Deep Multitask Learning for Semantic Dependency Parsing

By Hao Peng, Sam Thomson, Noah A. Smith. 2017

151 citations recorded by the source corpus.

We present a deep neural architecture that parses sentences into three semantic dependency graph formalisms. By using efficient, nearly arc-factored inference and a bidirectional-LSTM composed with a multi-layer perceptron, our base system is able to significantly improve the state of the art for semantic dependency parsing, without using hand-engineered features or syntax. We then explore two multitask learning approaches—one that shares parameters across formalisms, and one that uses higher-order structures to predict the graphs jointly. We find that both approaches improve performance across formalisms on average, achieving a new state of the art. Our code is open-source and available at https://github.com/Noahs-ARK/NeurboParser.

Subfields: Artificial Intelligence, Natural Language Processing

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 Natural Language Processing

Citations in the corpus

Semi-Supervised Sequence Modeling with Cross-View Training (2018, methodology): “For NLP, most work has focused on a small number of closely related tasks (Lu-ong et al., 2016; Zhang and Weiss, 2016; Søgaard and Goldberg, 2016; Peng et al., 2017).”
Parameter-Efficient Transfer Learning for NLP (2019, background): “, 2013), semantic parsing (Peng et al., 2017), machine translation (Johnson et al.”
Broad-Coverage Semantic Parsing as Transduction (2019, methodology): “Most recent parsers for SDP are graph-based: Peng et al. (2017a, 2018) use a max-margin clas-siﬁer on top of a BiLSTM, with the factored score for each graph over predicates, unlabeled arcs, and arc labels.”
Syntactic Scaffolds for Semantic Structures (2018, methodology): “Meanwhile, some recent methods forgo explicit syntactic processing altogether (Zhou and Xu, 2015; He et al., 2017; Lee et al., 2017; Peng et al., 2017).”
Multilingual and Multi-Aspect Hate Speech Analysis (2019, methodology): “It has been used in different NLP tasks such as parsing (Hashimoto et al., 2017), dependency parsing (Peng et al., 2017), neural machine translation (Luong et al., 2016), sentiment analysis (Au-genstein et al., 2018), and other tasks.”
Text Generation with Exemplar-based Adaptive Decoding (2019, unknown): “Rather, we are learning { U p , V p , U q , V q } directly; P , Q , { P i } , and { Q i } are never explicitly instantiated (Peng et al., 2017, 2018c).”
Word Emotion Induction for Multiple Languages as a Deep Multi-Task Learning Problem (2018, background): “…1997), work well for various NLP tasks (Setiawan et al., 2015; Liu et al., 2015; Søgaard and Goldberg, 2016; Cummins et al., 2016; Liu et al., 2017; Peng et al., 2017), and practically increases sample size, thus making it a natural choice for small-sized data sets typically found in the area of…”