Grammatical Sequence Prediction for Real-Time Neural Semantic Parsing
원문 초록
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. One performance bottleneck is predicting the most likely next token over a large vocabulary; methods to circumvent this bottleneck are a current research topic. We focus specifically on using seq2seq models for semantic parsing, where we observe that grammars often exist which specify valid formal representations of utterance semantics. By developing a generic approach for restricting the predictions of a seq2seq model to grammatically permissible continuations, we arrive at a widely applicable technique for speeding up semantic parsing. The technique leads to a 74% speed-up on an in-house dataset with a large vocabulary, compared to the same neural model without grammatical restrictions.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Where, What, Why: Towards Explainable Driver Attention Prediction
Optimal Conformal Prediction under Epistemic Uncertainty
Valid Selection among Conformal Sets
Anytime-valid, Bayes-assisted,Prediction-Powered Inference
Conformation-Aware Structure Prediction of Antigen-Recognizing Immune Proteins
Cautious Next Token Prediction
토론
이 논문과 연결된 포럼 글이 아직 없습니다.