Rewarding Smatch: Transition-Based AMR Parsing with Reinforcement Learning

Naseem, Tahira; Shah, Abhishek; Wan, Hui; Florian, Radu; Roukos, Salim; Ballesteros, Miguel

doi:10.18653/v1/p19-1451

Cited by 62 publications

(72 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Significant increases are also shown on wikification and negation, indicating the benefits of using DBpedia Spotlight API and negation detection rules in post-processing. On all other subtasks except named entities, our approach achieves competitive results to the previous best approaches (Lyu and Titov, 2018;Naseem et al, 2019), and outperforms the previous best attention-based approach (van Noord and Bos, 2017b). The difference of scores on named entities is mainly caused by anonymization methods used in preprocessing, which suggests a potential improvement by adapting the anonymization method presented in Lyu and Titov (2018) to our approach.…”

Section: Resultsmentioning

confidence: 71%

“…Table 2 summarizes their SMATCH scores on the test sets of two AMR general releases. On AMR 2.0, we outperform the latest push from Naseem et al (2019) by 0.8% F1, and significantly improves Lyu and Titov (2018)'s results by 1.9% F1. Compared to the previous best attention-based approach (van Noord and Bos, 2017b), our approach shows a substantial gain of 5.3% F1, with no usage of any silver-standard training data.…”

Section: Resultsmentioning

confidence: 86%

“…Corpus Parser F1(%) AMR 2.0 Buys and Blunsom (2017) 61.9 van Noord and Bos (2017b) 71.0 * Groschwitz et al (2018) 71.0±0.5 Lyu and Titov (2018) 74.4±0.2 Naseem et al (2019) 75.5…”

Section: Resultsmentioning

confidence: 99%

See 2 more Smart Citations

AMR Parsing as Sequence-to-Graph Transduction

Zhang¹,

Ma²,

Duh³

et al. 2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

109

134

View full text Add to dashboard Cite

We propose an attention-based model that treats AMR parsing as sequence-to-graph transduction. Unlike most AMR parsers that rely on pre-trained aligners, external semantic resources, or data augmentation, our proposed parser is aligner-free, and it can be effectively trained with limited amounts of labeled AMR data. Our experimental results outperform all previously reported SMATCH scores, on both AMR 2.0 (76.3% F1 on LDC2017T10) and AMR 1.0 (70.2% F1 on LDC2014T12). Another View of ReentrancyAMR is a rooted, directed, and usually acyclic graph where nodes represent concepts, and labeled directed edges represent the relationships between them (see Figure 1 for an AMR example). The reason for AMR being a graph instead of a tree is that it allows reentrant semantic relations. For instance, in Figure 1(a) "victim" is both ARG0 and arXiv:1905.08704v2 [cs.CL]

show abstract

Section: Resultsmentioning

confidence: 71%

Section: Resultsmentioning

confidence: 86%

See 1 more Smart Citation

AMR Parsing as Sequence-to-Graph Transduction

Zhang¹,

Ma²,

Duh³

et al. 2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

109

134

View full text Add to dashboard Cite

show abstract

“…The AMR setup followed Ballesteros and Al-Onaizan (2017a), which introduced new actions to segment text and derive nodes or entity sub-graphs. In addition, we use the alignments and wikification from Naseem et al (2019). Unlike previous works, we force-aligned the unaligned nodes to neighbouring words and allowed attachment to the leaf nodes of entity sub-graphs, this increased oracle Smatch from 93.7 to 98.1 and notably improved model performance.…”

Section: Experiments and Resultsmentioning

confidence: 99%

“…Unlike previous works, we force-aligned the unaligned nodes to neighbouring words and allowed attachment to the leaf nodes of entity sub-graphs, this increased oracle Smatch from 93.7 to 98.1 and notably improved model performance. We therefore provide results for the Naseem et al (2019) oracle for comparison. Both previous works predict a node creation action and then a node label, or call a lemmatizer if no label is found.…”

Section: Experiments and Resultsmentioning

confidence: 99%

Transition-based Parsing with Stack-Transformers

Astudillo¹,

Ballesteros²,

Naseem³

et al. 2020

Findings of the Association for Computational Linguistics: EMNLP 2020

Self Cite

View full text Add to dashboard Cite

Modeling the parser state is key to good performance in transition-based parsing. Recurrent Neural Networks considerably improved the performance of transition-based systems by modelling the global state, e.g. stack-LSTM parsers, or local state modeling of contextualized features, e.g. Bi-LSTM parsers. Given the success of Transformer architectures in recent parsing systems, this work explores modifications of the sequence-to-sequence Transformer architecture to model either global or local parser states in transition-based parsing. We show that modifications of the cross attention mechanism of the Transformer considerably strengthen performance both on dependency and Abstract Meaning Representation (AMR) parsing tasks, particularly for smaller models or limited training data. * Miguel's and Austin's contributions were carried out while at IBM Research.

show abstract

Leveraging Semantic Parsing for Relation Linking over Knowledge Bases

Mihindukulasooriya

Rossiello

Kapanipathi

et al. 2020

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Knowledge base question answering systems are heavily dependent on relation extraction and linking modules. However, the task of extracting and linking relations from text to knowledge bases faces two primary challenges; the ambiguity of natural language and lack of training data. To overcome these challenges, we present SLING, a relation linking framework which leverages semantic parsing using Abstract Meaning Representation (AMR) and distant supervision. SLING integrates multiple approaches that capture complementary signals such as linguistic cues, rich semantic representation, and information from the knowledge base. The experiments on relation linking using three KBQA datasets, QALD-7, QALD-9, and LC-QuAD 1.0 demonstrate that the proposed approach achieves state-of-the-art performance on all benchmarks.

show abstract

Rewarding Smatch: Transition-Based AMR Parsing with Reinforcement Learning

Cited by 62 publications

References 39 publications

AMR Parsing as Sequence-to-Graph Transduction

AMR Parsing as Sequence-to-Graph Transduction

Transition-based Parsing with Stack-Transformers

Leveraging Semantic Parsing for Relation Linking over Knowledge Bases

Contact Info

Product

Resources

About