EMNLP is one of the largest conferences on the topic in the world, as well as one of the most cited in the field of computer science.
USC researchers will present 17 papers at the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP) in Abu Dhabi, December 7-11. EMNLP is one of the largest conferences on the topic in the world, as well as one of the most cited in the field of computer science. The papers presented span from autonomously analyzing recordings of therapy sessions to large language models that can ‘understand’ the reasoning behind popular English phrases.
Learn more about USC at EMNLP:
Eliciting and Understanding Cross-Task Skills with Task-Level Mixture-of-Experts by Qinyuan Ye, Juan Zha and Xiang Ren
ER-Test: Evaluating Explanation Regularization Methods for Language Models by Brihi Joshi, Aaron Z. Chan, Ziyi Liu, Shaoliang Nie, Maziar Sanjabi, Hamed Firooz and Xiang Ren
Generalization Differences between End-to-End and Neuro-Symbolic Vision-Language Reasoning Systems by Wang Zhu, Jesse Thomason and Robin Jia
Disentangling Task Relations for Few-shot Text Classification via Self-Supervised Hierarchical Task Clustering by Juan Zha, Zheng Li, Ying Wei and Yu Zhang
Know Thy Strengths: Comprehensive Dialogue State Tracking Diagnostics by Hyundong Cho, Chinnadhurai Sankar, Christopher Lin, Kaushik Ram Sadagopan, Shahin Shayandeh, Asli Celikyilmaz, Jonathan May and Ahmad Beirami
Sharpness-Aware Minimization with Dynamic Reweighting by Wenxuan Zhou, Fangyu Liu, Huan Zhang and Muhao Chen
Leveraging Open Data and Task Augmentation to Automated Behavioral Coding of Psychotherapy Conversations in Low-Resource Scenarios by Zhuohao Chen, Nikolaos Flemotomos, Zac Imel, David Atkins and Shrikanth Narayanan
Investigating the Benefits of Free-Form Rationales by Jiao Sun, Swabha Swayamdipta, Jonathan May and Xuezhe Ma
Summarization as Indirect Supervision for Relation Extraction by Keming Lu, I-Hung Hsu, Wenxuan Zhou, Mingyu Derek Ma and Muhao Chen
PaCo: Preconditions Attributed to Commonsense Knowledge by Ehsan Qasemi, Filip Ilievski, Muhao Chen and Pedro Szekely
Sequentially Controlled Text Generation by Alexander Spangher, Yao Ming, Xinyu Hua and Nanyun Peng
Segmenting Numerical Substitution Ciphers by Nada Aldarrab and Jonathan May
Machine Translation Robustness to Natural Asemantic Variation by Jacob Bremerman, Xiang Ren and Jonathan May
Salience Allocation as Guidance for Abstractive Summarization by Fei Wang, Kaiqiang Song, Hongming Zhang, Lifeng Jin, Sangwoo Cho, Wenlin Yao, Xiaoyang Wang, Muhao Chen and Dong Yu
Does Your Model Classify Entities Reasonably? Diagnosing and Mitigating Spurious Correlations in Entity Typing by Nan Xu, Fei Wang, Bangzheng Li, Mingtao Dong and Muhao Chen
RobustLR: A Diagnostic Benchmark for Evaluating Logical Robustness of Deductive Reasoners by Soumya Sanyal, Zeyi Liao and Xiang Ren
Reflect, Not Reflex: Inference-Based Common Ground Improves Dialogue Response Quality by Pei Zhou, Hyundong J. Cho, Pegah Jandaghi, Dong-Ho Lee, Bill Yuchen Lin, Jay Pujara and Xiang Ren
Published on December 6th, 2022
Last updated on December 6th, 2022
