no code implementations • EMNLP (sustainlp) 2021 • Ameeta Agrawal, Suresh Singh, Lauren Schneider, Michael Samuels
Language models pretrained on vast corpora of unstructured text using self-supervised learning framework are used in numerous natural language understanding and generation tasks.
1 code implementation • COLING 2022 • Olubusayo Olabisi, Aaron Hudson, Antonie Jetter, Ameeta Agrawal
In this work, we take a complementary approach to analyzing and improving the quality of summaries generated from social media data in terms of their ability to represent salient as well as diverse perspectives.
no code implementations • 3 May 2024 • Olubusayo Olabisi, Ameeta Agrawal
Text summarization models have typically focused on optimizing aspects of quality such as fluency, relevance, and coherence, particularly in the context of news articles.
1 code implementation • 29 Apr 2024 • Sina Bagheri Nezhad, Ameeta Agrawal
This study investigates the factors influencing the performance of multilingual large language models (MLLMs) across diverse languages.
no code implementations • 26 Mar 2024 • Yufei Tao, Ameeta Agrawal, Judit Dombi, Tetyana Sydorenko, Jung In Lee
Recent advances in interactive large language models like ChatGPT have revolutionized various domains; however, their behavior in natural and role-play conversation settings remains underexplored.
no code implementations • 11 Mar 2024 • Atharva Phatak, Vijay K. Mago, Ameeta Agrawal, Aravind Inbasekaran, Philippe J. Giabbanelli
The use of generative AI to create text descriptions from graphs has mostly focused on knowledge graphs, which connect concepts using facts.
no code implementations • 31 Jan 2024 • Yufei Tao, Tiernan Mines, Ameeta Agrawal
Conversation systems accommodate diverse users with unique personalities and distinct writing styles.
no code implementations • 31 Dec 2023 • Enas Altarawneh, Ameeta Agrawal, Michael Jenkin, Manos Papagelis
In this work, we introduce the novel problem of Predicting Emotions in Conversations (PEC) for the next turn (n+1), given combinations of textual and/or emotion input up to turn n. We systematically approach the problem by modeling three dimensions inherently connected to evoked emotions in dialogues, including (i) sequence modeling, (ii) self-dependency modeling, and (iii) recency modeling.
1 code implementation • 31 Oct 2023 • Rhitabrat Pokharel, Ameeta Agrawal
The ability to process idiomatic or literal multiword expressions is a crucial aspect of understanding and generating any language.
1 code implementation • 9 Oct 2023 • Sina Bagheri Nezhad, Ameeta Agrawal
Multilingual language models have gained significant attention in recent years, enabling the development of applications that meet diverse linguistic contexts.
no code implementations • 8 Jun 2023 • Justin J. Xie, Ameeta Agrawal
Paraphrase generation, a. k. a.
1 code implementation • 1 Jun 2023 • Rhitabrat Pokharel, Ameeta Agrawal
Prior work typically describes out-of-domain (OOD) or out-of-distribution (OODist) samples as those that originate from dataset(s) or source(s) different from the training set but for the same task.
no code implementations • ACL 2020 • Nastaran Babanejad, Ameeta Agrawal, Aijun An, Manos Papagelis
Affective tasks such as sentiment analysis, emotion classification, and sarcasm detection have been popular in recent years due to an abundance of user-generated data, accurate computational linguistic models, and a broad range of relevant applications in various domains.
no code implementations • COLING 2018 • Ameeta Agrawal, Aijun An, Manos Papagelis
As a consequence, emotionally dissimilar words, such as {``}happy{''} and {``}sad{''} occurring in similar contexts would purport more similar meaning than emotionally similar words, such as {``}happy{''} and {``}joy{''}.
no code implementations • COLING 2016 • Ameeta Agrawal, Aijun An
Emotion classification from text typically requires some degree of word-emotion association, either gathered from pre-existing emotion lexicons or calculated using some measure of semantic relatedness.