1 code implementation • 30 Jun 2023 • Mehrad Moradshahi, Tianhao Shen, Kalika Bali, Monojit Choudhury, Gaël de Chalendar, Anmol Goel, Sungkyun Kim, Prashant Kodali, Ponnurangam Kumaraguru, Nasredine Semmar, Sina J. Semnani, Jiwon Seo, Vivek Seshadri, Manish Shrivastava, Michael Sun, Aditya Yadavalli, Chaobin You, Deyi Xiong, Monica S. Lam
We create a new multilingual benchmark, X-RiSAWOZ, by translating the Chinese RiSAWOZ to 4 languages: English, French, Hindi, Korean; and a code-mixed English-Hindi language.
1 code implementation • 18 Feb 2023 • Mehrad Moradshahi, Sina J. Semnani, Monica S. Lam
We propose automatic methods that use ToD training data in a source language to build a high-quality functioning dialogue agent in another target language that has no training data (i. e. zero-shot) or a small training set (i. e. few-shot).
7 code implementations • 16 Apr 2022 • Yizhong Wang, Swaroop Mishra, Pegah Alipoormolabashi, Yeganeh Kordi, Amirreza Mirzaei, Anjana Arunkumar, Arjun Ashok, Arut Selvan Dhanasekaran, Atharva Naik, David Stap, Eshaan Pathak, Giannis Karamanolakis, Haizhi Gary Lai, Ishan Purohit, Ishani Mondal, Jacob Anderson, Kirby Kuznia, Krima Doshi, Maitreya Patel, Kuntal Kumar Pal, Mehrad Moradshahi, Mihir Parmar, Mirali Purohit, Neeraj Varshney, Phani Rohitha Kaza, Pulkit Verma, Ravsehaj Singh Puri, Rushang Karia, Shailaja Keyur Sampat, Savan Doshi, Siddhartha Mishra, Sujan Reddy, Sumanta Patro, Tanay Dixit, Xudong Shen, Chitta Baral, Yejin Choi, Noah A. Smith, Hannaneh Hajishirzi, Daniel Khashabi
This large and diverse collection of tasks enables rigorous benchmarking of cross-task generalization under instructions -- training models to follow instructions on a subset of tasks and evaluating them on the remaining unseen ones.
1 code implementation • 23 Mar 2022 • Monica S. Lam, Giovanni Campagna, Mehrad Moradshahi, Sina J. Semnani, Silei Xu
Task-oriented conversational agents rely on semantic parsers to translate natural language to formal representations.
no code implementations • 23 Dec 2021 • Michael Sun, Kaili Huang, Mehrad Moradshahi
Therefore, we devise an efficient and effective training solution for multilingual task-orientated dialogue systems, using the same dataset generation pipeline and end-to-end dialogue system architecture as BiToD[5], which adopted some key design choices for a minimalistic natural language design where formal dialogue states are used in place of natural language inputs.
1 code implementation • 4 Nov 2021 • Mehrad Moradshahi, Victoria Tsai, Giovanni Campagna, Monica S. Lam
On RiSAWOZ, CrossWOZ, CrossWOZ-EN, and MultiWOZ-ZH datasets we improve the state of the art by 11%, 17%, 20%, and 0. 3% in joint goal accuracy.
1 code implementation • EMNLP 2020 • Mehrad Moradshahi, Giovanni Campagna, Sina J. Semnani, Silei Xu, Monica S. Lam
We propose Semantic Parser Localizer (SPL), a toolkit that leverages Neural Machine Translation (NMT) systems to localize a semantic parser for a new language.
1 code implementation • ACL 2020 • Giovanni Campagna, Agata Foryciarz, Mehrad Moradshahi, Monica S. Lam
We show that data augmentation through synthesized data can improve the accuracy of zero-shot learning for both the TRADE model and the BERT-based SUMBT model on the MultiWOZ 2. 1 dataset.
1 code implementation • 25 Oct 2019 • Mehrad Moradshahi, Hamid Palangi, Monica S. Lam, Paul Smolensky, Jianfeng Gao
We introduce HUBERT which combines the structured-representational power of Tensor-Product Representations (TPRs) and BERT, a pre-trained bidirectional Transformer language model.
1 code implementation • 18 Apr 2019 • Giovanni Campagna, Silei Xu, Mehrad Moradshahi, Richard Socher, Monica S. Lam
We advocate formalizing the capability of virtual assistants with a Virtual Assistant Programming Language (VAPL) and using a neural semantic parser to translate natural language into VAPL code.
no code implementations • 22 May 2018 • Soheil Esmaeilzadeh, Ouassim Khebzegga, Mehrad Moradshahi
Being able to predict clinical parameters in order to diagnose gait disorders in a patient is of great value in planning treatments.
no code implementations • 8 Apr 2018 • Mehrad Moradshahi, Utkarsh Contractor
Generative Adversarial Networks (GANs) have been promising in the field of image generation, however, they have been hard to train for language generation.