Related papers: Learning Gender-Neutral Word Embeddings
In this paper, we quantify, analyze and mitigate gender bias exhibited in ELMo's contextualized word vectors. First, we conduct several intrinsic analyses and find that (1) training data for ELMo contains significantly more male than female…
As Natural Language Processing (NLP) and Machine Learning (ML) tools rise in popularity, it becomes increasingly vital to recognize the role they play in shaping societal biases and stereotypes. Although NLP models have shown success in…
Linguistic similarity is multi-faceted. For instance, two words may be similar with respect to semantics, syntax, or morphology inter alia. Continuous word-embeddings have been shown to capture most of these shades of similarity to some…
We examine whether neural natural language processing (NLP) systems reflect historical biases in training data. We define a general benchmark to quantify gender bias in a variety of neural NLP tasks. Our empirical evaluation with…
Sentence representation at the semantic level is a challenging task for Natural Language Processing and Artificial Intelligence. Despite the advances in word embeddings (i.e. word vector representations), capturing sentence meaning is an…
Semantic sentence embedding models encode natural language sentences into vectors, such that closeness in embedding space indicates closeness in the semantics between the sentences. Bilingual data offers a useful signal for learning such…
Contextualized embeddings are proven to be powerful tools in multiple NLP tasks. Nonetheless, challenges regarding their interpretability and capability to represent lexical semantics still remain. In this paper, we propose that the task of…
Gender bias is a frequent occurrence in NLP-based applications, especially pronounced in gender-inflected languages. Bias can appear through associations of certain adjectives and animate nouns with the natural gender of referents, but also…
Word embeddings are an essential instrument in many NLP tasks. Most available resources are trained on general language from Web corpora or Wikipedia dumps. However, word embeddings for domain-specific language are rare, in particular for…
Natural Language Processing (NLP) has become increasingly utilized to provide adaptivity in educational applications. However, recent research has highlighted a variety of biases in pre-trained language models. While existing studies…
We propose new static word embeddings optimised for sentence semantic representation. We first extract word embeddings from a pre-trained Sentence Transformer, and improve them with sentence-level principal component analysis, followed by…
Natural language processing (NLP) tasks tend to suffer from a paucity of suitably annotated training data, hence the recent success of transfer learning across a wide variety of them. The typical recipe involves: (i) training a deep,…
Neural text classification models typically treat output labels as categorical variables which lack description and semantics. This forces their parametrization to be dependent on the label set size, and, hence, they are unable to scale to…
Most sentence embedding techniques heavily rely on expensive human-annotated sentence pairs as the supervised signals. Despite the use of large-scale unlabeled data, the performance of unsupervised methods typically lags far behind that of…
Words are not created equal. In fact, they form an aristocratic graph with a latent hierarchical structure that the next generation of unsupervised learned word embeddings should reveal. In this paper, justified by the notion of…
Numerous embedding models have been recently explored to incorporate semantic knowledge into visual recognition. Existing methods typically focus on minimizing the distance between the corresponding images and texts in the embedding space…
Cross-lingual transfer of word embeddings aims to establish the semantic mappings among words in different languages by learning the transformation functions over the corresponding word embedding spaces. Successfully solving this problem…
Graph-language models (GLMs) have demonstrated great potential in graph-based semi-supervised learning. A typical GLM consists of two key stages: graph generation and text embedding, which are usually implemented by inferring a latent graph…
The Global Vectors for word representation (GloVe), introduced by Jeffrey Pennington et al. is reported to be an efficient and effective method for learning vector representations of words. State-of-the-art performance is also provided by…
Generative adversarial networks (GANs) have shown considerable success, especially in the realistic generation of images. In this work, we apply similar techniques for the generation of text. We propose a novel approach to handle the…