Papers by Elizabeth Belding

6 papers
Mitigating Gender Bias in Natural Language Processing: Literature Review (P19-1)

Copied to clipboard

Challenge: NLP models propagate and may even amplify gender bias found in text corpora . methods to mitigate gender bias in NLP are relatively nascent .
Approach: They propose to analyze gender bias based on four forms of representation bias and discuss the advantages and drawbacks of existing gender debiasing methods.
Outcome: The proposed methods are based on four forms of representation bias and have advantages and drawbacks.
Learning to Decipher Hate Symbols (N19-1)

Copied to clipboard

Challenge: Existing computational models of hate speech focus on a binary or multiclass classification task . a recent study shows an alarming 4.6% increase in hate speech in 2016 .
Approach: They propose a task of deciphering hate symbols using the Urban Dictionary . they propose ciphers using Sequence-to-Sequence models and a Variational Decipher .
Outcome: The proposed model can crack hate symbols based on context and generalize better to unseen symbols in a more challenging testing setting.
Towards Understanding Gender Bias in Relation Extraction (2020.acl-main)

Copied to clipboard

Challenge: Existing bias mitigation techniques have a negative effect on NRE, a study finds .
Approach: They create a dataset to analyze gender bias in relation extraction systems . they find that existing bias mitigation techniques have a negative effect on NRE .
Outcome: The proposed dataset analyzes gender bias in relation extraction systems using a 10% human annotated test set.
Leveraging Intra-User and Inter-User Representation Learning for Automated Hate Speech Detection (N18-2)

Copied to clipboard

Challenge: Existing methods that focus on a single tweet as input are likely to yield high false positive and negative rates.
Approach: They propose a model that leverages intra-user and inter-user representation learning to improve hate speech detection on Twitter by suppressing the noise in a single Tweet.
Outcome: The proposed model significantly improves the f-score of a strong bidirectional LSTM model by 10.1%.
Hierarchical CVAE for Fine-Grained Hate Speech Classification (D18-1)

Copied to clipboard

Challenge: Existing work on automated hate speech detection focuses on binary classification or on differentiating among a small set of categories.
Approach: They propose a method to discriminate among 40 hate groups of 13 different hate group categories.
Outcome: The proposed method outperforms discriminative models on a fine-grained hate speech classification task.
A Benchmark Dataset for Learning to Intervene in Online Hate Speech (D19-1)

Copied to clipboard

Challenge: Existing methods to detect online hate speech ignore conversational context . generative hate speech intervention is a novel approach to counter online hate .
Approach: They propose a task where generative hate speech intervention generates responses to intervene during online conversations that contain hate speech.
Outcome: The proposed method can detect and block hate speech and discourage it . it can also generate responses written by Mechanical Turk workers .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations