# Entity-Centric Query Refinement

arXiv: https://arxiv.org/abs/2204.00743 · HTML: https://mlsanity.com/paper/2204.00743/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 42 references that are in the map.
- First posted on arXiv 2 Apr 2022.

## Builds on (most cited first, 10 of 10)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [AmbigQA: Answering Ambiguous Open-domain Questions](https://mlsanity.com/paper/2004.10645/) (2020)
- [Open-Domain Question Answering Goes Conversational via Question Rewriting](https://mlsanity.com/paper/2010.04898/) (2020)
- [Asking Clarifying Questions in Open-Domain Information-Seeking Conversations](https://mlsanity.com/paper/1907.06554/) (2019)
- [Entities as Experts: Sparse Memory Access with Entity Supervision](https://mlsanity.com/paper/2004.07202/) (2020)
- [A Hierarchical Recurrent Encoder-Decoder For Generative Context-Aware Query Suggestion](https://mlsanity.com/paper/1507.02221/) (2015)
- [Learning to Attend, Copy, and Generate for Session-Based Query Suggestion](https://mlsanity.com/paper/1708.03418/) (2017)
- [Learning Cross-Context Entity Representations from Text](https://mlsanity.com/paper/2001.03765/) (2020)
- [IntenT5: Search Result Diversification using Causal Language Models](https://mlsanity.com/paper/2108.04026/) (2021)
- [TableQnA: Answering List Intent Queries With Web Tables](https://mlsanity.com/paper/2001.04828/) (2020)

## Abstract (arXiv)

We introduce the task of entity-centric query refinement. Given an input query whose answer is a (potentially large) collection of entities, the task output is a small set of query refinements meant to assist the user in efficient domain exploration and entity discovery. We propose a method to create a training dataset for this task. For a given input query, we use an existing knowledge base taxonomy as a source of candidate query refinements, and choose a final set of refinements from among these candidates using a search procedure designed to partition the set of entities answering the input query. We demonstrate that our approach identifies refinement sets which human annotators judge to be interesting, comprehensive, and non-redundant. In addition, we find that a text generation model trained on our newly-constructed dataset is able to offer refinements for novel queries not covered by an existing taxonomy. Our code and data are available at https://github.com/google-research/language/tree/master/language/qresp.