Human-in-the-Loop Refinement of Word Embeddings
This work addresses bias and quality concerns in word embeddings for organizations using machine learning pipelines, but it is incremental as it builds on existing post-processing methods.
The paper tackles the problem of uneven semantic and syntactic representations and biases in word embeddings by proposing an interactive refitting system that allows humans to identify and address quality issues, enabling organizations to refine embeddings iteratively for better downstream task performance.
Word embeddings are a fixed, distributional representation of the context of words in a corpus learned from word co-occurrences. Despite their proven utility in machine learning tasks, word embedding models may capture uneven semantic and syntactic representations, and can inadvertently reflect various kinds of bias present within corpora upon which they were trained. It has been demonstrated that post-processing of word embeddings to apply information found in lexical dictionaries can improve the semantic associations, thus improving their quality. Building on this idea, we propose a system that incorporates an adaptation of word embedding post-processing, which we call "interactive refitting", to address some of the most daunting qualitative problems found in word embeddings. Our approach allows a human to identify and address potential quality issues with word embeddings interactively. This has the advantage of negating the question of who decides what constitutes bias or what other quality issues may affect downstream tasks. It allows each organization or entity to address concerns they may have at a fine grained level and to do so in an iterative and interactive fashion. It also allows for better insight into what effect word embeddings, and refinements to word embeddings, have on machine learning pipelines.