no code implementations • EMNLP (newsum) 2021 • Nicole Beckage, Shachi H Kumar, Saurav Sahay, Ramesh Manuvinakurike
By compressing the previous contexts by ~70%, we achieve better ROUGE scores over our baseline models.
no code implementations • ACL (CODI, CRAC) 2021 • Sopan Khosla, Juntao Yu, Ramesh Manuvinakurike, Vincent Ng, Massimo Poesio, Michael Strube, Carolyn Rosé
In this paper, we provide an overview of the CODI-CRAC 2021 Shared-Task: Anaphora Resolution in Dialogue.
no code implementations • SIGDIAL (ACL) 2020 • Amanda Bergqvist, Ramesh Manuvinakurike, Deepthi Karkada, Maike Paetzel
The present study aims to examine the prevalent notion that people entrain to the vocabulary of a dialogue system.
no code implementations • LREC 2022 • Deepthi Karkada, Ramesh Manuvinakurike, Maike Paetzel-Prüsmann, Kallirroi Georgila
In this work, we study entrainment of users playing a creative reference resolution game with an autonomous dialogue system.
no code implementations • SLPAT (ACL) 2022 • Shachi H. Kumar, Hsuan Su, Ramesh Manuvinakurike, Max Pinaroc, Sai Prasad, Saurav Sahay, Lama Nachman
Conversational assistants are ubiquitous among the general population, however, these systems have not had an impact on people with disabilities, or speech and language disorders, for whom basic day-to-day communication and social interaction is a huge struggle.
no code implementations • COLING (CODI, CRAC) 2022 • Juntao Yu, Sopan Khosla, Ramesh Manuvinakurike, Lori Levin, Vincent Ng, Massimo Poesio, Michael Strube, Carolyn Rosé
The CODI-CRAC 2022 Shared Task on Anaphora Resolution in Dialogues is the second edition of an initiative focused on detecting different types of anaphoric relations in conversations of different kinds.
no code implementations • ACL 2022 • Shachi H Kumar, Hsuan Su, Ramesh Manuvinakurike, Maximilian C. Pinaroc, Sai Prasad, Saurav Sahay, Lama Nachman
Intelligent conversational assistants have become an integral part of our lives for performing simple tasks.
no code implementations • SIGDIAL (ACL) 2021 • Ramesh Manuvinakurike, Saurav Sahay, Wenda Chen, Lama Nachman
In this work, we develop a dataset for incremental temporal summarization in a multiparty dialogue.
no code implementations • 29 Nov 2023 • Ramesh Manuvinakurike, Saurav Sahay, Sangeeta Manepalli, Lama Nachman
Large Language Models (LLMs) exhibit powerful summarization abilities.
no code implementations • 8 Mar 2023 • Sumanta Bhattacharyya, Ramesh Manuvinakurike, Sahisnu Mazumder, Saurav Sahay
In this work, we develop a prompting approach for incremental summarization of task videos.
no code implementations • 12 Feb 2023 • Hsuan Su, Shachi H Kumar, Sahisnu Mazumder, Wenda Chen, Ramesh Manuvinakurike, Eda Okur, Saurav Sahay, Lama Nachman, Shang-Tse Chen, Hung-Yi Lee
With the power of large pretrained language models, various research works have integrated knowledge into dialogue systems.
no code implementations • 3 Nov 2022 • Ramesh Manuvinakurike, Sovan Biswas, Giuseppe Raffa, Richard Beckwith, Anthony Rhodes, Meng Shi, Gesem Gudino Mejia, Saurav Sahay, Lama Nachman
Development of task guidance systems for aiding humans in a situated task remains a challenging problem.
no code implementations • 2 Nov 2022 • Sovan Biswas, Anthony Rhodes, Ramesh Manuvinakurike, Giuseppe Raffa, Richard Beckwith
Recent temporal action segmentation approaches need frame annotations during training to be effective.
no code implementations • 4 Dec 2021 • Shachi H Kumar, Hsuan Su, Ramesh Manuvinakurike, Saurav Sahay, Lama Nachman
We build models that can suggest relevant cues in the dialog response context which is used to control response generation and can speed up communication.
no code implementations • EACL (HumEval) 2021 • Jakob Nyberg, Ramesh Manuvinakurike, Maike Paetzel-Prüsmann
In this paper, we argue for exploring the use of subjective evaluations within the process of training language generation models in a multi-task learning setting.
no code implementations • LREC 2020 • Maike Paetzel, Deepthi Karkada, Ramesh Manuvinakurike
This paper presents a multimodal corpus of 209 spoken game dialogues between a human and a remote-controlled artificial agent.
no code implementations • 3 Sep 2019 • Maike Paetzel, Ramesh Manuvinakurike
In an increasingly globalized world, geographic literacy is crucial.
no code implementations • 3 Dec 2018 • Jacqueline Brixey, Ramesh Manuvinakurike, Nham Le, Tuan Lai, Walter Chang, Trung Bui
This work presents the task of modifying images in an image editing program using natural language written commands.
no code implementations • COLING 2018 • Deepthi Karkada, Ramesh Manuvinakurike, Kallirroi Georgila
We introduce a dataset containing human-authored descriptions of target locations in an "end-of-trip in a taxi ride" scenario.
no code implementations • COLING 2018 • Ramesh Manuvinakurike, Sumanth Bharadwaj, Kallirroi Georgila
In this study we collect and annotate human-human role-play dialogues in the domain of weight management.
no code implementations • WS 2018 • Ramesh Manuvinakurike, Trung Bui, Walter Chang, Kallirroi Georgila
We present {``}conversational image editing{''}, a novel real-world application domain combining dialogue, visual information, and the use of computer vision.
no code implementations • WS 2017 • Ramesh Manuvinakurike, David DeVault, Kallirroi Georgila
We apply Reinforcement Learning (RL) to the problem of incremental dialogue policy learning in the context of a fast-paced dialogue game.
no code implementations • LREC 2016 • Sina Zarrie{\ss}, Julian Hough, Casey Kennington, Ramesh Manuvinakurike, David DeVault, Raquel Fern{\'a}ndez, David Schlangen
PentoRef is a corpus of task-oriented dialogues collected in systematically manipulated settings.