scholarly journals Nurse is Closer to Woman than Surgeon? Mitigating Gender-Biased Proximities in Word Embeddings

2020 ◽  
Vol 8 ◽  
pp. 486-503
Author(s):  
Vaibhav Kumar ◽  
Tenzin Singhay Bhotia ◽  
Vaibhav Kumar ◽  
Tanmoy Chakraborty
Keyword(s):  
Gender Bias ◽  
State Of The Art ◽  
Spatial Arrangement ◽  
Coreference Resolution ◽  
Word Embeddings ◽  
Downstream Application ◽  
The Standard Model ◽  
Gender Based ◽  
Evaluation Metric ◽  
Bias Evaluation

Word embeddings are the standard model for semantic and syntactic representations of words. Unfortunately, these models have been shown to exhibit undesirable word associations resulting from gender, racial, and religious biases. Existing post-processing methods for debiasing word embeddings are unable to mitigate gender bias hidden in the spatial arrangement of word vectors. In this paper, we propose RAN-Debias, a novel gender debiasing methodology that not only eliminates the bias present in a word vector but also alters the spatial distribution of its neighboring vectors, achieving a bias-free setting while maintaining minimal semantic offset. We also propose a new bias evaluation metric, Gender-based Illicit Proximity Estimate (GIPE), which measures the extent of undue proximity in word vectors resulting from the presence of gender-based predilections. Experiments based on a suite of evaluation metrics show that RAN-Debias significantly outperforms the state-of-the-art in reducing proximity bias (GIPE) by at least 42.02%. It also reduces direct bias, adding minimal semantic disturbance, and achieves the best performance in a downstream application task (coreference resolution).

scholarly journals A Causal Inference Method for Reducing Gender Bias in Word Embedding Relations

2020 ◽  
Vol 34 (05) ◽  
pp. 9434-9441
Author(s):  
Zekun Yang ◽  
Juan Feng
Keyword(s):  
Gender Bias ◽  
Language Processing ◽  
State Of The Art ◽  
Word Embedding ◽  
Coreference Resolution ◽  
Word Embeddings ◽  
Inference Method ◽  
Sentence Level ◽  
Statistical Dependency ◽  
And Gender

Word embedding has become essential for natural language processing as it boosts empirical performances of various tasks. However, recent research discovers that gender bias is incorporated in neural word embeddings, and downstream tasks that rely on these biased word vectors also produce gender-biased results. While some word-embedding gender-debiasing methods have been developed, these methods mainly focus on reducing gender bias associated with gender direction and fail to reduce the gender bias presented in word embedding relations. In this paper, we design a causal and simple approach for mitigating gender bias in word vector relation by utilizing the statistical dependency between gender-definition word embeddings and gender-biased word embeddings. Our method attains state-of-the-art results on gender-debiasing tasks, lexical- and sentence-level evaluation tasks, and downstream coreference resolution tasks.

scholarly journals The practical ethics of bias reduction in machine translation: why domain adaptation is better than data debiasing

2021 ◽  
Author(s):  
Marcus Tomalin ◽  
Bill Byrne ◽  
Shauna Concannon ◽  
Danielle Saunders ◽  
Stefanie Ullmann
Keyword(s):  
Machine Translation ◽  
Gender Bias ◽  
Intelligent Systems ◽  
Domain Adaptation ◽  
State Of The Art ◽  
Bias Reduction ◽  
Neural Machine Translation ◽  
Ethical Implications ◽  
Baseline System ◽  
Gender Based

AbstractThis article probes the practical ethical implications of AI system design by reconsidering the important topic of bias in the datasets used to train autonomous intelligent systems. The discussion draws on recent work concerning behaviour-guiding technologies, and it adopts a cautious form of technological utopianism by assuming it is potentially beneficial for society at large if AI systems are designed to be comparatively free from the biases that characterise human behaviour. However, the argument presented here critiques the common well-intentioned requirement that, in order to achieve this, all such datasets must be debiased prior to training. By focusing specifically on gender-bias in Neural Machine Translation (NMT) systems, three automated strategies for the removal of bias are considered – downsampling, upsampling, and counterfactual augmentation – and it is shown that systems trained on datasets debiased using these approaches all achieve general translation performance that is much worse than a baseline system. In addition, most of them also achieve worse performance in relation to metrics that quantify the degree of gender bias in the system outputs. By contrast, it is shown that the technique of domain adaptation can be effectively deployed to debias existing NMT systems after they have been fully trained. This enables them to produce translations that are quantitatively far less biased when analysed using gender-based metrics, but which also achieve state-of-the-art general performance. It is hoped that the discussion presented here will reinvigorate ongoing debates about how and why bias can be most effectively reduced in state-of-the-art AI systems.

Learning emotional word embeddings for sentiment analysis

2021 ◽  
pp. 1-13
Author(s):  
Qingtian Zeng ◽  
Xishi Zhao ◽  
Xiaohui Hu ◽  
Hua Duan ◽  
Zhongying Zhao ◽  
...  
Keyword(s):  
Sentiment Analysis ◽  
Language Processing ◽  
State Of The Art ◽  
Research Problem ◽  
Emotional Word ◽  
Classification Model ◽  
Data Sets ◽  
Word Embeddings ◽  
Real World Data ◽  
Text Documents

Word embeddings have been successfully applied in many natural language processing tasks due to its their effectiveness. However, the state-of-the-art algorithms for learning word representations from large amounts of text documents ignore emotional information, which is a significant research problem that must be addressed. To solve the above problem, we propose an emotional word embedding (EWE) model for sentiment analysis in this paper. This method first applies pre-trained word vectors to represent document features using two different linear weighting methods. Then, the resulting document vectors are input to a classification model and used to train a text sentiment classifier, which is based on a neural network. In this way, the emotional polarity of the text is propagated into the word vectors. The experimental results on three kinds of real-world data sets demonstrate that the proposed EWE model achieves superior performances on text sentiment prediction, text similarity calculation, and word emotional expression tasks compared to other state-of-the-art models.

scholarly journals A Machine Learning Approach to Coreference Resolution of Noun Phrases

2001 ◽  
Vol 27 (4) ◽  
pp. 521-544 ◽  
Author(s):  
Wee Meng Soon ◽  
Hwee Tou Ng ◽  
Daniel Chung Yong Lim
Keyword(s):  
Machine Learning ◽  
Noun Phrase ◽  
State Of The Art ◽  
Noun Phrases ◽  
Learning Approach ◽  
Data Sets ◽  
Coreference Resolution ◽  
Machine Learning Approach

In this paper, we present a learning approach to coreference resolution of noun phrases in unrestricted text. The approach learns from a small, annotated corpus and the task includes resolving not just a certain type of noun phrase (e.g., pronouns) but rather general noun phrases. It also does not restrict the entity types of the noun phrases; that is, coreference is assigned whether they are of “organization,” “person,” or other types. We evaluate our approach on common data sets (namely, the MUC-6 and MUC-7 coreference corpora) and obtain encouraging results, indicating that on the general noun phrase coreference task, the learning approach holds promise and achieves accuracy comparable to that of nonlearning approaches. Our system is the first learning-based system that offers performance comparable to that of state-of-the-art nonlearning systems on these data sets.

scholarly journals Neutralizing Gender Bias in Word Embeddings with Latent Disentanglement and Counterfactual Generation

2020 ◽  
Author(s):  
Seungjae Shin ◽  
Kyungwoo Song ◽  
JoonHo Jang ◽  
Hyemi Kim ◽  
Weonyoung Joo ◽  
...  
Keyword(s):  
Gender Bias ◽  
Word Embeddings

scholarly journals Specializing Word Embeddings (for Parsing) by Information Bottleneck (Extended Abstract)

2020 ◽  
Author(s):  
Xiang Lisa Li ◽  
Jason Eisner
Keyword(s):  
Dimensionality Reduction ◽  
Semantic Information ◽  
State Of The Art ◽  
Word Embedding ◽  
Discrete Version ◽  
Word Embeddings ◽  
Continuous Version ◽  
Continuous Vector ◽  
Information Bottleneck ◽  
Art Performance

Pre-trained word embeddings like ELMo and BERT contain rich syntactic and semantic information, resulting in state-of-the-art performance on various tasks. We propose a very fast variational information bottleneck (VIB) method to nonlinearly compress these embeddings, keeping only the information that helps a discriminative parser. We compress each word embedding to either a discrete tag or a continuous vector. In the discrete version, our automatically compressed tags form an alternative tag set: we show experimentally that our tags capture most of the information in traditional POS tag annotations, but our tag sequences can be parsed more accurately at the same level of tag granularity. In the continuous version, we show experimentally that moderately compressing the word embeddings by our method yields a more accurate parser in 8 of 9 languages, unlike simple dimensionality reduction.

scholarly journals WEFE: The Word Embeddings Fairness Evaluation Framework

2020 ◽  
Author(s):  
Pablo Badilla ◽  
Felipe Bravo-Marquez ◽  
Jorge Pérez
Keyword(s):  
Gender Bias ◽  
Evaluation Framework ◽  
Clear Correlation ◽  
Word Embeddings ◽  
The Relationship

Word embeddings are known to exhibit stereotypical biases towards gender, race, religion, among other criteria. Severa fairness metrics have been proposed in order to automatically quantify these biases. Although all metrics have a similar objective, the relationship between them is by no means clear. Two issues that prevent a clean comparison is that they operate with different inputs, and that their outputs are incompatible with each other. In this paper we propose WEFE, the word embeddings fairness evaluation framework, to encapsulate, evaluate and compare fairness metrics. Our framework needs a list of pre-trained embeddings and a set of fairness criteria, and it is based on checking correlations between fairness rankings induced by these criteria. We conduct a case study showing that rankings produced by existing fairness methods tend to correlate when measuring gender bias. This correlation is considerably less for other biases like race or religion. We also compare the fairness rankings with an embedding benchmark showing that there is no clear correlation between fairness and good performance in downstream tasks.

scholarly journals Two-Level Transformer and Auxiliary Coherence Modeling for Improved Text Segmentation

2020 ◽  
Vol 34 (05) ◽  
pp. 7797-7804
Author(s):  
Goran Glavašš ◽  
Swapna Somasundaran
Keyword(s):  
State Of The Art ◽  
Language Transfer ◽  
Text Segmentation ◽  
Word Embeddings ◽  
Neural Architecture ◽  
Text Coherence ◽  
Sentence Level ◽  
Proposed Model ◽  
Benchmark Datasets ◽  
Cross Lingual

Breaking down the structure of long texts into semantically coherent segments makes the texts more readable and supports downstream applications like summarization and retrieval. Starting from an apparent link between text coherence and segmentation, we introduce a novel supervised model for text segmentation with simple but explicit coherence modeling. Our model – a neural architecture consisting of two hierarchically connected Transformer networks – is a multi-task learning model that couples the sentence-level segmentation objective with the coherence objective that differentiates correct sequences of sentences from corrupt ones. The proposed model, dubbed Coherence-Aware Text Segmentation (CATS), yields state-of-the-art segmentation performance on a collection of benchmark datasets. Furthermore, by coupling CATS with cross-lingual word embeddings, we demonstrate its effectiveness in zero-shot language transfer: it can successfully segment texts in languages unseen in training.

scholarly journals Improved CCG Parsing with Semi-supervised Supertagging

2014 ◽  
Vol 2 ◽  
pp. 327-338 ◽  
Author(s):  
Mike Lewis ◽  
Mark Steedman
Keyword(s):  
Wall Street Journal ◽  
State Of The Art ◽  
Training Data ◽  
Word Embeddings ◽  
Important Goal ◽  
Wall Street ◽  
Feature Sets ◽  
Lexical Categories ◽  
Unlabelled Data ◽  
Pos Tagger

Current supervised parsers are limited by the size of their labelled training data, making improving them with unlabelled data an important goal. We show how a state-of-the-art CCG parser can be enhanced, by predicting lexical categories using unsupervised vector-space embeddings of words. The use of word embeddings enables our model to better generalize from the labelled data, and allows us to accurately assign lexical categories without depending on a POS-tagger. Our approach leads to substantial improvements in dependency parsing results over the standard supervised CCG parser when evaluated on Wall Street Journal (0.8%), Wikipedia (1.8%) and biomedical (3.4%) text. We compare the performance of two recently proposed approaches for classification using a wide variety of word embeddings. We also give a detailed error analysis demonstrating where using embeddings outperforms traditional feature sets, and showing how including POS features can decrease accuracy.

A GLANCE BEYOND THE STANDARD MODEL: LATEST RESULTS FROM THE MEG EXPERIMENT

2014 ◽  
Vol 35 ◽  
pp. 1460390
Author(s):  
SIMEONE DUSSONI
Keyword(s):  
Beyond Standard Model ◽  
Standard Model ◽  
High Intensity ◽  
State Of The Art ◽  
Branching Ratio ◽  
Beyond The Standard Model ◽  
Upper Limit ◽  
The Standard Model ◽  
Key Features ◽  
Very High

The MEG experiment started taking data in 2009 looking for the Standard Model suppressed decay μ → e + γ, which, if observed, can reveal Beyond Standard Model physics. It makes use of state-of-the art detectors optimized for operating in conditions of very high intensity, rejecting as much background as possible. The data taking ended August 2013 and an upgrade R&D is started to push the experimental sensitivity. The present upper limit on the decay Branching Ratio (BR) is presented, obtained with the subset of data from 2009 to 2011 run, together with a description of the key features of the upgraded detector.

Sign in / Sign up

Export Citation Format

Share Document