Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userMitigating Biases in Toxic Language Detection through Invariant Rationalization
التخفيف من التحيزات في الكشف عن اللغة السامة من خلال الترشيد الثابت
174
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
يلعب الكشف التلقائي باللغة السامة دورا أساسيا في حماية مستخدمي الوسائط الاجتماعية، وخاصة مجموعات الأقليات، من الإساءة اللفظية.ومع ذلك، فإن التحيزات تجاه بعض الصفات، بما في ذلك النوع الاجتماعي والعرق واللهجة، موجودة في معظم مجموعات البيانات التدريبية للكشف عن السمية.تحيزات تجعل النماذج المستفادة غير عادلة ويمكن أن تؤدي إلى تفاقم تهميش الناس.بالنظر إلى أن طرق الدخل الحالية لمهام فهم اللغة الطبيعية العامة لا يمكن أن تخفف بشكل فعال من التحيزات في كاشفات السمية، نقترح استخدام الترشيد الثابت (invrat)، وهو إطار نظري للعبة يتكون من مولد الأساس المنطقي والتوقع، لاستبعاد الزائفةالارتباط ببعض الأنماط النحوية (على سبيل المثال، يذكر الهوية، لهجة) إلى تسميات السمية.نظرا لإيذاء أن طريقتنا تنتج معدل إيجابي كاذب أقل في كل من الصفات المعجمية واللهائية من أساليب الدخل السابقة.
Automatic detection of toxic language plays an essential role in protecting social media users, especially minority groups, from verbal abuse. However, biases toward some attributes, including gender, race, and dialect, exist in most training datasets for toxicity detection. The biases make the learned models unfair and can even exacerbate the marginalization of people. Considering that current debiasing methods for general natural language understanding tasks cannot effectively mitigate the biases in the toxicity detectors, we propose to use invariant rationalization (InvRat), a game-theoretic framework consisting of a rationale generator and a predictor, to rule out the spurious correlation of certain syntactic patterns (e.g., identity mentions, dialect) to toxicity labels. We empirically show that our method yields lower false positive rate in both lexical and dialectal attributes than previous debiasing methods.
References used
https://aclanthology.org/
rate research
Read More
Biases continue to be prevalent in modern text and media, especially subjective bias -- a special type of bias that introduces improper attitudes or presents a statement with the presupposition of truth. To tackle the problem of detecting and further
mitigating subjective bias, we introduce a manually annotated parallel corpus WIKIBIAS with more than 4,000 sentence pairs from Wikipedia edits. This corpus contains annotations towards both sentence-level bias types and token-level biased segments. We present systematic analyses of our dataset and results achieved by a set of state-of-the-art baselines in terms of three tasks: bias classification, tagging biased segments, and neutralizing biased text. We find that current models still struggle with detecting multi-span biases despite their reasonable performances, suggesting that our dataset can serve as a useful research benchmark. We also demonstrate that models trained on our dataset can generalize well to multiple domains such as news and political speeches.
With the rapid growth in technology, social media activity has seen a boom across all age groups. It is humanly impossible to check all the tweets, comments and status manually whether they follow proper community guidelines. A lot of toxicity is reg
ularly posted on these social media platforms. This research aims to find toxic words in a sentence so that a healthy social community is built across the globe and the users receive censored content with specific warnings and facts. To solve this challenging problem, authors have combined concepts of Linked List for pre-processing and then used the idea of stacked embeddings like BERT Embeddings, Flair Embeddings and Word2Vec on the flairNLP framework to get the desired results. F1 metric was used to evaluate the model. The authors were able to produce a 0.74 F1 score on their test set.
This paper explores three simple data manipulation techniques (synthesis, augmentation, curriculum) for improving abstractive summarization models without the need for any additional data. We introduce a method of data synthesis with paraphrasing, a
data augmentation technique with sample mixing, and curriculum learning with two new difficulty metrics based on specificity and abstractiveness. We conduct experiments to show that these three techniques can help improve abstractive summarization across two summarization models and two different small datasets. Furthermore, we show that these techniques can improve performance when applied in isolation and when combined.
We generalize the notion of measuring social biases in word embeddings to visually grounded word embeddings. Biases are present in grounded embeddings, and indeed seem to be equally or more significant than for ungrounded embeddings. This is despite
the fact that vision and language can suffer from different biases, which one might hope could attenuate the biases in both. Multiple ways exist to generalize metrics measuring bias in word embeddings to this new setting. We introduce the space of generalizations (Grounded-WEAT and Grounded-SEAT) and demonstrate that three generalizations answer different yet important questions about how biases, language, and vision interact. These metrics are used on a new dataset, the first for grounded bias, created by augmenting standard linguistic bias benchmarks with 10,228 images from COCO, Conceptual Captions, and Google Images. Dataset construction is challenging because vision datasets are themselves very biased. The presence of these biases in systems will begin to have real-world consequences as they are deployed, making carefully measuring bias and then mitigating it critical to building a fair society.
With the ever-increasing availability of digital information, toxic content is also on the rise. Therefore, the detection of this type of language is of paramount importance. We tackle this problem utilizing a combination of a state-of-the-art pre-tr
ained language model (CharacterBERT) and a traditional bag-of-words technique. Since the content is full of toxic words that have not been written according to their dictionary spelling, attendance to individual characters is crucial. Therefore, we use CharacterBERT to extract features based on the word characters. It consists of a CharacterCNN module that learns character embeddings from the context. These are, then, fed into the well-known BERT architecture. The bag-of-words method, on the other hand, further improves upon that by making sure that some frequently used toxic words get labeled accordingly. With a ∼4 percent difference from the first team, our system ranked 36 th in the competition. The code is available for further research and reproduction of the results.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
