no code implementations • EMNLP (BlackboxNLP) 2021 • Federico Fancellu, Lan Xiao, Allan Jepson, Afsaneh Fazly
We address this gap for two structure generation tasks, namely dependency and semantic parsing.
no code implementations • 24 Jan 2024 • Hai X. Pham, Isma Hadji, Xinnuo Xu, Ziedune Degutyte, Jay Rainey, Evangelos Kazakos, Afsaneh Fazly, Georgios Tzimiropoulos, Brais Martinez
The key technological enabler is a novel mechanism for automatic question-answer generation from procedural text which can ingest large amounts of textual instructions and produce exhaustive in-domain QA training data.
no code implementations • ICCV 2023 • Mohamed Ashraf Abdelsalam, Samrudhdhi B. Rangrej, Isma Hadji, Nikita Dvornik, Konstantinos G. Derpanis, Afsaneh Fazly
While most previous work focus on the problem of data scarcity in procedural video datasets, another core challenge of future anticipation is how to account for multiple plausible future realizations in natural settings.
1 code implementation • 31 Oct 2022 • Avery Ma, Nikita Dvornik, Ran Zhang, Leila Pishdad, Konstantinos G. Derpanis, Afsaneh Fazly
For image classification, the most popular data augmentation techniques range from simple photometric and geometrical transformations, to more complex methods that use visual saliency to craft new training examples.
no code implementations • 26 Oct 2022 • Mohamed Ashraf Abdelsalam, Zhan Shi, Federico Fancellu, Kalliopi Basioti, Dhaivat J. Bhatt, Vladimir Pavlovic, Afsaneh Fazly
The success of scene graphs for visual scene understanding has brought attention to the benefits of abstracting a visual input (e. g., image) into a structured representation, where entities (people and objects) are nodes connected by edges specifying their relations.
1 code implementation • 10 Oct 2022 • Nikita Dvornik, Isma Hadji, Hai Pham, Dhaivat Bhatt, Brais Martinez, Afsaneh Fazly, Allan D. Jepson
In this setup, we seek the optimal step ordering consistent with the procedure flow graph and a given video.
no code implementations • 20 Apr 2022 • Leila Pishdad, Ran Zhang, Konstantinos G. Derpanis, Allan Jepson, Afsaneh Fazly
Probabilistic embeddings have proven useful for capturing polysemous word meanings, as well as ambiguity in image matching.
no code implementations • EACL 2021 • {\'A}kos K{\'a}d{\'a}r, Lan Xiao, Mete Kemertas, Federico Fancellu, Allan Jepson, Afsaneh Fazly
We do so by casting dependency parsing as a tree embedding problem where we incorporate geometric properties of dependency trees in the form of training losses within a graph-based parser.
no code implementations • 1 Jan 2021 • Leila Pishdad, Ran Zhang, Afsaneh Fazly, Allan Jepson
Learning multimodal representations is a requirement for many tasks such as image--caption retrieval.
no code implementations • COLING 2020 • Leila Pishdad, Federico Fancellu, Ran Zhang, Afsaneh Fazly
Despite the recent advances in coherence modelling, most such models including state-of-the-art neural ones, are evaluated on either contrived proxy tasks such as the standard order discrimination benchmark, or tasks that require special expert annotation.
no code implementations • Findings of the Association for Computational Linguistics 2020 • Federico Fancellu, {\'A}kos K{\'a}d{\'a}r, Ran Zhang, Afsaneh Fazly
We significantly improve upon this work, by proposing a simpler architecture as well as more efficient training and inference algorithms that can always guarantee the well-formedness of the generated graphs.
no code implementations • 4 Nov 2019 • Alborz Rezazadeh Sereshkeh, Gary Leung, Krish Perumal, Caleb Phillips, Minfan Zhang, Afsaneh Fazly, Iqbal Mohomed
We present VASTA, a novel vision and language-assisted Programming By Demonstration (PBD) system for smartphone task automation.
no code implementations • WS 2017 • Shiva Taslimipoor, Omid Rohanian, Ruslan Mitkov, Afsaneh Fazly
This study investigates the supervised token-based identification of Multiword Expressions (MWEs).
no code implementations • LREC 2016 • SoHyun Park, Afsaneh Fazly, Annie Lee, Br Seibel, on, Wenjie Zi, Paul Cook
We then propose a supervised approach to classify out-of-vocabulary terms according to these categories, drawing on features based on word embeddings, and linguistic knowledge of common properties of out-of-vocabulary terms.
no code implementations • LREC 2012 • Shiva Taslimipoor, Afsaneh Fazly, Ali Hamzeh
In particular, LVCs are formed semi-productively: often a semantically-general verb (such as take) combines with a number of semantically-similar nouns to form semantically-related LVCs, as in make a decision/choice/commitment.