no code implementations • 28 Jan 2025 • Mert İnan, Anthony Sicilia, Suvodip Dey, Vardhan Dongre, Tejas Srinivasan, Jesse Thomason, Gökhan Tür, Dilek Hakkani-Tür, Malihe Alikhani
While theories of discourse and cognitive science have long recognized the value of unhurried pacing, recent dialogue research tends to minimize friction in conversational systems.
no code implementations • 17 Oct 2024 • Mert İnan, Katherine Atwell, Anthony Sicilia, Lorna Quandt, Malihe Alikhani
We introduce a goal-oriented conversational AI system enhanced with American Sign Language (ASL) instructions, presenting the first implementation of such a system on a worldwide multimodal conversational AI platform.
no code implementations • 17 Oct 2024 • Qi Cheng, Mert İnan, Rahma Mbarki, Grace Grmek, Theresa Choi, Yiming Sun, Kimele Persaud, Jenny Wang, Malihe Alikhani
In this work, for the first time, we present a dataset annotated in collaboration with developmental and cognitive psychologists for the purpose of studying nonverbal cues of uncertainty.
no code implementations • 10 May 2023 • Mert İnan, Aishwarya Padmakumar, Spandana Gella, Patrick Lange, Dilek Hakkani-Tur
Task planning is an important component of traditional robotics systems enabling robots to compose fine grained skills to perform more complex tasks.
1 code implementation • Findings (ACL) 2022 • Mert İnan, Yang Zhong, Sabit Hassan, Lorna Quandt, Malihe Alikhani
To employ our strategies, we first annotate a subset of the benchmark PHOENIX-14T, a German Sign Language dataset, with different levels of intensification.
no code implementations • 11 Feb 2022 • Carla Viegas, Mert İnan, Lorna Quandt, Malihe Alikhani
State-of-the-art sign language generation frameworks lack expressivity and naturalness which is the result of only focusing manual signs, neglecting the affective, grammatical and semantic functions of facial expressions.
2 code implementations • Findings (EMNLP) 2021 • Mert İnan, Piyush Sharma, Baber Khalid, Radu Soricut, Matthew Stone, Malihe Alikhani
Developers of text generation models rely on automated evaluation metrics as a stand-in for slow and expensive manual evaluations.