Papers with feature adaptation

3 papers
Feature-Adaptive and Data-Scalable In-Context Learning (2024.acl-long)

Copied to clipboard

Challenge: In-context learning (ICL) is a popular way to stimulate LLM capabilities for downstream tasks due to context length constraints.
Approach: They propose a feature-adaptive and data-scalable in-context learning framework which leverages task-adaptives to promote inference on the downstream task.
Outcome: The proposed framework outperforms state-of-the-art methods on 10 datasets under different data settings and LLM scale.
Cross-Domain Data Augmentation with Domain-Adaptive Language Modeling for Aspect-Based Sentiment Analysis (2023.acl-long)

Copied to clipboard

Challenge: Cross-domain Aspect-Based Sentiment Analysis (ABSA) aims to identify aspect-sentiment pairs in sentences from a target domain.
Approach: They propose a domain-adaptive language model to generate labeled data from a source domain.
Outcome: The proposed approach outperforms existing methods on ABSA and Aspect Extraction tasks.
A Unified Speaker Adaptation Approach for ASR (2021.emnlp-main)

Copied to clipboard

Challenge: Adapting a model to target speakers requires a lot of compute and may cause catastrophic forgetting to the existing speakers.
Approach: They propose a unified speaker adaptation approach consisting of feature adaptation and model adaptation.
Outcome: The proposed model outperforms baseline models with 20.58% relative WER reduction and surpasses finetuning method by 2.54% on target speaker adaptation.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations