifying Annotation Guidelines for Coreference Resolution (Ankita Gupta, Marzena Karpinska, Wenlong Zhao, Kalpesh Krishna, Jack Merullo, Luke Yeh, Mohit Iyyer and Brendan O’Connor)
15:00 – 15:10: LongtoNotes: OntoNotes with Longer Coreference Chains (Kumar Shridhar, Nicholas Monath, Raghuveer Thirukovalluru, Alessandro Stolfo, Manzil Zaheer, Andrew McCallum and Mrinmaya Sachan)
15:10 – 15:20: A Memory Model for Question Answering from Streaming Data Supported by Rehearsal and Anticipation of Coreference Information (Vladimir Araujo, Alvaro Soto and Marie-Francine Moens)
15:20 – 15:30: Investigating Multilingual Coreference Resolution by Universal Annotations (Haixia Chai and Michael Strube)
Coffee break
Panel on Universal Anaphora
16:00 – 17:00: Panel discussion (moderated by Sameer Pradhan, cancelled)
December 7: CRAC 2023 Shared Task on Multilingual Coreference Resolution
Invited talk
9:00 – 9:45: Recent Computational Approaches to Coreference Resolution (Milan Straka)
Overview paper talk
9:45 – 10:30: Findings of the Second Shared Task on Multilingual Coreference Resolution (Zdeněk Žabokrtský, Miloslav Konopík, Anna Nedoluzhko, Michal Novák, Maciej Ogrodniczuk, Martin Popel, Ondřej Pražák, Jakub Sido and Daniel Zeman)
Coffee break
Shared task system demonstration session
11:00 – 11:20: Multilingual coreference resolution: Adapt and Generate (Natalia Skachkova, Tatiana Anikina and Anna Mokhova)
11:20 – 11:40: Neural End-to-End Coreference Resolution using Morphological Information (Tuğba Pamay Arslan, Kutay Acar and Gülşen Eryiğit)
11:40 – 12:00: ÚFAL CorPipe at CRAC 2023: Larger Context Improves Multilingual Coreference Resolution (Milan Straka) – Shared Task Winner
12:00 – 12:20: McGill at CRAC 2023: Multilingual Generalization of Entity-Ranking Coreference Resolution Models (Ian Porada and Jackie Chi Kit Cheung)
Surprise presentation
12:20 – 12:30: Bridging and Anaphorcity (Cennet Oguz, Ivana Kruijff-Korbayova, Pascal Denis, Emmanuel Vincent and Josef van Genabith)
Closing remarks
12:30 – 12:35: Closing the workshop (Maciej Ogrodniczuk, Sameer Pradhan and Vincent Ng)
Program Committee
Rahul Aralikatte (Mila – Quebec Artificial Intelligence Institute)
Antonio Branco (University of Lisbon)
Arie Cattan (Bar-Ilan University)
Haixia Chai (Heidelberg University)
Yulia Grishina (Amazon)
Christian Hardmeier (IT University of Copenhagen)
Lars Hellan (Norwegian University of Science and Technology)
Veronique Hoste (Ghent University)
Yufang Hou (IBM Research)
Ruihong Huang (Texas A&M University)
Sobha Lalitha Devi (AU-KBC Research Center, Anna University of Chennai)
Ekaterina Lapshinova-Koltunski (University of Hildesheim)
Sharid Loáiciga (University of Gothenburg)
Costanza Navaretta (University of Copenhagen)
Anna Nedoluzhko (Charles University in Prague)
Michal Novák (Charles University in Prague)
Massimo Poesio (Queen Mary University of London)
Ian Porada (Mila – Quebec Artificial Intelligence Institute)
Yaqin Yang (Brandeis University)
Yilun Zhu (Georgetown University)
Heike Zinsmeister (University of Hamburg)
Organizing Committee
Maciej Ogrodniczuk (Institute of Computer Science, Polish Academy of Sciences)
Vincent Ng (University of Texas at Dallas)
Sameer Pradhan (University of Pennsylvania and cemantix)
Massimo Poesio (Queen Mary University of London)