One Semantic Parser to Parse Them All: Sequence to Sequence Multi-Task Learning on Semantic Parsing Datasets
Not on the map. Why?
Abstract (arXiv)
Semantic parsers map natural language utterances to meaning representations. The lack of a single standard for meaning representations led to the creation of a plethora of semantic parsing datasets. To unify different datasets and train a single model for them, we investigate the use of Multi-Task Learning (MTL) architectures. We experiment with five datasets (Geoquery, NLMaps, TOP, Overnight, AMR). We find that an MTL architecture that shares the entire network across datasets yields competitive or better parsing accuracies than the single-task baselines, while reducing the total number of parameters by 68%. We further provide evidence that MTL has also better compositional generalization than single-task models. We also present a comparison of task sampling methods and propose a competitive alternative to widespread proportional sampling strategies.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 37 of its 67 references that are in the map. First posted on arXiv 8 Jun 2021.
Builds on
37 of 67 references.
References · 37
- 2017Attention Is All You Needcited by 59,932
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
- 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,854
- 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
- 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
- 2015Pointer Networkscited by 882
- 2017An Overview of Multi-Task Learning in Deep Neural Networkscited by 791
- 2019Green AIcited by 620
- 2017Exploring Generalization in Deep Learningcited by 595
- 2016Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translationcited by 467
- 2019Measuring Compositional Generalization: A Comprehensive Method on Realistic Datacited by 280
25 more
- 2016Transfer Learning for Low-Resource Neural Machine Translationcited by 188
- 2018Improving Text-to-SQL Evaluation Methodologycited by 133
- 2016Data Recombination for Neural Semantic Parsingcited by 111
- 2018Semantic Parsing for Task Oriented Dialog using Hierarchical Representationscited by 101
- 2015Multi-task Sequence to Sequence Learningcited by 94
- 2018Pre-training on high-resource speech recognition improves low-resource speech-to-text translationcited by 70
- 2017Identifying beneficial task relations for multi-task learning in deep neural networkscited by 59
- 2020Don't Parse, Generate! A Sequence to Sequence Architecture for Task-Oriented Semantic Parsingcited by 59
- 2017Neural AMR: Sequence-to-Sequence Models for Parsing and Generationcited by 56
- 2018A Hierarchical Multi-task Approach for Learning Embeddings from Semantic Taskscited by 54
- 2020AMR Parsing via Graph-Sequence Iterative Inferencecited by 47
- 2017The Parallel Meaning Bank: Towards a Multilingual Corpus of Translations Annotated with Compositional Meaning Representationscited by 41
- 2020Conversational Semantic Parsingcited by 39
- 2016An Incremental Parser for Abstract Meaning Representationcited by 34
- 2018Improving a Neural Semantic Parser by Counterfactual Learning from Human Bandit Feedbackcited by 32
- 2019Broad-Coverage Semantic Parsing as Transductioncited by 32
- 2013Lambda Dependency-Based Compositional Semanticscited by 26
- 2016When is multitask learning effective? Semantic sequence prediction under varying data conditionscited by 21
- 2017Cross-domain Semantic Parsing via Paraphrasingcited by 19
- 2019Compositional Semantic Parsing Across Graphbankscited by 15
- 2018Learning compositionally through attentive guidancecited by 11
- 2018Multitask Parsing Across Semantic Representationscited by 10
- 2019Practical Semantic Parsing for Spoken Language Understandingcited by 7
- 2017Transfer Learning for Neural Semantic Parsingcited by 5
- 2018Counterfactual Learning from Human Proofreading Feedback for Semantic Parsingcited by 4
Built on by
Citing papers per year: 2022: 3.
3 papers.