 Vesper: A Compact and Effective Pretrained Model for Speech Emotion
RecognitionIEEE Transactions on Affective Computing (IEEE Trans. Affective Comput.), 2023 |
 Once is Enough: A Light-Weight Cross-Attention for Fast Sentence Pair
ModelingConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 |
 RAAT: Relation-Augmented Attention Transformer for Relation Modeling in
Document-Level Event ExtractionNorth American Chapter of the Association for Computational Linguistics (NAACL), 2022 |
 Differentially Private Model CompressionNeural Information Processing Systems (NeurIPS), 2022 |
 Exploring Extreme Parameter Compression for Pre-trained Language ModelsInternational Conference on Learning Representations (ICLR), 2022 |
 Transkimmer: Transformer Learns to Layer-wise SkimAnnual Meeting of the Association for Computational Linguistics (ACL), 2022 |
 TR-BERT: Dynamic Token Reduction for Accelerating BERT InferenceNorth American Chapter of the Association for Computational Linguistics (NAACL), 2021 |
 Retrieval-Free Knowledge-Grounded Dialogue Response Generation with
AdaptersWorkshop on Document-grounded Dialogue and Conversational Question Answering (DialDoc), 2021 |
 Probing Classifiers: Promises, Shortcomings, and AdvancesInternational Conference on Computational Logic (ICCL), 2021 |
 Modeling Context in Answer Sentence Selection Systems on a Latency
BudgetConference of the European Chapter of the Association for Computational Linguistics (EACL), 2021 |
 Learning Dense Representations of Phrases at ScaleAnnual Meeting of the Association for Computational Linguistics (ACL), 2020 |
 ReadOnce Transformers: Reusable Representations of Text for TransformersAnnual Meeting of the Association for Computational Linguistics (ACL), 2020 |
 Which *BERT? A Survey Organizing Contextualized EncodersConference on Empirical Methods in Natural Language Processing (EMNLP), 2020 |
 Compressing Large-Scale Transformer-Based Models: A Case Study on BERTTransactions of the Association for Computational Linguistics (TACL), 2020 |
