Many Papers on Machine Learning in NLP are Scientifically Dubious
In response to a previous blog, many people expressed concerns to me about the quality of many papers they saw on ML in NLP. I summarise some of these concerns, which are worrying.
Learning does not require evaluation metrics
I was recently asked if machine learning requires evaluation metrics. The answer is no, and the fact that people are asking such questions suggests that some newcomers to the field may have a limited perspective on NLP research methodology.
How Should Different NLG Components Add Value?
Some comments on how different components in the NLG pipeline can “add value” by contributing to the ultimate goal of generating texts that easy for people to read and understand.
Challenges of Surface Realisation
I think surface realisation becomes especially challenging when syntax depends on semantics or pragmatics. From engineering perspective, handling phenomena that only occur in a few languages can be painful.
“Will I Pass my PhD Viva”
Many students get stressed about their PhD viva (oral exam) even though they are very unlikely to fail. I present some rules and a flowchart to suggest when there is real cause for concern, and when there is not.
How I Review Papers
A few comments on how I review papers (what I actually do, not what I am supposed to do), and associated advice for authors.
Lexical Choice Needs Machine Learning!
Lexical choice is an area of NLG which really needs machine-learning and data-based techniques.
Academic Researchers Should be Scouts and Explorers
Perhaps being somewhat idealistic, I think academic researchers should act as “scouts” exploring unknown research terrain
Notes from a Dev Conf: Sensible Attitude to Trendy AI Tech, Arria Presentations
I went to my first developers conference last week and was impressed, not least by the sensible attitude towards deep learning and other trendy AI technology.
Use Good Engineering Methodology When Building NLG Systems!
Good software engineering is criticial when building NLG systems, including requirements analysis, design, testing, and support.
