Search for: All records

Many of the questions for training AIs how to answer questions come from the queries users type into search engines (like Google's Natural Questions). Is there a cheaper---perhaps even better---way? We propose a "naturalization" technique to turn high-quality, rigorously edited trivia questions into examples that resemble Natural Questions. Training on our naturalized questions and testing on natural questions comes close to the results with using Natural Questions, and we can improve results on MMLU (a standard modern evaluation set) by using our data. 

Word embeddings, which represent words as dense feature vectors, are widely used in natural language processing. In their seminal paper on word2vec, Mikolov and colleagues showed that a feature space created by training a word prediction network on a large text corpus will encode semantic information that supports analogy by vector arithmetic, e.g., "king" minus "man" plus "woman" equals "queen". To help novices appreciate this idea, people have sought effective graphical representations of word embeddings.We describe a new interactive tool for visually exploring word embeddings. Our tool allows users to define semantic dimensions by specifying opposed word pairs, e.g., gender is defined by pairs such as boy/girl and father/mother, and age by pairs such as father/son and mother/daughter. Words are plotted as points in a zoomable and rotatable 3D space, where the third ”residual” dimension encodes distance from the hyperplane defined by all the opposed word vectors with age and gender subtracted out. Our tool allows users to visualize vector analogies, drawing the vector from “king” to “man” and a parallel vector from “woman” to “king-man+woman”, which is closest to “queen”. Visually browsing the embedding space and experimenting with this tool can make word embeddings more intuitive. We include a series of experiments teachers can use to help K-12 students appreciate the strengths and limitations of this representation. 

Word embeddings, which represent words as dense feature vectors, are widely used in natural language processing. In their seminal paper on word2vec, Mikolov and colleagues showed that a feature space created by training a word prediction network on a large text corpus will encode semantic information that supports analogy by vector arithmetic, e.g., "king" minus "man" plus "woman" equals "queen". To help novices appreciate this idea, people have sought effective graphical representations of word embeddings.We describe a new interactive tool for visually exploring word embeddings. Our tool allows users to define semantic dimensions by specifying opposed word pairs, e.g., gender is defined by pairs such as boy/girl and father/mother, and age by pairs such as father/son and mother/daughter. Words are plotted as points in a zoomable and rotatable 3D space, where the third ”residual” dimension encodes distance from the hyperplane defined by all the opposed word vectors with age and gender subtracted out. Our tool allows users to visualize vector analogies, drawing the vector from “king” to “man” and a parallel vector from “woman” to “king-man+woman”, which is closest to “queen”. Visually browsing the embedding space and experimenting with this tool can make word embeddings more intuitive. We include a series of experiments teachers can use to help K-12 students appreciate the strengths and limitations of this representation.