Papers with context-aware approach
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. |