Papers with context-aware approach

3 papers
Improving Retrieval in Sponsored Search by Leveraging Query Context Signals (2024.emnlp-industry)

Copied to clipboard

Challenge: Existing models for retrieving relevant bid keywords fail to capture nuanced user intent . a new approach to enhance query understanding uses contextual signals .
Approach: They propose a method to augment queries with rich contextual signals from web search results and large language models stored in an online cache.
Outcome: The proposed approach outperforms context-free models in retrieving relevant bid keywords for user queries.
Zero-Shot Contextual Embeddings via Offline Synthetic Corpus Generation (2025.findings-emnlp)

Copied to clipboard

Challenge: Context-aware embedding methods boost retrieval accuracy by conditioning on corpus statistics extracted from neighboring documents.
Approach: They propose a zero-shot contextual adaptation framework that replaces real corpus access with a one-time offline synthesis of a compact proxy.
Outcome: The proposed framework replaces real corpus access with offline synthesis of a compact proxy.
Improving Multi-Criteria Chinese Word Segmentation through Learning Sentence Representation (2023.findings-emnlp)

Copied to clipboard

Challenge: Recent Chinese word segmentation models tend to learn the segmentation knowledge through in-vocabulary words rather than understanding the meaning of the entire context.
Approach: They propose a context-aware approach that incorporates unsupervised sentence representation learning over different dropout masks into the multi-criteria training framework.
Outcome: The proposed approach achieves state-of-the-art (SoTA) performance on six of the nine CWS benchmark datasets and out-of vocabulary (OOV) recalls for eight of nine.

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