no code implementations • 28 Feb 2024 • Sahithya Ravi, Patrick Huber, Akshat Shrivastava, Aditya Sagar, Ahmed Aly, Vered Shwartz, Arash Einolghozati
The emergence of Large Language Models (LLMs) has brought to light promising language generation capabilities, particularly in performing tasks like complex reasoning and creative writing.
no code implementations • 2 Feb 2022 • Akshat Shrivastava, Shrey Desai, Anchit Gupta, Ali Elkahky, Aleksandr Livshits, Alexander Zotov, Ahmed Aly
We tackle this problem by introducing scenario-based semantic parsing: a variant of the original task which first requires disambiguating an utterance's "scenario" (an intent-slot template with variable leaf spans) before generating its frame, complete with ontology and utterance tokens.
no code implementations • 12 Oct 2021 • Pooja Sethi, Denis Savenkov, Forough Arabshahi, Jack Goetz, Micaela Tolliver, Nicolas Scheffer, Ilknur Kabul, Yue Liu, Ahmed Aly
Improving the quality of Natural Language Understanding (NLU) models, and more specifically, task-oriented semantic parsing models, in production is a cumbersome task.
no code implementations • 10 Jul 2021 • Shrey Desai, Akshat Shrivastava, Justin Rill, Brian Moran, Safiyyah Saleem, Alexander Zotov, Ahmed Aly
Data efficiency, despite being an attractive characteristic, is often challenging to measure and optimize for in task-oriented semantic parsing; unlike exact match, it can require both model- and domain-specific setups, which have, historically, varied widely across experiments.
no code implementations • ICML Workshop AutoML 2021 • David Eriksson, Pierce I-Jen Chuang, Samuel Daulton, Peng Xia, Akshat Shrivastava, Arun Babu, Shicong Zhao, Ahmed Aly, Ganesh Venkatesh, Maximilian Balandat
When tuning the architecture and hyperparameters of large machine learning models for on-device deployment, it is desirable to understand the optimal trade-offs between on-device latency and model accuracy.
no code implementations • Findings (ACL) 2021 • Shrey Desai, Ahmed Aly
Modern task-oriented semantic parsing approaches typically use seq2seq transformers to map textual utterances to semantic frames comprised of intents and slots.
no code implementations • 15 Apr 2021 • Shrey Desai, Akshat Shrivastava, Alexander Zotov, Ahmed Aly
Task-oriented semantic parsing models typically have high resource requirements: to support new ontologies (i. e., intents and slots), practitioners crowdsource thousands of samples for supervised fine-tuning.
no code implementations • Findings (EMNLP) 2021 • Akshat Shrivastava, Pierce Chuang, Arun Babu, Shrey Desai, Abhinav Arora, Alexander Zotov, Ahmed Aly
An effective recipe for building seq2seq, non-autoregressive, task-oriented parsers to map utterances to semantic frames proceeds in three steps: encoding an utterance $x$, predicting a frame's length |y|, and decoding a |y|-sized frame with utterance and ontology tokens.
1 code implementation • NAACL 2021 • Arun Babu, Akshat Shrivastava, Armen Aghajanyan, Ahmed Aly, Angela Fan, Marjan Ghazvininejad
Semantic parsing using sequence-to-sequence models allows parsing of deeper representations compared to traditional word tagging based models.
no code implementations • 4 Feb 2020 • Shrey Desai, Geoffrey Goh, Arun Babu, Ahmed Aly
The increasing computational and memory complexities of deep neural networks have made it difficult to deploy them on low-resource electronic devices (e. g., mobile phones, tablets, wearables).
1 code implementation • IEEE ICICIS 2019 2019 • Ahmed Aly, Gianluca Guadagni, Joanne Bechta Dugan
Deep neural networks (DNNs) have been found useful for many applications.
no code implementations • WS 2019 • Shrey Desai, Hongyuan Zhan, Ahmed Aly
The Lottery Ticket Hypothesis suggests large, over-parameterized neural networks consist of small, sparse subnetworks that can be trained in isolation to reach a similar (or better) test accuracy.
1 code implementation • IEEE UEMCON 2019 2019 • Ahmed Aly, Gianluca Guadagni, Joanne Bechta Dugan
LS is an algorithm where constrained noise is iteratively applied to subsets of the search space.
1 code implementation • 17 Jan 2019 • Ahmed Aly, David Weikersdorfer, Claire Delaunay
This paper presents an evolutionary metaheuristic called Multiple Search Neuroevolution (MSN) to optimize deep neural networks.
2 code implementations • 12 Dec 2018 • Ahmed Aly, Kushal Lakhotia, Shicong Zhao, Mrinal Mohit, Barlas Oguz, Abhinav Arora, Sonal Gupta, Christopher Dewan, Stef Nelson-Lindall, Rushin Shah
We introduce PyText - a deep learning based NLP modeling framework built on PyTorch.
no code implementations • 17 Aug 2018 • Viral Thakar, Himani Saini, Walid Ahmed, Mohammad M Soltani, Ahmed Aly, Jia Yuan Yu
Asset monitoring in construction sites is an intricate, manually intensive task, that can highly benefit from automated solutions engineered using deep neural networks.
1 code implementation • 16 Aug 2018 • Ahmed Aly, Joanne B. Dugan
We test our algorithm first on a simulated task of playing the game Flappy Bird, then on a physical NAO robot in a static Object Centering task.