collaborators
Showing cs.CLShow all

8 papers · 1 filter

cs.CL2024

Schema Augmentation for Zero-Shot Domain Adaptation in Dialogue State Tracking

Christopher Richardson, Roshan Sharma, Neeraj Gaur +3

Zero-shot domain adaptation for dialogue state tracking (DST) remains a challenging problem in task-oriented dialogue (TOD) systems, where models must generalize to target domains…

cs.CL2024

Speech vs. Transcript: Does It Matter for Human Annotators in Speech Summarization?

Roshan Sharma, Suwon Shon, Mark Lindsey +3

Reference summaries for abstractive speech summarization require human annotation, which can be performed by listening to an audio recording or by reading textual transcripts of th…

cs.CL2024

On the Evaluation of Speech Foundation Models for Spoken Language Understanding

Siddhant Arora, Ankita Pasad, Chung-Ming Chien +9

The Spoken Language Understanding Evaluation (SLUE) suite of benchmark tasks was recently introduced to address the need for open resources and benchmarking of complex spoken langu…

cs.CL2024

AugSumm: towards generalizable speech summarization using synthetic labels from large language model

Jee-weon Jung, Roshan Sharma, William Chen +2

Abstractive speech summarization (SSUM) aims to generate human-like summaries from speech. Given variations in information captured and phrasing, recordings can be summarized in mu…

cs.CL20234 cited

LoFT: Local Proxy Fine-tuning For Improving Transferability Of Adversarial Attacks Against Large Language Model

Muhammad Ahmed Shah, Roshan Sharma, Hira Dhamyal +10

It has been shown that Large Language Model (LLM) alignments can be circumvented by appending specially crafted attack suffixes with harmful queries to elicit harmful responses. To…

cs.CL2023

UniverSLU: Universal Spoken Language Understanding for Diverse Tasks with Natural Language Instructions

Siddhant Arora, Hayato Futami, Jee-weon Jung +6

Recent studies leverage large language models with multi-tasking capabilities, using natural language prompts to guide the model's behavior and surpassing performance of task-speci…