TY - JOUR

T1 - A Neighborhood Framework for Resource-Lean Content Flagging

AU - Sarwar, Sheikh Muhammad

AU - Zlatkova, Dimitrina

AU - Hardalov, Momchil

AU - Dinkov, Yoan

AU - Augenstein, Isabelle

AU - Nakov, Preslav

N1 - Publisher Copyright: © 2022 Association for Computational Linguistics. Distributed under a CC-BY 4.0 license.

PY - 2022

Y1 - 2022

N2 - We propose a novel framework for cross-lingual content flagging with limited target-language data, which significantly outperforms prior work in terms of predictive performance. The framework is based on a nearest-neighbor architecture. It is a modern instantiation of the vanilla k-nearest neighbor model, as we use Transformer representations in all its components. Our framework can adapt to new source-language instances, without the need to be retrained from scratch. Unlike prior work on neighborhood-based approaches, we encode the neighborhood information based on query– neighbor interactions. We propose two encoding schemes and we show their effectiveness using both qualitative and quantitative analysis. Our evaluation results on eight languages from two different datasets for abusive language detection show sizable improvements of up to 9.5 F1 points absolute (for Italian) over strong baselines. On average, we achieve 3.6 absolute F1 points of improvement for the three languages in the Jigsaw Multilingual dataset and 2.14 points for the WUL dataset.

AB - We propose a novel framework for cross-lingual content flagging with limited target-language data, which significantly outperforms prior work in terms of predictive performance. The framework is based on a nearest-neighbor architecture. It is a modern instantiation of the vanilla k-nearest neighbor model, as we use Transformer representations in all its components. Our framework can adapt to new source-language instances, without the need to be retrained from scratch. Unlike prior work on neighborhood-based approaches, we encode the neighborhood information based on query– neighbor interactions. We propose two encoding schemes and we show their effectiveness using both qualitative and quantitative analysis. Our evaluation results on eight languages from two different datasets for abusive language detection show sizable improvements of up to 9.5 F1 points absolute (for Italian) over strong baselines. On average, we achieve 3.6 absolute F1 points of improvement for the three languages in the Jigsaw Multilingual dataset and 2.14 points for the WUL dataset.

U2 - 10.1162/tacl_a_00472

DO - 10.1162/tacl_a_00472

M3 - Journal article

AN - SCOPUS:85125809351

VL - 10

SP - 484

EP - 502

JO - Transactions of the Association for Computational Linguistics

JF - Transactions of the Association for Computational Linguistics

SN - 2307-387X

ER -