no code implementations • NAACL 2022 • Sha Li, Mahdi Namazifar, Di Jin, Mohit Bansal, Heng Ji, Yang Liu, Dilek Hakkani-Tur
In this work, we propose to automatically convert the background knowledge documents into document semantic graphs and then perform knowledge selection over such graphs.
no code implementations • 29 Nov 2023 • Taha Aksu, Devamanyu Hazarika, Shikib Mehri, Seokhwan Kim, Dilek Hakkani-Tür, Yang Liu, Mahdi Namazifar
We apply CESAR on InstructDial, a benchmark for instruction-based dialog tasks.
no code implementations • 24 Nov 2023 • Di Jin, Shikib Mehri, Devamanyu Hazarika, Aishwarya Padmakumar, Sungjin Lee, Yang Liu, Mahdi Namazifar
Learning from human feedback is a prominent technique to align the output of large language models (LLMs) with human expectations.
1 code implementation • 20 May 2023 • Chao Zhao, Spandana Gella, Seokhwan Kim, Di Jin, Devamanyu Hazarika, Alexandros Papangelis, Behnam Hedayatnia, Mahdi Namazifar, Yang Liu, Dilek Hakkani-Tur
We hope this task and dataset can promote further research on TOD and subjective content understanding.
1 code implementation • 17 Feb 2023 • Yan Xu, Mahdi Namazifar, Devamanyu Hazarika, Aishwarya Padmakumar, Yang Liu, Dilek Hakkani-Tür
Large pre-trained language models (PLMs) have been shown to retain implicit knowledge within their parameters.
no code implementations • 16 Feb 2023 • Mahdi Namazifar, Devamanyu Hazarika, Dilek Hakkani-Tur
Moreover, we argue that the bias term of the value linear transformation has a more prominent role than that of the bias term of the query linear transformation.
no code implementations • 10 Feb 2023 • Yen-Ting Lin, Alexandros Papangelis, Seokhwan Kim, Sungjin Lee, Devamanyu Hazarika, Mahdi Namazifar, Di Jin, Yang Liu, Dilek Hakkani-Tur
This work focuses on in-context data augmentation for intent detection.
Ranked #1 on Intent Detection on BANKING77 10-shot
1 code implementation • 26 Oct 2022 • Yifan Chen, Devamanyu Hazarika, Mahdi Namazifar, Yang Liu, Di Jin, Dilek Hakkani-Tur
Prefix-tuning, or more generally continuous prompt tuning, has become an essential paradigm of parameter-efficient transfer learning.
no code implementations • 15 Jun 2022 • Sha Li, Mahdi Namazifar, Di Jin, Mohit Bansal, Heng Ji, Yang Liu, Dilek Hakkani-Tur
Providing conversation models with background knowledge has been shown to make open-domain dialogues more informative and engaging.
1 code implementation • Findings (NAACL) 2022 • Yifan Chen, Devamanyu Hazarika, Mahdi Namazifar, Yang Liu, Di Jin, Dilek Hakkani-Tur
The massive amount of trainable parameters in the pre-trained language models (PLMs) makes them hard to be deployed to multiple downstream tasks.
no code implementations • 11 Jun 2021 • Devamanyu Hazarika, Mahdi Namazifar, Dilek Hakkani-Tür
In this work, we propose novel approaches for controlling encoder-decoder transformer-based NLG models in zero-shot.
no code implementations • 26 Mar 2021 • Mahdi Namazifar, John Malik, Li Erran Li, Gokhan Tur, Dilek Hakkani Tür
Masked language models have revolutionized natural language processing systems in the past few years.
no code implementations • 5 Nov 2020 • Mahdi Namazifar, Alexandros Papangelis, Gokhan Tur, Dilek Hakkani-Tür
Different flavors of transfer learning have shown tremendous impact in advancing research and applications of machine learning.
no code implementations • 3 Nov 2020 • Mahdi Namazifar, Gokhan Tur, Dilek Hakkani Tür
The insertion and drop modification of the input text during training of WLM resemble the types of noise due to Automatic Speech Recognition (ASR) errors, and as a result WLMs are likely to be more robust to ASR noise.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +4
no code implementations • 28 Jan 2020 • Yue Weng, Sai Sumanth Miryala, Chandra Khatri, Runze Wang, Huaixiu Zheng, Piero Molino, Mahdi Namazifar, Alexandros Papangelis, Hugh Williams, Franziska Bell, Gokhan Tur
As a baseline approach, we trained task-specific Statistical Language Models (SLM) and fine-tuned state-of-the-art Generalized Pre-training (GPT) Language Model to re-rank the n-best ASR hypotheses, followed by a model to identify the dialog act and slots.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +3
no code implementations • 24 Jan 2020 • Andrea Madotto, Mahdi Namazifar, Joost Huizinga, Piero Molino, Adrien Ecoffet, Huaixiu Zheng, Alexandros Papangelis, Dian Yu, Chandra Khatri, Gokhan Tur
In this work, we propose to use the exploration approach of Go-Explore for solving text-based games.
4 code implementations • 17 Jan 2020 • Alexandros Papangelis, Mahdi Namazifar, Chandra Khatri, Yi-Chia Wang, Piero Molino, Gokhan Tur
Plato has been designed to be easy to understand and debug and is agnostic to the underlying learning frameworks that train each component.
1 code implementation • WS 2019 • Lei Shu, Piero Molino, Mahdi Namazifar, Hu Xu, Bing Liu, Huaixiu Zheng, Gokhan Tur
It is based on a simple and practical yet very effective sequence-to-sequence approach, where language understanding and state tracking tasks are modeled jointly with a structured copy-augmented sequential decoder and a multi-label decoder for each slot.
no code implementations • 6 Dec 2017 • Mahdi Namazifar
We frame NESC as a binary classification problem and we use NER as well as recurrent neural networks to find the probability of candidate named entity is a real named entity.