A Latent Variable Model of Synchronous Syntactic-Semantic Parsing for Multiple Languages

By Andrea Gesmundo, James Henderson, Paola Merlo, Ivan Titov. 2009

55 citations recorded by the source corpus.

Motivated by the large number of languages (seven) and the short development time (two months) of the 2009 CoNLL shared task, we exploited latent variables to avoid the costly process of hand-crafted feature engineering, allowing the latent variables to induce features from the data. We took a pre-existing generative latent variable model of joint syntactic-semantic dependency parsing, developed for English, and applied it to six new languages with minimal adjustments. The parser's robustness across languages indicates that this parser has a very general feature set. The parser's high performance indicates that its latent variables succeeded in inducing effective features. This system was ranked third overall with a macro averaged F1 score of 82.14%, only 0.5% worse than the best system.

Subfields: Artificial Intelligence

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

Citations in the corpus

Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling (2017, methodology): “Perhaps the earliest methods modeling syntax-semantics interface with RNNs are due to (Hen-derson et al., 2008; Titov et al., 2009; Gesmundo et al., 2009), they used shift-reduce parsers for joint SRL and syntactic parsing, and relied on RNNs to model statistical dependencies across syntactic and…”
Greedy, Joint Syntactic-Semantic Parsing with Stack LSTMs (2016, methodology): “(2008) and variants (Gesmundo et al., 2009; Titov et al., 2009; Henderson et al., 2013) on the CoNLL 2008 and 2009 (English) shared tasks.”
The CoNLL-2009 Shared Task: Syntactic and Semantic Dependencies in Multiple Languages (2009, methodology): “(Gesmundo et al., 2009) use an incremental parsing model with synchronous syntactic and semantic derivations and a joint probability model for syntactic and semantic dependency structures.”
Top Accuracy and Fast Dependency Parsing is not a Contradiction (2010, methodology): “For a transition based parser, Gesmundo et al. (2009) reported run times between 2.2 days for English and 4.7 days for Czech for the joint training of syntactic and semantic dependencies.”
High-Order Low-Rank Tensors for Semantic Role Labeling (2015, background): “We compare against three systems that achieve the top average performance in the joint syntactic and semantic parsing track of the CoNLL-2009 shared task (Che et al., 2009; Zhao et al., 2009a; Gesmundo et al., 2009).”
A Simple and Accurate Syntax-Agnostic Neural Model for Dependency-based Semantic Role Labeling (2017, methodology): “Initially achieving stateof-the-art results only in the multilingual setting, where careful feature engineering is not practical (Gesmundo et al., 2009; Titov et al., 2009), neural SRL models now also outperform their traditional counterparts on standard benchmarks for English (FitzGerald et al.”
Incremental Sigmoid Belief Networks for Grammar Learning (2010, methodology): “For example, ISBNs have been applied to the dependency parsing problem (Titov and Henderson, 2007) and to joint dependency parsing and semantic role labelling (Henderson et al., 2008; Gesmundo et al., 2009), where in both cases they achieved state-of-the-art results.”