A Neighbourhood Framework for Resource-Lean Content Flagging
Not on the map. Why?
Abstract (arXiv)
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-neighbour architecture. It is a modern instantiation of the vanilla k-nearest neighbour 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 neighbourhood-based approaches, we encode the neighbourhood information based on query--neighbour 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.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 40 of its 71 references that are in the map. First posted on arXiv 31 Mar 2021.
Builds on
40 of 71 references.
References · 40
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
- 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
- 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,243
- 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
- 2017Billion-scale similarity search with GPUscited by 2,477
- 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
- 2020MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformerscited by 1,414
- 2019Cross-lingual Language Model Pretrainingcited by 1,088
- 2016Bag of Tricks for Efficient Text Classificationcited by 869
- 2019Generalization through Memorization: Nearest Neighbor Language Modelscited by 788
- 2019How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddingscited by 770
28 more
- 2017Dynamic Routing Between Capsulescited by 689
- 2020Language-agnostic BERT Sentence Embeddingcited by 621
- 2020Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillationcited by 591
- 2018Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyondcited by 434
- 2017A Structured Self-attentive Sentence Embeddingcited by 318
- 2019Predicting the Type and Target of Offensive Posts in Social Mediacited by 268
- 2016Ex Machina: Personal Attacks Seen at Scalecited by 208
- 2019Racial Bias in Hate Speech and Abusive Language Detection Datasetscited by 208
- 2019SemEval-2019 Task 6: Identifying and Categorizing Offensive Language in Social Media (OffensEval)cited by 206
- 2020SemEval-2020 Task 12: Multilingual Offensive Language Identification in Social Media (OffensEval 2020)cited by 138
- 2019Multilingual and Multi-Aspect Hate Speech Analysiscited by 133
- 2017A Deep Relevance Matching Model for Ad-hoc Retrievalcited by 126
- 2019TANDA: Transfer and Adapt Pre-Trained Transformer Models for Answer Sentence Selectioncited by 74
- 2020Multilingual Offensive Language Identification with Cross-lingual Embeddingscited by 71
- 2017Learning to Remember Rare Eventscited by 63
- 2020Augmenting Transformers with KNN-Based Composite Memory for Dialoguecited by 53
- 2020SOLID: A Large-Scale Semi-Supervised Dataset for Offensive Language Identificationcited by 53
- 2019A Just and Comprehensive Strategy for Using NLP to Address Online Abusecited by 49
- 2020Inducing Language-Agnostic Multilingual Representationscited by 48
- 2018Learning Cross-Lingual Sentence Representations via a Multi-task Dual-Encoder Modelcited by 46
- 2020Toxic Language Detection in Social Media for Brazilian Portuguese: New Dataset and Multilingual Analysiscited by 45
- 2020Stereotypical Bias Removal for Hate Speech Detection Task using Knowledge-based Generalizationscited by 40
- 2018Deep Learning for Detecting Cyberbullying Across Multiple Social Media Platformscited by 37
- 2020BERT-kNN: Adding a kNN Search Component to Pretrained Language Models for Better QAcited by 36
- 2018Challenges in Discriminating Profanity from Hate Speechcited by 23
- 2020Cross-lingual Zero- and Few-shot Hate Speech Detection Utilising Frozen Transformer Language Models and AXELcited by 23
- 2018Convolutional Neural Networks for Toxic Comment Classificationcited by 21
- 2018Interpreting Neural Networks With Nearest Neighborscited by 18
Built on by
Citing papers per year: 2021: 2; 2022: 1.
3 papers.