activity
20162025
most citedA Review of Deep Learning Techniques for Speech Processing

22 citations · 37 across the 24 of their papers we have counts for

collaborators
Showing cs.CLShow all

7 papers · 1 filter

cs.CL2023

Task-Adaptive Tokenization: Enhancing Long-Form Text Generation Efficacy in Mental Health and Beyond

Siyang Liu, Naihao Deng, Sahand Sabour +3

We propose task-adaptive tokenization as a way to adapt the generation pipeline to the specifics of a downstream task and enhance long-form generation in mental health. Inspired by…

cs.CL20231 cited

HI-TOM: A Benchmark for Evaluating Higher-Order Theory of Mind Reasoning in Large Language Models

Yinghui He, Yufan Wu, Yilin Jia +3

Theory of Mind (ToM) is the ability to reason about one's own and others' mental states. ToM plays a critical role in the development of intelligence, language understanding, and c…

cs.CL20231 cited

Psychologically-Inspired Causal Prompts

Zhiheng Lyu, Zhijing Jin, Justus Mattern +3

NLP datasets are richer than just input-output pairs; rather, they carry causal relations between the input and output variables. In this work, we take sentiment classification as…

cs.CL20231 cited

Evaluating Parameter-Efficient Transfer Learning Approaches on SURE Benchmark for Speech Understanding

Yingting Li, Ambuj Mehrish, Shuai Zhao +5

Fine-tuning is widely used as the default algorithm for transfer learning from pre-trained models. Parameter inefficiency can however arise when, during transfer learning, all the…

cs.CL2022

Using Paraphrases to Study Properties of Contextual Embeddings

Laura Burdick, Jonathan K. Kummerfeld, Rada Mihalcea

We use paraphrases as a unique source of data to analyze contextualized embeddings, with a particular focus on BERT. Because paraphrases naturally encode consistent word and phrase…

cs.CL20161 cited

Predicting the Industry of Users on Social Media

Konstantinos Pappas, Rada Mihalcea

Automatic profiling of social media users is an important task for supporting a multitude of downstream applications. While a number of studies have used social media content to ex…