# Multi-facet Universal Schema

arXiv: https://arxiv.org/abs/2103.15339 · HTML: https://mlsanity.com/paper/2103.15339/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 41 references that are in the map.
- First posted on arXiv 29 Mar 2021.

## Builds on (most cited first, 15 of 15)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Matching the Blanks: Distributional Similarity for Relation Learning](https://mlsanity.com/paper/1906.03158/) (2019)
- [More Data, More Relations, More Context and More Openness: A Review and Outlook for Relation Extraction](https://mlsanity.com/paper/2004.03186/) (2020)
- [Simultaneously Self-Attending to All Mentions for Full-Abstract Biological Relation Extraction](https://mlsanity.com/paper/1802.10569/) (2018)
- [Efficient Non-parametric Estimation of Multiple Embeddings per Word in Vector Space](https://mlsanity.com/paper/1504.06654/) (2015)
- [Question Answering on Knowledge Bases and Text using Universal Schema and Memory Networks](https://mlsanity.com/paper/1704.08384/) (2017)
- [Hypernyms under Siege: Linguistically-motivated Artillery for Hypernymy Detection](https://mlsanity.com/paper/1612.04460/) (2016)
- [Multimodal Word Distributions](https://mlsanity.com/paper/1704.08424/) (2017)
- [Multilingual Relation Extraction using Compositional Universal Schema](https://mlsanity.com/paper/1511.06396/) (2015)
- [OpenKI: Integrating Open Information Extraction and Knowledge Bases with Relation Inference](https://mlsanity.com/paper/1904.12606/) (2019)
- [A Data-driven Approach for Noise Reduction in Distantly Supervised Biomedical Relation Extraction](https://mlsanity.com/paper/2005.12565/) (2020)
- [Generalizing to Unseen Entities and Entity Pairs with Row-less Universal Schema](https://mlsanity.com/paper/1606.05804/) (2016)
- [Global Relation Embedding for Relation Extraction](https://mlsanity.com/paper/1704.05958/) (2017)

## Built on by (most cited first, 1 of 1)

- [On the Theoretical Limitations of Embedding-Based Retrieval](https://mlsanity.com/paper/2508.21038/) (2025)

## Abstract (arXiv)

Universal schema (USchema) assumes that two sentence patterns that share the same entity pairs are similar to each other. This assumption is widely adopted for solving various types of relation extraction (RE) tasks. Nevertheless, each sentence pattern could contain multiple facets, and not every facet is similar to all the facets of another sentence pattern co-occurring with the same entity pair. To address the violation of the USchema assumption, we propose multi-facet universal schema that uses a neural model to represent each sentence pattern as multiple facet embeddings and encourage one of these facet embeddings to be close to that of another sentence pattern if they co-occur with the same entity pair. In our experiments, we demonstrate that multi-facet embeddings significantly outperform their single-facet embedding counterpart, compositional universal schema (CUSchema) (Verga et al., 2016), in distantly supervised relation extraction tasks. Moreover, we can also use multiple embeddings to detect the entailment relation between two sentence patterns when no manual label is available.