The Role of Syntax in Vector Space Models of Compositional Semantics

By Karl Moritz Hermann, Phil Blunsom. 2013

181 citations recorded by the source corpus.

Subfields: Natural Language Processing, Representation & Self-Supervised Learning

How researchers see this paper

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

In Natural Language Processing

In Representation & Self-Supervised Learning

Citations in the corpus

Convolutional Neural Networks for Sentence Classification (2014, methodology): “CCAE: Combinatorial Category Autoencoders with combinatorial category grammar operators (Hermann and Blunsom, 2013).”
Recent Trends in Deep Learning Based Natural Language Processing (2017, methodology): “[13] used embeddings along with stacked denoising autoencoders for domain adaptation in sentiment classification and Hermann and Blunsom [14] presented combinatory categorial autoencoders to learn the compositionality”
Deep Learning for Answer Sentence Selection (2014, methodology): “Popular ideas for this include exploiting categor y theory [4], using parse trees in conjunction with recursive autoencoders [17, 9], and convolutional neu ral networks [5, 13].”
Discriminative Neural Sentence Modeling by Tree-Based Convolution (2015, background): “Dependency parse and the combinatory categorical grammar can also be exploited as RNNs’ skeletons (Hermann and Blunsom, 2013; Iyyer et al., 2014).”
Multilingual Distributed Representations without Word Alignment (2013, methodology): “Subsequent work has also attempted to learn distributed semantics of larger structures, allowing us to apply distributed representation to tasks such as sentiment analysis or paraphrase detection (i.a. [1, 3, 12, 14, 21, 25]).”
Recurrent Convolutional Neural Networks for Discourse Compositionality (2013, background): “Proceedings of the Workshop on Continuous Vector Space Models and their Compositionality, pages 119–126, Sofia, Bulgaria, August 9 2013. c©2013 Association for Computational Linguistics”
Compositional Morphology for Word Representations and Language Modelling (2014, background): “Accounting for linguistically derived information such as morphology (Luong et al., 2013; Lazari-dou et al., 2013) or syntax (Hermann & Blunsom, 2013) has recently proved beneﬁcial to learning vector representations of words.”
Multilingual Models for Compositional Distributed Semantics (2014, background): “More complex composition functions using matrix-vector composition, convolutional neural networks or tensor composition have proved useful in tasks such as sentiment analysis (Socher et al., 2011; Hermann and Blunsom, 2013), relational similarity (Turney, 2012) or dialogue analy-”
A Primer on Neural Network Models for Natural Language Processing (2015, neutral): “…on parse trees (Iyyer, Enns, Boyd-Graber, & Resnik, 2014b), sentiment classification (Socher, Perelygin, Wu, Chuang, Manning, Ng, & Potts, 2013; Hermann & Blunsom, 2013), target-dependent sentiment classification (Dong, Wei, Tan, Tang, Zhou, & Xu, 2014) and question answering (Iyyer,…”
The minority report: some common assumptions to reconsider in the modelling of the brain and behaviour (2016, background): “…tags, chunks, named entity tags, semantic roles, semantically similar words and the likelihood that the sentence makes sense (grammatically and semantically); it also holds for the DN-based parser of Hermann and Blunsom (2013), whose tasks were sentiment estimation and phrase similarity ranking.”
Extraction of Salient Sentences from Labelled Documents (2014, background): “…answering (Bordes et al., 2014; Weston et al., 2014), dialogue systems (Kalchbrenner & Blunsom, 2013b), sentiment analysis (Socher et al., 2011; 2012; Hermann & Blunsom, 2013), and other natural language processing tasks such as chunking and named entity recognition (Collobert et al., 2011).”