paper-with-me

Papers

Exploring multi-task multi-lingual learning of transformer models for hate speech and offensive speech identification in social media

2021-01-27 · Sudhanshu Mishra, Shivangi Prasad, Shubhanshu Mishra

Hate Speech has become a major content moderation issue for online social media platforms. Given the volume and velocity of online content production, it is impossible to manually moderate hate speech related content on any platform. In this paper we utilize a multi-task and multi-lingual approach based on recently proposed Transformer Neural Networks to solve three sub-tasks for hate speech. These sub-tasks were part of the 2019 shared task on hate speech and offensive content (HASOC) identification in Indo-European languages. We expand on our submission to that competition by utilizing multi-task models which are trained using three approaches, a) multi-task learning with separate task heads, b) back-translation, and c) multi-lingual training. Finally, we investigate the performance of various models and identify instances where the Transformer based models perform differently and better. We show that it is possible to to utilize different combined approaches to obtain models that can generalize easily on different languages and tasks, while trading off slight accuracy (in some cases) for a much reduced inference time compute cost. We open source an updated version of our HASOC 2019 code with the new improvements at https://github.com/socialmediaie/MTML_HateSpeech.

📄 PDF Abstract BibTeX arXiv:2101.11155

Code (1)

socialmediaie/MTML_HateSpeech 공식 구현 pytorch

Tasks

Multi-Task LearningTranslation

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Attention 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

Hinglish to English Machine Translation using Multilingual Transformers

2021-09-01 · RANLP 2021 9 · Vibhav Agarwal, Pooja Rao, Dinesh Babu Jayagopi

Code-Mixed language plays a very important role in communication in multilingual societies and with the recent increase in internet users especially in multilingual societies, the usage of such mixed language has also in…

Machine TranslationTranslation

Exploring Pre-Trained Transformers and Bilingual Transfer Learning for Arabic Coreference Resolution

2021-11-01 · CRAC (ACL) 2021 11 · Bonan Min

In this paper, we develop bilingual transfer learning approaches to improve Arabic coreference resolution by leveraging additional English annotation via bilingual or multilingual pre-trained transformers. We show that b…

coreference-resolutionCoreference ResolutionTransfer Learning

Codewithzichao@DravidianLangTech-EACL2021: Exploring Multilingual Transformers for Offensive Language Identification on Code Mixing Text

2021-04-01 · EACL (DravidianLangTech) 2021 4 · Zichao Li

This paper describes our solution submitted to shared task on Offensive Language Identification in Dravidian Languages. We participated in all three of offensive language identification. In order to address the task, we …

Language Identification

Exploring Anisotropy and Outliers in Multilingual Language Models for Cross-Lingual Semantic Sentence Similarity

2023-06-01 · Katharina Hämmerl, Alina Fastowski, Jindřich Libovický, Alexander Fraser

Previous work has shown that the representations output by contextual language models are more anisotropic than static type embeddings, and typically display outlier dimensions. This seems to be true for both monolingual…

Semantic SimilaritySemantic Textual SimilaritySentenceSentence Similarity

Exploring Routing Strategies for Multilingual Mixture-of-Experts Models

2021-01-01 · Sneha Kudugunta, Yanping Huang, Ankur Bapna, Maxim Krikun 외

Sparsely-Gated Mixture-of-Experts (MoE) has been a successful approach for scaling multilingual translation models to billions of parameters without a proportional increase in training computation. These models, however,…

DecoderMixture-of-ExpertsSentence