AIConfPaper
← Search

Alexandros Papangelis

10 accepted papers

2024

FANTAstic SEquences and Where to Find Them: Faithful and Efficient API Call Generation through State-tracked Constrained Decoding and Reranking

Zhuoer Wang, Leonardo F. R. Ribeiro, Alexandros Papangelis, Rohan Mukherjee, Tzu-Yen Wang, Xinyan Zhao +3
EMNLP 2024finding

API call generation is the cornerstone of large language models’ tool-using ability that provides access to the larger world. However, existing supervised and in-context learning approaches suffer from high training costs, poor data efficiency, and generated API calls that can be unfaithful to the A…

Cited by 1Source ↗PDF ↗code ↗Scholar ↗
2024

Semi-Supervised Reward Modeling via Iterative Self-Training

Yifei He, Haoxiang Wang, Ziyan Jiang, Alexandros Papangelis, Han Zhao
EMNLP 2024finding

Reward models (RM) capture the values and preferences of humans and play a central role in Reinforcement Learning with Human Feedback (RLHF) to align pretrained large language models (LLMs). Traditionally, training these models relies on extensive human-annotated preference data, which poses signifi…

Cited by 3Source ↗PDF ↗code ↗Scholar ↗
2023

Identifying Entrainment in Task-Oriented Conversations

Run Chen, Seokhwan Kim, Alexandros Papangelis, Julia Hirschberg, Yang Liu, Dilek Hakkani-Tür
ICASSP 2023accepted

Human interlocutors adapt their behavior to each other in a conversation through entrainment. While entrainment has been found in long chit-chat conversations, much less research has been conducted on task-oriented dialogs. In this paper, we investigate short task-oriented Wizard-of-Oz conversations…

Cited by 0Source ↗Scholar ↗
2023

Towards Credible Human Evaluation of Open-Domain Dialog Systems Using Interactive Setup

Sijia Liu, Patrick Lange, Behnam Hedayatnia, Alexandros Papangelis, Di Jin, Andrew Wirth +2
AAAI 2023technical

Evaluating open-domain conversation models has been an open challenge due to the open-ended nature of conversations. In addition to static evaluations, recent work has started to explore a variety of per-turn and per-dialog interactive evaluation mechanisms and provide advice on the best setup. In t…

Cited by 3Source ↗PDF ↗code ↗Scholar ↗
2022

What is wrong with you?: Leveraging User Sentiment for Automatic Dialog Evaluation

Sarik Ghazarian, Behnam Hedayatnia, Alexandros Papangelis, Yang Liu, Dilek Hakkani-Tur
ACL 2022findings

Accurate automatic evaluation metrics for open-domain dialogs are in high demand. Existing model-based metrics for system response evaluation are trained on human annotated data, which is cumbersome to collect. In this work, we propose to use information that can be automatically extracted from the…

Cited by 21Source ↗PDF ↗code ↗Scholar ↗
2021

Language Model is all You Need: Natural Language Understanding as Question Answering

Mahdi Namazifar, Alexandros Papangelis, Gökhan Tür, Dilek Hakkani-Tür
ICASSP 2021accepted

Different flavors of transfer learning have shown tremendous impact in advancing research and applications of machine learning. In this work we study the use of a certain family of transfer learning, where the target domain is mapped to the source domain. Specifically we map Natural Language Underst…

Cited by 0Source ↗Scholar ↗
2020

Exploration Based Language Learning for Text-Based Games

Andrea Madotto, Mahdi Namazifar, Joost Huizinga, Piero Molino, Adrien Ecoffet, Huaixiu Zheng +4
IJCAI 2020poster

This work presents an exploration and imitation-learning-based agent capable of state-of-the-art performance in playing text-based computer games. These games are of interest as they can be seen as a testbed for language understanding, problem-solving, and language generation by artificial agents.…

Cited by 0Source ↗PDF ↗Scholar ↗
2020

Joint Contextual Modeling for ASR Correction and Language Understanding

Yue Weng, Sai Sumanth Miryala, Chandra Khatri, Runze Wang, Huaixiu Zheng, Piero Molino +5
ICASSP 2020accepted

The quality of automatic speech recognition (ASR) is critical to Dialogue Systems as ASR errors propagate to and directly impact downstream tasks such as language understanding (LU). In this paper, we propose multi-task neural approaches to perform contextual language correction on ASR outputs joint…

Cited by 0Source ↗Scholar ↗
2017

Predicting dialogue success, naturalness, and length with acoustic features

Alexandros Papangelis, Margarita Kotti, Yannis Stylianou
ICASSP 2017accepted

Statistical methods for Spoken Dialogue Systems have been shown to reduce the cost of development, while successfully handling a variety of applications. However, such systems are usually trained with simulated users or paid subjects in controlled settings. While this may be sufficient to jump-start…

Cited by 0Source ↗Scholar ↗