All Publications

  • Zero-Shot Transfer Learning with Synthesized Data for Multi-Domain Dialogue State Tracking Campagna, G., Foryciarz, A., Moradshahi, M., Lam, M. S., Assoc Computat Linguist ASSOC COMPUTATIONAL LINGUISTICS-ACL. 2020: 122–32

    View details for Web of Science ID 000570978200012

  • Localizing Open-Ontology QA Semantic Parsers in a Day Using Machine Translation Empirical Methods in Natural Language Processing (EMNLP) Moradshahi, M., Campagna, G., Semnani, S. J., Semnani, S., Lam, M. S. 2020: 14

    View details for DOI 10.18653/v1/2020.emnlp-main.481

  • Genie: A Generator of Natural Language Semantic Parsers for Virtual Assistant Commands Campagna, G., Xu, S., Moradshahi, M., Socher, R., Lam, M. S., McKinley, K. S., Fisher, K. ASSOC COMPUTING MACHINERY. 2019: 394–410

    View details for DOI 10.1145/3314221.3314594

    View details for Web of Science ID 000523190300026

  • HUBERT Untangles BERT to Improve Transfer across NLP Tasks Moradshahi, M., Palangi, H., Lam, M. S., Smolensky, P., Gao, J. arXiv. 2019 13

    Abstract

    We introduce HUBERT which combines the structured-representational power of Tensor-Product Representations (TPRs) and BERT, a pre-trained bidirectional Transformer language model. We show that there is shared structure between different NLP datasets that HUBERT, but not BERT, is able to learn and leverage. We validate the effectiveness of our model on the GLUE benchmark and HANS dataset. Our experiment results show that untangling data-specific semantics from general language structure is key for better transfer among NLP tasks.

  • Optical MIMO Signal Processing for Direct-Detection Mode-Division Multiplexing Choutagunta, K., Arik, S. O., Moradshahi, M., Kahn, J. M., IEEE IEEE. 2017

    View details for Web of Science ID 000427031500329