Search

Word embeddings have become a integral part of machine learning solutions for natural language processing (NLP) challenges. They are learned by taking the statistical co-occurrence information from a corpus and representing it in a dense vector (often hundreds of dimensions). This has resulted in many NLP tasks employing word embedding solutions to achieve state of the art performance metrics. The embedding process produces a challenge of understanding and interpreting these vectors as humans. In this thesis I aim to explore how to understand and explain what word embeddings are representing and why they improve the performance of many tasks. I achieve this by utilising concepts, human understandable lists of words that aim to define an abstract object or class. Using concepts I define a method to show that they remain present in word embeddings, I then use this method to measure word embeddings understanding of these same concepts. I then use these measurements to provide reasoning for deciding on a ``better'' word embedding algorithms, or finding corpora that when embedded better represents a domain (such as medicine). I then define and use a method to measure a word's association to a concept, and by extension association to a bias. I show that unwanted biases (such as gendered, and racial) exist in word embeddings. I further show that gendered biases are representative of real world statistics. I then show that while removing these biases may seem like an ideal solution, it decreases a word embeddings representation of the same real world statistics. I also show colour biases and compare them to real world psychology studies, showing that pink is has a feminine bias and pink and blue are positively biased. I apply the methods I have defined for measuring biases to historical corpora (1800 - 1959) and look to see if occupational words change in gender or emotional biases over time. I then look at the semantic changes of words over those 150 years. Finally, I see if there is any correlation between bias changes and changes in the semantic meaning of a word over time.

Changing pottery production methods are one of numerous significant developments in the archaeological record of Later Iron Age southern Britain. Previous studies of ceramic technology in this period (e.g. Rigby & Freestone 1997; Hill 2002) suffered from a lack of empirical data with which to characterise technological change, and only sparingly engaged with material culture theory. Our understanding of the social significance of changing technology has therefore remained largely obscured. Clay is a plastic medium upon which numerous traces of technological practices leave their mark. These practices yield valuable information pertaining to how people interacted with the material world in socially-constructed ways, and how this changed during periods of upheaval. On this basis, this study provides the first attempt to empirically characterise the nature of ceramic technological change in two studyregions: Berkshire and northern Hampshire; and Hertfordshire. Petrographic and SEM analyses were used to characterise technological properties of Middle and Late Iron Age ceramic fabrics from the two regions; and radiographic analysis of 428 vessels revealed details of forming methods employed. Elements of continuity are identified for the first time: for example, in patterns of clay preparation or the use of coil-building; as well as in the continued production of flint-tempered pottery in Hampshire. Novel technology was variably employed alongside this continuity: for example, in both regions the potter’s wheel was employed in at least two different ways - wheel-coiling, and throwing. Results point to a Middle Iron Age characterised by numerous localised systems of technical practice, from which emerged a Late Iron Age that saw technical knowledge flow more freely between groups of producers. This enriched technological background provided the means for the constitution of new forms of identity, and the reconfiguration of what it meant to be a craftsperson in a rapidly changing society.