no code implementations • NAACL 2022 • Nidhi Vakil, Hadi Amiri
We present a generic and trend-aware curriculum learning approach that effectively integrates textual and structural information in text graphs for relation extraction between entities, which we consider as node pairs in graphs.
no code implementations • 22 Nov 2023 • Nidhi Vakil, Hadi Amiri
We present a curriculum learning approach that builds on existing knowledge about text and graph complexity formalisms for training with text graph data.
1 code implementation • 18 Nov 2023 • Jiali Cheng, Hadi Amiri
MMUL formulates the multimodal unlearning task by focusing on three key properties: (a): modality decoupling, which effectively decouples the association between individual unimodal data points within multimodal inputs marked for deletion, rendering them as unrelated data points within the model's context, (b): unimodal knowledge retention, which retains the unimodal representation capability of the model post-unlearning, and (c): multimodal knowledge retention, which retains the multimodal representation capability of the model post-unlearning.
1 code implementation • 31 Oct 2023 • Mohamed Elgaar, Hadi Amiri
We employ a characterization of linguistic complexity from psycholinguistic and language acquisition research to develop data-driven curricula to understand the underlying linguistic knowledge that models learn to address NLP tasks.
no code implementations • 17 Jul 2023 • Nidhi Vakil, Hadi Amiri
The proposed solution advances existing research in curriculum learning for graph neural networks with the ability to incorporate a fine-grained spectrum of graph difficulty criteria in their training paradigms.
no code implementations • 14 Jul 2023 • Mohamed Elgaar, Hadi Amiri
We introduce the problem of curriculum discovery and describe a curriculum learning framework capable of discovering effective curricula in a curriculum space based on prior knowledge about sample difficulty.
no code implementations • 17 May 2022 • Nidhi Vakil, Hadi Amiri
We present a generic and trend-aware curriculum learning approach for graph neural networks.
no code implementations • 29 Sep 2021 • Mohamed Elgaar, Hadi Amiri
We describe a curriculum learning framework capable of discovering optimal curricula in addition to performing standard curriculum learning.
no code implementations • ACL 2021 • Hadi Amiri, Mitra Mohtarami, Isaac Kohane
We present a text representation approach that can combine different views (representations) of the same input through effective data fusion and attention strategies for ranking purposes.
no code implementations • ACL 2021 • Nazanin Dehghani, Hassan Hajipoor, Hadi Amiri
We propose an effective context-sensitive neural model for time to event (TTE) prediction task, which aims to predict the amount of time to/from the occurrence of given events in streaming content.
no code implementations • NAACL 2019 • Hassan Hajipoor, Hadi Amiri, Maseud Rahgozar, Farhad Oroumchian
Serial recall experiments study the ability of humans to recall words in the order in which they occurred.
no code implementations • NAACL 2019 • Hadi Amiri, Mitra Mohtarami
We present Vector of Locally Aggregated Embeddings (VLAE) for effective and, ultimately, lossless representation of textual content.
no code implementations • NAACL 2019 • Hadi Amiri
Self-training is a semi-supervised learning approach for utilizing unlabeled data to create better learners.
no code implementations • WS 2018 • Chen Lin, Timothy Miller, Dmitriy Dligach, Hadi Amiri, Steven Bethard, Guergana Savova
Neural network models are oftentimes restricted by limited labeled instances and resort to advanced architectures and features for cutting edge performance.
no code implementations • NAACL 2018 • Hadi Amiri, Timothy Miller, Guergana Savova
Automatic identification of spurious instances (those with potentially wrong labels in datasets) can improve the quality of existing language resources, especially when annotations are obtained through crowdsourcing or automatically generated based on coded rankings.
no code implementations • EMNLP 2017 • Hadi Amiri, Timothy Miller, Guergana Savova
We present a novel approach for training artificial neural networks.
no code implementations • WS 2017 • Timothy Miller, Steven Bethard, Hadi Amiri, Guergana Savova
Detecting negated concepts in clinical texts is an important part of NLP information extraction systems.