Fast Forward Through Opportunistic Incremental Meaning Representation Construction

Abstract

One of the challenges semantic parsers face involves upstream errors originating from pre-processing modules such as ASR and syntactic parsers, which undermine the end result from the get go. We report the work in progress on a novel incremental semantic parsing algorithm that supports simultaneous application of independent heuristics and facilitates the construction of partial but potentially actionable meaning representations to overcome this problem. Our contribution to this point is mainly theoretical. In future work we intend to evaluate the algorithm as part of a dialogue understanding system on state of the art benchmarks.

"Listen, Understand and Translate": Triple Supervision Decouples End-to-end Speech-to-text Translation

“…Data Preprocessing Following the efforts of (Babkin and Nirenburg, 2017;Liu et al, 2019a;Wang et al, 2020), we introduce acoustic features that are 80 dimensional log Mel filterbanks. The features are extracted with a step size of 10ms and a window size of 25ms and extended with mean subtraction and variance normalization.…”