DetIE: Multilingual Open Information Extraction Inspired by Object Detection

06/24/2022
by   Michael Vasilkovsky, et al.
0

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 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 multilingual Re-OIE2016, reaching 75 languages. Code and models are available at https://github.com/sberbank-ai/DetIE.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/28/2023

Multilingual Sentence Transformer as A Multilingual Word Aligner

Multilingual pretrained language models (mPLMs) have shown their effecti...
research
04/03/2019

75 Languages, 1 Model: Parsing Universal Dependencies Universally

We present UDify, a multilingual multi-task model capable of accurately ...
research
12/19/2022

BLOOM+1: Adding Language Support to BLOOM for Zero-Shot Prompting

The BLOOM model is a large open-source multilingual language model capab...
research
09/17/2020

Multi^2OIE: Multilingual Open Information Extraction based on Multi-Head Attention with BERT

In this paper, we propose Multi^2OIE, which performs open information ex...
research
03/23/2021

Multilingual Autoregressive Entity Linking

We present mGENRE, a sequence-to-sequence system for the Multilingual En...
research
10/07/2020

OpenIE6: Iterative Grid Labeling and Coordination Analysis for Open Information Extraction

A recent state-of-the-art neural open information extraction (OpenIE) sy...
research
08/27/2022

YOLOX-PAI: An Improved YOLOX, Stronger and Faster than YOLOv6

We develop an all-in-one computer vision toolbox named EasyCV to facilit...

Please sign up or login with your details

Forgot password? Click here to reset