The Geometry of Distributed Representations for Better Alignment, Attenuated Bias, and Improved Interpretability
arXiv:2011.12465
Abstract
High-dimensional representations for words, text, images, knowledge graphs and other structured data are commonly used in different paradigms of machine learning and data mining. These representations have different degrees of interpretability, with efficient distributed representations coming at the cost of the loss of feature to dimension mapping. This implies that there is obfuscation in the way concepts are captured in these embedding spaces. Its effects are seen in many representations and tasks, one particularly problematic one being in language representations where the societal biases, learned from underlying data, are captured and occluded in unknown dimensions and subspaces. As a result, invalid associations (such as different races and their association with a polar notion of good versus bad) are made and propagated by the representations, leading to unfair outcomes in different tasks where they are used. This work addresses some of these problems pertaining to the transparency and interpretability of such representations. A primary focus is the detection, quantification, and mitigation of socially biased associations in language representation.
arXiv commentPhD thesis, University of Utah (2020)
References in corpus (18)
- Efficient Estimation of Word Representations in Vector Space
- Distributed Representations of Words and Phrases and their Compositionality
- Semantics derived automatically from language corpora contain human-like biases
- NLTK: The Natural Language Toolkit
- Bidirectional Attention Flow for Machine Comprehension
- Exploiting Similarities among Languages for Machine Translation
- Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings
- Enriching Word Vectors with Subword Information
- A Comprehensive Survey of Graph Embedding: Problems, Techniques and Applications
- Women also Snowboard: Overcoming Bias in Captioning Models
- Attenuating Bias in Word Vectors
- Assessing Social and Intersectional Biases in Contextualized Word Representations
- Multilingual Distributed Representations without Word Alignment
- Mitigating Gender Bias in Natural Language Processing: Literature Review
- Neutralizing Gender Bias in Word Embedding with Latent Disentanglement and Counterfactual Generation
- Gender Bias in Multilingual Embeddings and Cross-Lingual Transfer
- Towards a Flexible Embedding Learning Framework
- Consistent Alignment of Word Embedding Models