A New Generation of Perspective API: Efficient Multilingual Character-level Transformers

02/22/2022
by   Alyssa Lees, et al.
0

On the world wide web, toxic content detectors are a crucial line of defense against potentially hateful and offensive messages. As such, building highly effective classifiers that enable a safer internet is an important research area. Moreover, the web is a highly multilingual, cross-cultural community that develops its own lingo over time. As such, it is crucial to develop models that are effective across a diverse range of languages, usages, and styles. In this paper, we present the fundamentals behind the next version of the Perspective API from Google Jigsaw. At the heart of the approach is a single multilingual token-free Charformer model that is applicable across a range of languages, domains, and tasks. We demonstrate that by forgoing static vocabularies, we gain flexibility across a variety of settings. We additionally outline the techniques employed to make such a byte-level model efficient and feasible for productionization. Through extensive experiments on multilingual toxic comment classification benchmarks derived from real API traffic and evaluation on an array of code-switching, covert toxicity, emoji-based hate, human-readable obfuscation, distribution shift, and bias evaluation settings, we show that our proposed approach outperforms strong baselines. Finally, we present our findings from deploying this system in production.

READ FULL TEXT
research
09/27/2022

mRobust04: A Multilingual Version of the TREC Robust 2004 Benchmark

Robust 2004 is an information retrieval benchmark whose large number of ...
research
04/19/2021

Operationalizing a National Digital Library: The Case for a Norwegian Transformer Model

In this work, we show the process of building a large-scale training set...
research
03/24/2023

Improving API Documentation Comprehensibility via Continuous Optimization and Multilingual SDK

Optimizing and maintaining up-to-date API documentation is a challenging...
research
11/11/2022

MINION: a Large-Scale and Diverse Dataset for Multilingual Event Detection

Event Detection (ED) is the task of identifying and classifying trigger ...
research
04/25/2017

280 Birds with One Stone: Inducing Multilingual Taxonomies from Wikipedia using Character-level Classification

We propose a simple, yet effective, approach towards inducing multilingu...
research
03/15/2023

PRESTO: A Multilingual Dataset for Parsing Realistic Task-Oriented Dialogs

Research interest in task-oriented dialogs has increased as systems such...
research
02/18/2021

MUDES: Multilingual Detection of Offensive Spans

The interest in offensive content identification in social media has gro...

Please sign up or login with your details

Forgot password? Click here to reset