TreePiece: Faster Semantic Parsing via Tree Tokenization
Not on the map. Why?
Abstract (arXiv)
Autoregressive (AR) encoder-decoder neural networks have proved successful in many NLP problems, including Semantic Parsing -- a task that translates natural language to machine-readable parse trees. However, the sequential prediction process of AR models can be slow. To accelerate AR for semantic parsing, we introduce a new technique called TreePiece that tokenizes a parse tree into subtrees and generates one subtree per decoding step. On TopV2 benchmark, TreePiece shows 4.6 times faster decoding speed than standard AR, and comparable speed but significantly higher accuracy compared to Non-Autoregressive (NAR).
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 34 of its 50 references that are in the map. First posted on arXiv 30 Mar 2023.
Builds on
34 of 50 references.
References · 34
- 2017Attention Is All You Needcited by 59,932
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
- 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
- 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,898
- 2018SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processingcited by 1,973
- 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,120
- 2017Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learningcited by 679
- 2018Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidatescited by 632
- 2017Non-Autoregressive Neural Machine Translationcited by 457
- 2015Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networkscited by 305
22 more
- 2018Deterministic Non-Autoregressive Neural Sequence Modeling by Iterative Refinementcited by 194
- 2016Language to Logical Form with Neural Attentioncited by 158
- 2019Insertion Transformer: Flexible Sequence Generation via Insertion Operationscited by 123
- 2018Coarse-to-Fine Decoding for Neural Semantic Parsingcited by 110
- 2018Semantic Parsing for Task Oriented Dialog using Hierarchical Representationscited by 101
- 2020SmBoP: Semi-autoregressive Bottom-up Semantic Parsingcited by 97
- 2019FlowSeq: Non-Autoregressive Conditional Sequence Generation with Generative Flowcited by 89
- 2018End-to-End Non-Autoregressive Neural Machine Translation with Connectionist Temporal Classificationcited by 72
- 2020Low-Resource Domain Adaptation for Compositional Task-Oriented Semantic Parsingcited by 72
- 2020Don't Parse, Generate! A Sequence to Sequence Architecture for Task-Oriented Semantic Parsingcited by 59
- 2019Non-Autoregressive Machine Translation with Auxiliary Regularizationcited by 52
- 2018Semi-Autoregressive Neural Machine Translationcited by 48
- 2020Conversational Semantic Parsingcited by 39
- 2019Imitation Learning for Non-Autoregressive Neural Machine Translationcited by 36
- 2021Non-Autoregressive Text Generation with Pre-trained Language Modelscited by 36
- 2021Span Pointer Networks for Non-Autoregressive Task-Oriented Semantic Parsingcited by 18
- 2021Non-Autoregressive Semantic Parsing for Compositional Task-Oriented Dialogcited by 17
- 2017Learning Structured Natural Language Representations for Semantic Parsingcited by 15
- 2017Learning an Executable Neural Semantic Parsercited by 14
- 2020Improving Non-autoregressive Neural Machine Translation with Monolingual Datacited by 10
- 2022Retrieve-and-Fill for Scenario-based Task-Oriented Semantic Parsingcited by 7
- 2019Mask-Predict: Parallel Decoding of Conditional Masked Language Modelscited by 5
Built on by
Citing papers per year: 2023: 2.
2 papers.