# Multilingual Relation Extraction using Compositional Universal Schema

arXiv: https://arxiv.org/abs/1511.06396 · HTML: https://mlsanity.com/paper/1511.06396/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Nov 2015.

## Built on by (most cited first, 11 of 11)

- [Prototypical Representation Learning for Relation Extraction](https://mlsanity.com/paper/2103.11647/) (2021)
- [Benchmarking Commonsense Knowledge Base Population with an Effective Evaluation Dataset](https://mlsanity.com/paper/2109.07679/) (2021)
- [Manual Evaluation Matters: Reviewing Test Protocols of Distantly Supervised Relation Extraction](https://mlsanity.com/paper/2105.09543/) (2021)
- [SENT: Sentence-level Distant Relation Extraction via Negative Training](https://mlsanity.com/paper/2106.11566/) (2021)
- [MultiTACRED: A Multilingual Version of the TAC Relation Extraction Dataset](https://mlsanity.com/paper/2305.04582/) (2023)
- [Extending Multi-Sense Word Embedding to Phrases and Sentences for Unsupervised Semantic Applications](https://mlsanity.com/paper/2103.15330/) (2021)
- [CoRI: Collective Relation Integration with Data Augmentation for Open Information Extraction](https://mlsanity.com/paper/2106.00793/) (2021)
- [Weakly Supervised Reasoning by Neuro-Symbolic Approaches](https://mlsanity.com/paper/2309.13072/) (2023)
- [Multi-facet Universal Schema](https://mlsanity.com/paper/2103.15339/) (2021)
- [Learning Translations via Matrix Completion](https://mlsanity.com/paper/2406.13195/) (2024)
- [BigText-QA: Question Answering over a Large-Scale Hybrid Knowledge Graph](https://mlsanity.com/paper/2212.05798/) (2022)

## Abstract (arXiv)

Universal schema builds a knowledge base (KB) of entities and relations by jointly embedding all relation types from input KBs as well as textual patterns expressing relations from raw text. In most previous applications of universal schema, each textual pattern is represented as a single embedding, preventing generalization to unseen patterns. Recent work employs a neural network to capture patterns' compositional semantics, providing generalization to all possible input text. In response, this paper introduces significant further improvements to the coverage and flexibility of universal schema relation extraction: predictions for entities unseen in training and multilingual transfer learning to domains with no annotation. We evaluate our model through extensive experiments on the English and Spanish TAC KBP benchmark, outperforming the top system from TAC 2013 slot-filling using no handwritten patterns or additional annotation. We also consider a multilingual setting in which English training data entities overlap with the seed KB, but Spanish text does not. Despite having no annotation for Spanish data, we train an accurate predictor, with additional improvements obtained by tying word embeddings across languages. Furthermore, we find that multilingual training improves English relation extraction accuracy. Our approach is thus suited to broad-coverage automated knowledge base construction in a variety of languages and domains.