Semantic Parsing with Dual Learning

Cao, Ruisheng; Zhu, Su; Liu, Chen; Li, Jieyu; Yu, Kai

doi:10.18653/v1/p19-1007

Cited by 57 publications

(39 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As shown in the "syntrain" row of Table 3, retraining the model on the combination of this data and the supervised data leads to overfitting in the training environments. A method related to data-augmentation is jointly supervising the model using the training data in the reverse direction, for example by generating utterance from query (Fried et al, 2018;Cao et al, 2019). For Spider, we find that this dual objective (57.…”

Section: Resultsmentioning

confidence: 84%

Grounded Adaptation for Zero-shot Executable Semantic Parsing

Zhong¹,

Lewis²,

Wang³

et al. 2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

We propose Grounded Adaptation for Zeroshot Executable Semantic Parsing (GAZP) to adapt an existing semantic parser to new environments (e.g. new database schemas). GAZP combines a forward semantic parser with a backward utterance generator to synthesize data (e.g. utterances and SQL queries) in the new environment, then selects cycleconsistent examples to adapt the parser. Unlike data-augmentation, which typically synthesizes unverified examples in the training environment, GAZP synthesizes examples in the new environment whose inputoutput consistency are verified. On the Spider, Sparc, and CoSQL zero-shot semantic parsing tasks, GAZP improves logical form and execution accuracy of the baseline parser. Our analyses show that GAZP outperforms dataaugmentation in the training environment, performance increases with the amount of GAZPsynthesized data, and cycle-consistency is central to successful adaptation.

show abstract

Section: Resultsmentioning

confidence: 84%

Grounded Adaptation for Zero-shot Executable Semantic Parsing

Zhong¹,

Lewis²,

Wang³

et al. 2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

show abstract

“…It will be a future work to incorporate relations among dialogue states, utterances and domain schemata. To further mitigate the data sparsity problem of multi-domain DST, it would be also interesting to incorporate data augmentations (Zhao et al, 2019) and semi-supervised learnings (Lan et al, 2018;Cao et al, 2019).…”

Section: Discussionmentioning

confidence: 99%

Efficient Context and Schema Fusion Networks for Multi-Domain Dialogue State Tracking

Zhu¹,

Li²,

Chen³

et al. 2020

Findings of the Association for Computational Linguistics: EMNLP 2020

Self Cite

View full text Add to dashboard Cite

Dialogue state tracking (DST) aims at estimating the current dialogue state given all the preceding conversation. For multi-domain DST, the data sparsity problem is a major obstacle due to increased numbers of state candidates and dialogue lengths. To encode the dialogue context efficiently, we utilize the previous dialogue state (predicted) and the current dialogue utterance as the input for DST. To consider relations among different domain-slots, the schema graph involving prior knowledge is exploited. In this paper, a novel context and schema fusion network is proposed to encode the dialogue context and schema graph by using internal and external attention mechanisms. Experiment results show that our approach can outperform strong baselines, and the previous state-of-the-art method (SOM-DST) can also be improved by our proposed schema graph.

show abstract

“…They are either synthetic-only (Marzoev et al, 2020) or use human data from other Overnight domains (Herzig and Berant, 2018b). For reference, we also include two of the best-performing models that use in-domain human data (Cao et al, 2019;Chen et al, 2018) 4 .…”

Section: Applying Autoqa To Overnightmentioning

confidence: 99%

“…Numbers are copied from the cited papers. We report the numbers for the BL-Att model ofDamonte et al (2019), Att+Dual+LF ofCao et al (2019), ZEROSHOT model of…”

mentioning

confidence: 99%

AutoQA: From Databases To QA Semantic Parsers With Only Synthetic Training Data

Xu¹,

J.²,

Campagna³

et al. 2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

We propose AutoQA, a methodology and toolkit to generate semantic parsers that answer questions on databases, with no manual effort. Given a database schema and its data, AutoQA automatically generates a large set of high-quality questions for training that covers different database operations. It uses automatic paraphrasing combined with templatebased parsing to find alternative expressions of an attribute in different parts of speech. It also uses a novel filtered auto-paraphraser to generate correct paraphrases of entire sentences.We apply AutoQA to the Schema2QA dataset and obtain an average logical form accuracy of 62.9% when tested on natural questions, which is only 6.4% lower than a model trained with expert natural language annotations and paraphrase data collected from crowdworkers. To demonstrate the generality of AutoQA, we also apply it to the Overnight dataset. AutoQA achieves 69.8% answer accuracy, 16.4% higher than the state-of-the-art zero-shot models and only 5.2% lower than the same model trained with human data.

show abstract

Semantic Parsing with Dual Learning

Cited by 57 publications

References 48 publications

Grounded Adaptation for Zero-shot Executable Semantic Parsing

Grounded Adaptation for Zero-shot Executable Semantic Parsing

Efficient Context and Schema Fusion Networks for Multi-Domain Dialogue State Tracking

AutoQA: From Databases To QA Semantic Parsers With Only Synthetic Training Data

Contact Info

Product

Resources

About