# Seq2RDF: An end-to-end application for deriving Triples from Natural Language Text

arXiv: https://arxiv.org/abs/1807.01763 · HTML: https://mlsanity.com/paper/1807.01763/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Jul 2018.

## Built on by (most cited first, 7 of 7)

- [GenIE: Generative Information Extraction](https://mlsanity.com/paper/2112.08340/) (2021)
- [Distantly Supervised Relation Extraction with Sentence Reconstruction and Knowledge Base Priors](https://mlsanity.com/paper/2104.08225/) (2021)
- [HySPA: Hybrid Span Generation for Scalable Text-to-Graph Extraction](https://mlsanity.com/paper/2106.15838/) (2021)
- [Better Call the Plumber: Orchestrating Dynamic Information Extraction Pipelines](https://mlsanity.com/paper/2102.10966/) (2021)
- [Extracting Relational Triples Based on Graph Recursive Neural Network via Dynamic Feedback Forest Algorithm](https://mlsanity.com/paper/2308.11411/) (2023)
- [Autoregressive Language Models for Knowledge Base Population: A case study in the space mission domain](https://mlsanity.com/paper/2503.18502/) (2025)
- [DISCIE -- Discriminative Closed Information Extraction](https://mlsanity.com/paper/2506.16348/) (2025)

## Abstract (arXiv)

We present an end-to-end approach that takes unstructured textual input and generates structured output compliant with a given vocabulary. Inspired by recent successes in neural machine translation, we treat the triples within a given knowledge graph as an independent graph language and propose an encoder-decoder framework with an attention mechanism that leverages knowledge graph embeddings. Our model learns the mapping from natural language text to triple representation in the form of subject-predicate-object using the selected knowledge graph vocabulary. Experiments on three different data sets show that we achieve competitive F1-Measures over the baselines using our simple yet effective approach. A demo video is included.