no code implementations • 21 Jul 2023 • Konstantine Arkoudas
GPT-4 was released in March 2023 to wide acclaim, marking a very substantial improvement across the board over GPT-3. 5 (OpenAI's previously best model, which had powered the initial release of ChatGPT).
no code implementations • 24 Jan 2023 • Subendhu Rongali, Mukund Sridhar, Haidar Khan, Konstantine Arkoudas, Wael Hamza, Andrew McCallum
In this work, we present an architecture to perform such domain adaptation automatically, with only a small amount of metadata about the new domain and without any new training data (zero-shot) or with very few examples (few-shot).
2 code implementations • 1 Dec 2022 • Konstantine Arkoudas, Nicolas Guenon des Mesnards, Melanie Rubino, Sandesh Swamy, Saarthak Khanna, Weiqi Sun, Khan Haidar
Much recent work in task-oriented parsing has focused on finding a middle ground between flat slots and intents, which are inexpressive but easy to annotate, and powerful representations such as the lambda calculus, which are expressive but costly to annotate.
no code implementations • 15 Jun 2022 • Jack FitzGerald, Shankar Ananthakrishnan, Konstantine Arkoudas, Davide Bernardi, Abhishek Bhagia, Claudio Delli Bovi, Jin Cao, Rakesh Chada, Amit Chauhan, Luoxin Chen, Anurag Dwarakanath, Satyam Dwivedi, Turan Gojayev, Karthik Gopalakrishnan, Thomas Gueudre, Dilek Hakkani-Tur, Wael Hamza, Jonathan Hueser, Kevin Martin Jose, Haidar Khan, Beiye Liu, Jianhua Lu, Alessandro Manzotti, Pradeep Natarajan, Karolina Owczarzak, Gokmen Oz, Enrico Palumbo, Charith Peris, Chandana Satya Prakash, Stephen Rawls, Andy Rosenbaum, Anjali Shenoy, Saleh Soltan, Mukund Harakere Sridhar, Liz Tan, Fabian Triefenbach, Pan Wei, Haiyang Yu, Shuai Zheng, Gokhan Tur, Prem Natarajan
We present results from a large-scale experiment on pretraining encoders with non-embedding parameter counts ranging from 700M to 9. 3B, their subsequent distillation into smaller models ranging from 17M-170M parameters, and their application to the Natural Language Understanding (NLU) component of a virtual assistant system.
Cross-Lingual Natural Language Inference intent-classification +5
no code implementations • DeepLo 2022 • Melanie Rubino, Nicolas Guenon des Mesnards, Uday Shah, Nanjiang Jiang, Weiqi Sun, Konstantine Arkoudas
However, a single model is still typically trained and deployed for each task separately, requiring labeled training data for each, which makes it challenging to support new tasks, even within a single business vertical (e. g., food-ordering or travel booking).
1 code implementation • NAACL 2022 • Wenting Zhao, Konstantine Arkoudas, Weiqi Sun, Claire Cardie
Task-oriented parsing (TOP) aims to convert natural language into machine-readable representations of specific tasks, such as setting an alarm.
1 code implementation • 29 Apr 2022 • Subendhu Rongali, Konstantine Arkoudas, Melanie Rubino, Wael Hamza
Semantic parsing is an important NLP problem, particularly for voice assistants such as Alexa and Google Assistant.
no code implementations • 5 Mar 2022 • Weiqi Sun, Haidar Khan, Nicolas Guenon des Mesnards, Melanie Rubino, Konstantine Arkoudas
We examine two such promising techniques, prefix tuning and bias-term tuning, specifically on semantic parsing.
no code implementations • NAACL 2021 • Victor Soto, Konstantine Arkoudas
Accordingly, unsupervised learning and SSL (semi-supervised learning) techniques continue to be of vital importance.
no code implementations • 15 Dec 2020 • Subendhu Rongali, Beiye Liu, Liwei Cai, Konstantine Arkoudas, Chengwei Su, Wael Hamza
Since our model can process both speech and text input sequences and learn to predict a target sequence, it also allows us to do zero-shot E2E SLU by training on only text-hypothesis data (without any speech) from a new domain.
Ranked #3 on Spoken Language Understanding on Snips-SmartLights
Automatic Speech Recognition Automatic Speech Recognition (ASR) +4
no code implementations • COLING 2020 • Boya Yu, Konstantine Arkoudas, Wael Hamza
We present a neural model for paraphrasing and train it to generate delexicalized sentences.
no code implementations • WS 2019 • Chunyang Xiao, Christoph Teichmann, Konstantine Arkoudas
While sequence-to-sequence (seq2seq) models achieve state-of-the-art performance in many natural language processing tasks, they can be too slow for real-time applications.
no code implementations • 22 Jun 2019 • Konstantine Arkoudas, Mohamed Yahya
The Bloomberg Terminal has been a leading source of financial data and analytics for over 30 years.