activity
20192022
most citedCompositional Processing Emerges in Neural Networks Solving Math Problems

21 citations · 29 across the 5 of their papers we have counts for

collaborators

9 papers

cs.CL20222 cited

Deep Learning on a Healthy Data Diet: Finding Important Examples for Fairness

Abdelrahman Zayed, Prasanna Parthasarathi, Goncalo Mordido +3

Data-driven predictive solutions predominant in commercial applications tend to suffer from biases and stereotypes, which raises equity concerns. Prediction models may discover, us…

cs.CL2021

Enriching Transformers with Structured Tensor-Product Representations for Abstractive Summarization

Yichen Jiang, Asli Celikyilmaz, Paul Smolensky +7

Abstractive summarization, the task of generating a concise summary of input documents, requires: (1) reasoning over the source document to determine the salient pieces of informat…

cs.LG202121 cited

Compositional Processing Emerges in Neural Networks Solving Math Problems

Jacob Russin, Roland Fernandez, Hamid Palangi +4

A longstanding question in cognitive science concerns the learning mechanisms underlying compositionality in human cognition. Humans can infer the structured relationships (e.g., g…

cs.CV20201 cited

Neuro-Symbolic Representations for Video Captioning: A Case for Leveraging Inductive Biases for Vision and Language

Hassan Akbari, Hamid Palangi, Jianwei Yang +6

Neuro-symbolic representations have proved effective in learning structure information in vision and language. In this paper, we propose a new model architecture for learning multi…

cs.CV20205 cited

Novel Human-Object Interaction Detection via Adversarial Domain Generalization

Yuhang Song, Wenbo Li, Lei Zhang +6

We study in this paper the problem of novel human-object interaction (HOI) detection, aiming at improving the generalization ability of the model to unseen scenarios. The challenge…

cs.CL2019

HUBERT Untangles BERT to Improve Transfer across NLP Tasks

Mehrad Moradshahi, Hamid Palangi, Monica S. Lam +2

We introduce HUBERT which combines the structured-representational power of Tensor-Product Representations (TPRs) and BERT, a pre-trained bidirectional Transformer language model.…