Frontiers of Engineering Reports on Leading-Edge Engineering from the 2017 Symposium (2018) / Chapter Skim
Currently Skimming:
Humans and Computers Working Together to Measure Machine Learning Interpretability - Jordan Boyd-Graber
Humans and Computers Working Together to Measure Machine Learning Interpretability - Jordan Boyd-Graber
Pages 5-12
The Chapter Skim interface presents what we've algorithmically identified as the most significant single chunk of text within every page in the chapter.
Select key terms on the right to highlight them within pages of the chapter.
From page 5... ...
Topic models, for example, are sold as a tool for understanding large data collections: lawyers scouring Enron emails for a smoking gun, journalists making sense of Wikileaks, or humanists characterizing the oeuvre of Lope de Vega. But topic models' proponents never asked what those lawyers, journalists, or humanists needed.
|
From page 6... ...
Quiz Bowl Fortunately, there is a ready-made source of questions written with these properties from a competition known as Quiz Bowl. Thousands of questions are written every year for competitions that engage participants from middle schoolers to grizzled veterans on the "open circuit." These questions represent decades of iterative refinement of how to best discriminate which humans are most knowledgeable (in contrast, Jeopardy's format has not changed since its debut half a century ago; its television-oriented format is thus not considered as "pure" a competition among trivia enthusiasts)
|
From page 7... ...
Q: This man ordered Thomas Larkin to buy him 70 square miles of land, leading him to acquire his Mariposa gold mine. He married J essie, the daughter of Thomas Hart Benton, and, during the Civil War, he controversially confiscated (*
|
From page 8... ...
The language of chess is relatively simple; given a single board configuration, only a handful of moves are worthwhile. Unlike chess, Quiz Bowl is grounded in language, which makes the task of explaining hypotheses, features, and probabilities more complicated.
|
From page 9... ...
Thus, a prerequisite for ooperative c QA is the creation of interpretable explanations for the answers that machine learning systems provide. Linear Approximations Deep learning algorithms have earned a reputation for being ninterpretable u and susceptible to tampering to produce the wrong answer (Szegedy et al.
|
From page 10... ...
In other words, the rise of machine learning in everyday life becomes a virtuous cycle: with a clear objective that captures human interpretability, machine learning algorithms become less opaque and more understandable every time they are used. Despite the hyperbole about an impending robot apocalypse associated with artificial intelligence killing all humans, I think a bigger threat is automation disrupting human livelihood.
|
From page 11... ...
2015. Deep unordered composition rivals syntactic methods for text classification.
|
Key Terms
This material may be derived from roughly machine-read images, and so is provided only to facilitate research.
More
information on Chapter Skim is available.