When learned without exploration, local models for structured prediction tasks are subject to exposure bias and cannot be trained without detailed guidance.
We find for this application (1) some annotator disagreements of economic policy uncertainty can be attributed to ambiguity in language, and (2) switching measurements from keyword-matching to supervised machine learning classifiers results in low correlation, a concerning implication for the validity of the index.
While sequence-to-sequence (seq2seq) models achieve state-of-the-art performance in many natural language processing tasks, they can be too slow for real-time applications.
We present a model which predicts how individual users of a dialog system understand and produce utterances based on user groups.
The referring expressions (REs) produced by a natural language generation (NLG) system can be misunderstood by the hearer, even when they are semantically correct.