Shafiuddin Rehan Ahmed

I am a 4th year PhD Candidate in the Department of Computer Science at the University of Colorado, Boulder advised by James H. Martin. My research interest lies in the fundamental understanding of actions and events in language and efficient Natural Language Processing. My most recent projects revolve around tractable methods for Event Coreference Resolution.

news

Feb 20, 2024	Our paper Linear Cross-document Event Coreference Resolution with X-AMR was accepted at LREC-COLING 2024!
Jan 22, 2024	Our paper X-AMR Annotation Tool was accepted for System Demo at EACL, 2024!
Aug 28, 2023	TAing the NLP fall 2023 class. Check out the course page!
Jul 9, 2023	Visiting Toronto, Canada for the ACL conference from July 9-14. Checkout the pics here!
Jun 6, 2023	New preprint released: https://arxiv.org/abs/2306.05434.
May 23, 2023	Our paper How Good is the Model in Model-in-the-loop Event Coreference Resolution Annotation? was accepted to The 17th Linguistic Annotation Workshop (Co-located with ACL 2023).
May 22, 2023	Starting summer internship at explosion.ai (Makers of spaCy).
May 10, 2023	New preprint released: https://arxiv.org/abs/2305.05672.
May 2, 2023	Our paper $2n$ is better than $n^2$: Decomposing Event Coreference Resolution into Two Tractable Problems* was accepted to Findings of the Association for Computational Linguistics, 2023.
May 9, 2022	Started summer internship at explosion.ai (Makers of spaCy).

selected publications

X-AMR Annotation Tool

Shafiuddin Rehan Ahmed, Jon Cai, Martha Palmer, and James H. Martin

In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations, Mar 2024

Abs Bib URL Code

This paper presents a novel Cross-document Abstract Meaning Representation (X-AMR) annotation tool designed for annotating key corpus-level event semantics. Leveraging machine assistance through the Prodigy Annotation Tool, we enhance the user experience, ensuring ease and efficiency in the annotation process. Through empirical analyses, we demonstrate the effectiveness of our tool in augmenting an existing event corpus, highlighting its advantages when integrated with GPT-4.
@inproceedings{ahmed-etal-2024-x, title = {{X}-{AMR} Annotation Tool}, author = {Ahmed, Shafiuddin Rehan and Cai, Jon and Palmer, Martha and Martin, James H.}, editor = {Aletras, Nikolaos and De Clercq, Orphee}, booktitle = {Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations}, month = mar, year = {2024}, address = {St. Julians, Malta}, publisher = {Association for Computational Linguistics}, url = {https://aclanthology.org/2024.eacl-demo.19}, pages = {177--186}, }
How Good Is the Model in Model-in-the-loop Event Coreference Resolution Annotation?

Shafiuddin Rehan Ahmed, Abhijnan Nath, Michael Regan, Adam Pollins, and 2 more authors

In Proceedings of the 17th Linguistic Annotation Workshop (LAW-XVII), Jul 2023

Abs Bib URL Code

Annotating cross-document event coreference links is a time-consuming and cognitively demanding task that can compromise annotation quality and efficiency. To address this, we propose a model-in-the-loop annotation approach for event coreference resolution, where a machine learning model suggests likely corefering event pairs only. We evaluate the effectiveness of this approach by first simulating the annotation process and then, using a novel annotator-centric Recall-Annotation effort trade-off metric, we compare the results of various underlying models and datasets. We finally present a method for obtaining 97% recall while substantially reducing the workload required by a fully manual annotation process.
@inproceedings{ahmed-etal-2023-good, title = {How Good Is the Model in Model-in-the-loop Event Coreference Resolution Annotation?}, author = {Ahmed, Shafiuddin Rehan and Nath, Abhijnan and Regan, Michael and Pollins, Adam and Krishnaswamy, Nikhil and Martin, James H.}, booktitle = {Proceedings of the 17th Linguistic Annotation Workshop (LAW-XVII)}, month = jul, year = {2023}, address = {Toronto, Canada}, publisher = {Association for Computational Linguistics}, url = {https://aclanthology.org/2023.law-1.14}, doi = {10.18653/v1/2023.law-1.14}, pages = {136--145}, }
2*n is better than n^2: Decomposing Event Coreference Resolution into Two Tractable Problems

Shafiuddin Rehan Ahmed, Abhijnan Nath, James H. Martin, and Nikhil Krishnaswamy

In Findings of the Association for Computational Linguistics: ACL 2023, Jul 2023

Abs Bib URL Code

Event Coreference Resolution (ECR) is the task of linking mentions of the same event either within or across documents. Most mention pairs are not coreferent, yet many that are coreferent can be identified through simple techniques such as lemma matching of the event triggers or the sentences in which they appear. Existing methods for training coreference systems sample from a largely skewed distribution, making it difficult for the algorithm to learn coreference beyond surface matching. Additionally, these methods are intractable because of the quadratic operations needed. To address these challenges, we break the problem of ECR into two parts: a) a heuristic to efficiently filter out a large number of non-coreferent pairs, and b) a training approach on a balanced set of coreferent and non-coreferent mention pairs. By following this approach, we show that we get comparable results to the state of the art on two popular ECR datasets while significantly reducing compute requirements. We also analyze the mention pairs that are “hard” to accurately classify as coreferent or non-coreferentcode repo: \mathttgithub.com/ahmeshaf/lemma_ce_coref.
@inproceedings{ahmed-etal-2023-2, title = {$2*n$ is better than $n^2$: Decomposing Event Coreference Resolution into Two Tractable Problems}, author = {Ahmed, Shafiuddin Rehan and Nath, Abhijnan and Martin, James H. and Krishnaswamy, Nikhil}, booktitle = {Findings of the Association for Computational Linguistics: ACL 2023}, month = jul, year = {2023}, address = {Toronto, Canada}, publisher = {Association for Computational Linguistics}, url = {https://aclanthology.org/2023.findings-acl.100}, doi = {10.18653/v1/2023.findings-acl.100}, pages = {1569--1583}, }