Interview Questions for Anne Kao, Boeing Research and Technology's Senior Technical Fellow
In the dynamic world of aerospace, data analytics has undergone a significant transformation over the past three decades. Once a fledgling concept, text mining is now a game-changer, thanks to innovative approaches like the one taken by Anne Kao, Senior Technical Fellow at Boeing Research and Technology.
Kao, who has been with Boeing since 1990, developed a tool called PANDA, short for Part Name Discovery Analytics. This powerful tool helps identify part names in maintenance reports and other records, a task that, due to the complexity of part names and the lack of a standardised list, has been less understood than traditional entity extraction.
Kao's approach to language, influenced by her philosophy background, is data-driven and follows the Ordinary Language philosophy of late Wittgenstein and JL Austin. This philosophy is evident in her method for normalising part names, UNAMER. UNAMER leverages a combination of linguistic knowledge and machine learning, and requires very little machine learning training data, making it advantageous in adapting to different contexts.
The importance of leveraging domain knowledge has also been recognised in the aerospace industry. UNAMER's ability to process noisy text data is crucial to unlocking the value in free text data, which remains a primary means of communication and documentation in various industries. PANDA, in particular, is particularly useful for industries like the bio-industry due to its complexity and the large number of new terms.
Normalising the extracted key information is essential to form a complete picture of trends or groupings in the data and utilise the result for decision support. Without this normalisation, it is difficult to gain insights from the vast amount of data contained in free text, such as part information which is crucial for understanding issues such as quality, reliability, supply chain management, and airplane health management.
Boeing now has an entire initiative devoted to interpretable methods in data analytics, known as Boeing AnalytX. This initiative, coupled with Kao's groundbreaking work, is set to continue revolutionising the way data is analysed and utilised in the aerospace industry.
Moreover, PANDA and UNAMER by Anne Kao have been applied or could be adapted in industries such as healthcare, finance, marketing, and customer service to improve the processing of free-text data. The tool UNAMER developed by Kao can benefit any situation where people need to deal with lots of non-standard spelling or usage in text data.
According to Kao, language is evolving constantly to serve the goal of communication, and the meaning of a word is its use in the language. This philosophy is reflected in her work, making her tools not just useful for the aerospace industry but for any industry dealing with a large number of parts or any domain with a large number of new terms.
In conclusion, the work of Anne Kao and Boeing AnalytX is set to continue reshaping the future of data analytics in various industries, unlocking the hidden value in free text data and driving innovation in the era of big data.
