A Discriminative Graph-Based Parser for the Abstract Meaning Representation

By Jeffrey Flanigan, Sam Thomson, Jaime G. Carbonell, Chris Dyer, Noah A. Smith. Annual Meeting of the Association for Computational Linguistics, 2014

334 citations recorded by the source corpus.

Abstract Meaning Representation (AMR) is a semantic formalism for which a grow- ing set of annotated examples is avail- able. We introduce the first approach to parse sentences into this representa- tion, providing a strong baseline for fu- ture improvement. The method is based on a novel algorithm for finding a maxi- mum spanning, connected subgraph, em- bedded within a Lagrangian relaxation of an optimization problem that imposes lin- guistically inspired constraints. Our ap- proach is described in the general frame- work of structured prediction, allowing fu- ture incorporation of additional features and constraints, and may extend to other formalisms as well. Our open-source sys- tem, JAMR, is available at: http://github.com/jflanigan/jamr

Subfields: Artificial Intelligence, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/33a9d1a702eb75da709d26c44aaeb7c2015c870b

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Molecular Biology

Citations in the corpus

Toward Abstractive Summarization Using Semantic Representations (2018, methodology): “We use a statistical semantic parser, JAMR (Flanigan et al., 2014), which was trained on AMR Bank.”
Scene Graph Parsing as Dependency Parsing (2018, background): “Apart from dependency parsing, Abstract Meaning Representation (AMR) parsing (Flanigan et al., 2014; Werling et al., 2015; Wang et al., 2015; Konstas et al., 2017) may also benefit scene graph generation.”
Context Dependent Semantic Parsing: A Survey (2020, background): “Those corresponding parsers further differentiate between graph-based parsers (Flanigan et al., 2014; Zettlemoyer and Collins, 2012) and shift-reduce parsers (Zhao and Huang, 2014) due to the adopted parsing algorithms and the ways to generate derivations.”
Generation from Abstract Meaning Representation using Tree Transducers (2016, methodology): “The AMR graph and the sentence are aligned; we use the JAMR aligner from Flanigan et al. (2014), which aligns non-overlapping sub-graphs of the graph to spans of words.”
Structured Pruning of Large Language Models (2019, background): “Lagrangian relaxation methods have been explored in many NLP problems (Bastings et al., 2019; Martins et al., 2011; Flanigan et al., 2014; Rush et al., 2010).”
GPT-too: A Language-Model-First Approach for AMR-to-Text Generation (2020, methodology): “We tokenize each input text using The JAMR toolkit (Flanigan et al., 2014).”
FactGraph: Evaluating Factuality in Summarization with Semantic Graph Representations (2022, positive): “We use the JAMR aligner (Flanigan et al., 2014) to obtain node-to-word alignments.”
Solving Geometry Problems: Combining Text and Diagram Interpretation (2015, methodology): “We represent literals using a hypergraph (Figure 4) (Klein and Manning, 2005; Flanigan et al., 2014).”
Unsupervised Entity Linking with Abstract Meaning Representation (2015, methodology): “13 System AMR using AMR nodes and edges automatically generated by an AMR parser (Flanigan et al., 2014).”
Transforming Dependency Structures to Logical Forms for Semantic Parsing (2016, background): “Typically, an over-generating grammar is used whose accepted parses are ranked (Zelle and Mooney, 1996; Zettle-moyer and Collins, 2005; Wong and Mooney, 2007; Kwiatkowksi et al., 2010; Liang et al., 2011; Berant et al., 2013; Flanigan et al., 2014; Groschwitz et al., 2015).”
Linguistic realisation as machine translation: Comparing different MT models for AMR-to-text generation (2017, methodology): “The models of Flanigan et al. (2016) and Pourdamghani et al. (2016) were officially trained with”
Liberal Entity Extraction: Rapid Construction of Fine-Grained Entity Typing Systems (2017, positive): “We utilize the AMR parser developed by Flanigan et al. 44 and manually map AMR types and system-generated types to three coarse-grained types.”
Neural AMR: Sequence-to-Sequence Models for Parsing and Generation (2017, methodology): “Our full models outperform JAMR, a graph-based model but still lags behind other parser-dependent systems (CAMR6), and resource heavy approaches (SBMT).”
Deep Multitask Learning for Semantic Dependency Parsing (2017, methodology): “This is in contrast to AMR whose vertices are abstract concepts, with no explicit alignment to tokens, which makes parsing more difficult (Flanigan et al., 2014).”
Broad-Coverage Semantic Parsing as Transduction (2019, background): “based parsers build AMRs by identifying concepts and scoring edges between them, either in a pipeline (Flanigan et al., 2014), or jointly (Zhou et al.”
Generating Semantically Precise Scene Graphs from Textual Descriptions for Improved Image Retrieval (2015, background): “Parsing to graph-based representations Rep-resenting semantic information with graphs has recently experienced a resurgence caused by the development of the Abstract Meaning Representation (AMR) (Banarescu et al., 2013) which was followed by several works on parsing natural language sentences to AMR”
AMR-to-text Generation with Synchronous Node Replacement Grammar (2017, background): “Despite much literature so far on text-to-AMR parsing (Flanigan et al., 2014; Wang et al., 2015; Peng et al., 2015; Vanderwende et al., 2015; Pust et al., 2015; Artzi et al., 2015; Groschwitz et al., 2015; Goodman et al., 2016; Zhou et al., 2016), there has been little work on AMR-to-text generation”
Learning Structured Natural Language Representations for Semantic Parsing (2017, background): “…to a meaning representation directly via learning a task-speciﬁc grammar (Zelle and Mooney, 1996; Zettlemoyer and Collins, 2005; Wong and Mooney, 2006; Kwiatkowksi et al., 2010; Liang et al., 2011; Berant et al., 2013; Flanigan et al., 2014; Pasupat and Liang, 2015; Groschwitz et al., 2015).”