DetIE: Multilingual Open Information Extraction Inspired by Object Detection
This work addresses efficient and accurate information extraction for NLP applications, offering a novel approach that improves speed and performance, though it is incremental in adapting computer vision techniques to a known bottleneck.
The authors tackled the problem of open information extraction by proposing a single-pass method inspired by object detection, achieving a new state-of-the-art F1 score of 67.7% on CaRB and being 3.35x faster than previous methods, with multilingual versions improving performance by 15% on Re-OIE2016 for Portuguese and Spanish.
State of the art neural methods for open information extraction (OpenIE) usually extract triplets (or tuples) iteratively in an autoregressive or predicate-based manner in order not to produce duplicates. In this work, we propose a different approach to the problem that can be equally or more successful. Namely, we present a novel single-pass method for OpenIE inspired by object detection algorithms from computer vision. We use an order-agnostic loss based on bipartite matching that forces unique predictions and a Transformer-based encoder-only architecture for sequence labeling. The proposed approach is faster and shows superior or similar performance in comparison with state of the art models on standard benchmarks in terms of both quality metrics and inference time. Our model sets the new state of the art performance of 67.7% F1 on CaRB evaluated as OIE2016 while being 3.35x faster at inference than previous state of the art. We also evaluate the multilingual version of our model in the zero-shot setting for two languages and introduce a strategy for generating synthetic multilingual data to fine-tune the model for each specific language. In this setting, we show performance improvement 15% on multilingual Re-OIE2016, reaching 75% F1 for both Portuguese and Spanish languages. Code and models are available at https://github.com/sberbank-ai/DetIE.