Fast semantic parsing with well-typedness guarantees

Lindemann, Matthias; Groschwitz, Jonas; Koller, Alexander

doi:10.18653/v1/2020.emnlp-main.323

Cited by 21 publications

(27 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…with fixed tree decoder (incl. post-processing bugfix for AMR as per Lindemann et al (2020)). FG'20 is Fernández-González and Gómez-Rodríguez (2020).…”

Section: Resultsmentioning

confidence: 99%

“…The central challenge of compositional methods lies in the fact that the compositional structures are not provided in the graphbanks. Existing AM parsers (Groschwitz et al, 2018;Lindemann et al, , 2020 use hand-built heuristics to extract AM dep-trees for supervised training from the graphs in the graphbank. These heuristics require extensive expert work, including graphbank-specific decisions for source allocations and graphbank-and phenomenon-specific patterns to extract type requests for reentrancies.…”

Section: Decomposition Algorithmmentioning

confidence: 99%

“…For instance, the AM (Apply-Modify) dependency parser of Groschwitz et al (2018) uses a neural model to predict AM dependency trees, compositional structures that evaluate to semantic graphs. Their parser achieves high accuracy and parsing speed (Lindemann et al, 2020) across a variety of English semantic graphbanks. To obtain an AM dependency tree for each graph in the corpus, they use hand-written graphbank-specific heuristics.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Learning compositional structures for semantic graph parsing

Groschwitz¹,

Fowlie²,

Koller³

2021

Proceedings of the 5th Workshop on Structured Prediction for NLP (SPNLP 2021)

Self Cite

View full text Add to dashboard Cite

AM dependency parsing is a method for neural semantic graph parsing that exploits the principle of compositionality. While AM dependency parsers have been shown to be fast and accurate across several graphbanks, they require explicit annotations of the compositional tree structures for training. In the past, these were obtained using complex graphbankspecific heuristics written by experts. Here we show how they can instead be trained directly on the graphs with a neural latent-variable model, drastically reducing the amount and complexity of manual heuristics. We demonstrate that our model picks up on several linguistic phenomena on its own and achieves comparable accuracy to supervised training, greatly facilitating the use of AM dependency parsing for new sembanks.

show abstract

“…with fixed tree decoder (incl. post-processing bugfix for AMR as per Lindemann et al (2020)). FG'20 is Fernández-González and Gómez-Rodríguez (2020).…”

Section: Resultsmentioning

confidence: 99%

Section: Decomposition Algorithmmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Learning compositional structures for semantic graph parsing

Groschwitz¹,

Fowlie²,

Koller³

2021

Proceedings of the 5th Workshop on Structured Prediction for NLP (SPNLP 2021)

Self Cite

View full text Add to dashboard Cite

show abstract

“…Constrained Decoding. After neural parsers model semantic parsing as a sentence to logical form translation task (Yih et al, 2015;Krishnamurthy et al, 2017;Iyyer et al, 2017;Jie and Lu, 2018;Lindemann et al, 2020), many constrained decoding algorithms are also proposed, such as type constraint-based illegal token filtering (Krishnamurthy et al, 2017); Lisp interpreter-based method (Liang et al, 2017); type constraints for generating valid actions (Iyyer et al, 2017).…”

Section: Related Workmentioning

confidence: 99%

From Paraphrasing to Semantic Parsing: Unsupervised Semantic Parsing via Synchronous Semantic Decoding

Wu¹,

Chen²,

Xin³

et al. 2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

View full text Add to dashboard Cite

Semantic parsing is challenging due to the structure gap and the semantic gap between utterances and logical forms. In this paper, we propose an unsupervised semantic parsing method -Synchronous Semantic Decoding (SSD), which can simultaneously resolve the semantic gap and the structure gap by jointly leveraging paraphrasing and grammarconstrained decoding. Specifically, we reformulate semantic parsing as a constrained paraphrasing problem: given an utterance, our model synchronously generates its canonical utterance 1 and meaning representation. During synchronous decoding: the utterance paraphrasing is constrained by the structure of the logical form, therefore the canonical utterance can be paraphrased controlledly; the semantic decoding is guided by the semantics of the canonical utterance, therefore its logical form can be generated unsupervisedly. Experimental results show that SSD is a promising approach and can achieve competitive unsupervised semantic parsing performance on multiple datasets. * Corresponding Author 1 Canonical utterances are pseudo-language representations of logical forms, which have the synchronous structure of logical forms.

show abstract

“…L'19 are results of with fixed tree decoder (incl. post-processing bugfix for AMR as perLindemann et al (2020)). FG'20 is…”

mentioning

confidence: 99%

Proceedings of the 5th Workshop on Structured Prediction for NLP (SPNLP 2021)

2021

View full text Add to dashboard Cite

To date, most abstractive summarisation models have relied on variants of the negative loglikelihood (NLL) as their training objective. In some cases, reinforcement learning has been added to train the models with an objective that is closer to their evaluation measures (e.g. ROUGE). However, the reward function to be used within the reinforcement learning approach can play a key role for performance and is still partially unexplored. For this reason, in this paper, we propose two reward functions for the task of abstractive summarisation: the first function, referred to as RwB-Hinge, dynamically selects the samples for the gradient update. The second function, nicknamed RISK, leverages a small pool of strong candidates to inform the reward. In the experiments, we probe the proposed approach by fine-tuning an NLL pre-trained model over nine summarisation datasets of diverse size and nature. The experimental results show a consistent improvement over the negative loglikelihood baselines.

show abstract

Fast semantic parsing with well-typedness guarantees

Cited by 21 publications

References 23 publications

Learning compositional structures for semantic graph parsing

Learning compositional structures for semantic graph parsing

From Paraphrasing to Semantic Parsing: Unsupervised Semantic Parsing via Synchronous Semantic Decoding

Proceedings of the 5th Workshop on Structured Prediction for NLP (SPNLP 2021)

Contact Info

Product

Resources

About