A Comparative Analysis of Task-Agnostic Distillation Methods for Compressing Transformer Language Models
- Takuma Udagawa
- Aashka Trivedi
- et al.
- 2023
- EMNLP 2023
Conference paper
Publications
27 results at EMNLP 2023
Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs
- Roi Herzig
- Alon Mendelson
- et al.
- 2023
- EMNLP 2023
Conference paperTaskDiff: A Similarity Metric for Task-Oriented Conversations
- Ankita Bhaumik
- Praveen Venkateswaran
- et al.
- 2023
- EMNLP 2023
Conference paperKnowledge Graph Compression for Enhancing Diverse Commonsense Generation
- Eunjeong Hwang
- Veronika Thost
- et al.
- 2023
- EMNLP 2023
Conference paperPrompting with Pseudo-Code Instructions
- Mayank Mishra
- Prince Kumar
- et al.
- 2023
- EMNLP 2023
Conference paperEnsemble-Instruct: Generating Instruction-Tuning Data with a Heterogeneous Mixture of LMs
- Young-Suk Lee
- Arafat Sultan
- et al.
- 2023
- EMNLP 2023
Conference paperWelcome to the Real World: Efficient, Incremental and Scalable Key Point Analysis
- Lilach Edelstein
- Yoav Kantor
- et al.
- 2023
- EMNLP 2023
Conference paperPROMINET: Prototype-based Multi-View Network for Interpretable Email Response Prediction
- Yuqing Wang
- Prashanth Vijayaraghavan
- et al.
- 2023
- EMNLP 2023
Conference paperDiSTRICT: Dialogue State Tracking with Retriever Driven In-Context Tuning
- Praveen Venkateswaran
- Evelyn Duesterwald
- et al.
- 2023
- EMNLP 2023
Conference paperUDAPDR: Unsupervised Domain Adaptation via LLM Prompting and Distillation of Rerankers
- Jon Saad-Falcon
- Omar Khattab
- et al.
- 2023
- EMNLP 2023
Conference paper