Posted by Dan Walker and Dan Liebling, Software Engineers, Google Research People don’t write in the same way that they speak. Written language is controlled and deliberate, whereas transcripts of spontaneous speech (like interviews) are hard to read because speech is disorganized and less fluent. One aspect that makes speech transcripts particularly difficult to read is disfluency, which includes self-corrections, repetitions, and filled pauses (e.g., words like “umm”, and “you know”). Following is an example of a spoken sentence with disfluencies from the LDC CALLHOME corpus: But that’s it’s not, it’s not, it’s, uh, it’s a word play on what […]

Posted by Ethan Dyer and Guy Gur-Ari, Research Scientists, Google Research, Blueshift Team Language models have demonstrated remarkable performance on a variety of natural language tasks — indeed, a general lesson from many works, including BERT, GPT-3, Gopher, and PaLM, has been that neural networks trained on diverse data at large scale in an unsupervised way can perform well on a variety of tasks. Quantitative reasoning is one area in which language models still fall far short of human-level performance. Solving mathematical and scientific questions requires a combination of skills, including correctly parsing a question with natural language and mathematical notation, […]

Explanation methods that help users understand and trust machine-learning models often describe how much certain features used in the model contribute to its prediction. For example, if a model predicts a patient’s risk of developing cardiac disease, a physician might want to know how strongly the patient’s heart rate data influences that prediction. But if those features are so complex or convoluted that the user can’t understand them, does the explanation method do any good? MIT researchers are striving to improve the interpretability of features so decision makers will be more comfortable using the outputs of machine-learning models. Drawing on […]