# Event-Centric Query Expansion in Web Search

arXiv: https://arxiv.org/abs/2305.19019 · HTML: https://mlsanity.com/paper/2305.19019/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 46 references that are in the map.
- First posted on arXiv 30 May 2023.

## Builds on (most cited first, 22 of 22)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [mT5: A massively multilingual pre-trained text-to-text transformer](https://mlsanity.com/paper/2010.11934/) (2020)
- [Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval](https://mlsanity.com/paper/2007.00808/) (2020)
- [Representation Degeneration Problem in Training Natural Language Generation Models](https://mlsanity.com/paper/1907.12009/) (2019)
- [Unified Structure Generation for Universal Information Extraction](https://mlsanity.com/paper/2203.12277/) (2022)
- [Learning Dense Representations for Entity Retrieval](https://mlsanity.com/paper/1909.10506/) (2019)
- [Pre-trained Language Model based Ranking in Baidu Search](https://mlsanity.com/paper/2105.11108/) (2021)
- [N-LTP: An Open-source Neural Language Technology Platform for Chinese](https://mlsanity.com/paper/2009.11616/) (2020)
- [QUILL: Query Intent with Large Language Models using Retrieval Augmentation and Multi-stage Distillation](https://mlsanity.com/paper/2210.15718/) (2022)
- [Query Expansion with Locally-Trained Word Embeddings](https://mlsanity.com/paper/1605.07891/) (2016)
- [Title2Event: Benchmarking Open Event Extraction with a Large-scale Chinese Title Dataset](https://mlsanity.com/paper/2211.00869/) (2022)
- [Relevance-based Word Embedding](https://mlsanity.com/paper/1705.03556/) (2017)
- [Mask-then-Fill: A Flexible and Effective Data Augmentation Framework for Event Extraction](https://mlsanity.com/paper/2301.02427/) (2023)
- [Query Understanding via Intent Description Generation](https://mlsanity.com/paper/2008.10889/) (2020)
- [A new approach for query expansion using Wikipedia and WordNet](https://mlsanity.com/paper/1901.10197/) (2019)
- [Event-Driven Query Expansion](https://mlsanity.com/paper/2012.12065/) (2020)
- [NxtPost: User to Post Recommendations in Facebook Groups](https://mlsanity.com/paper/2202.03645/) (2022)
- [Query Expansion and Entity Weighting for Query Reformulation Retrieval in Voice Assistant Systems](https://mlsanity.com/paper/2202.13869/) (2022)

## Built on by (most cited first, 2 of 2)

- [Event-driven Real-time Retrieval in Web Search](https://mlsanity.com/paper/2312.00372/) (2023)
- [Event-enhanced Retrieval in Real-time Search](https://mlsanity.com/paper/2404.05989/) (2024)

## Abstract (arXiv)

In search engines, query expansion (QE) is a crucial technique to improve search experience. Previous studies often rely on long-term search log mining, which leads to slow updates and is sub-optimal for time-sensitive news searches. In this work, we present Event-Centric Query Expansion (EQE), a novel QE system that addresses these issues by mining the best expansion from a significant amount of potential events rapidly and accurately. This system consists of four stages, i.e., event collection, event reformulation, semantic retrieval and online ranking. Specifically, we first collect and filter news headlines from websites. Then we propose a generation model that incorporates contrastive learning and prompt-tuning techniques to reformulate these headlines to concise candidates. Additionally, we fine-tune a dual-tower semantic model to function as an encoder for event retrieval and explore a two-stage contrastive training approach to enhance the accuracy of event retrieval. Finally, we rank the retrieved events and select the optimal one as QE, which is then used to improve the retrieval of event-related documents. Through offline analysis and online A/B testing, we observe that the EQE system significantly improves many metrics compared to the baseline. The system has been deployed in Tencent QQ Browser Search and served hundreds of millions of users. The dataset and baseline codes are available at https://open-event-hub.github.io/eqe .