Abstract | Instead, we introduce a Compositional Vector Grammar (CVG), which combines PCFGs with a syntactically untied recursive neural network that learns syntactico-semantic, compositional vector representations. |
Introduction | The vectors for nonterminals are computed via a new type of recursive neural network which is conditioned on syntactic categories from a PCFG. |
Introduction | l. CVGs combine the advantages of standard probabilistic context free grammars (PCFG) with those of recursive neural networks (RNNs). |
Introduction | sets of discrete states and recursive deep learning models that jointly learn classifiers and continuous feature representations for variable-sized inputs. |
Background | Another set of models that have very successfully been applied in this area are recursive autoencoders (Socher et al., 2011a; Socher et al., 2011b), which are discussed in the next section. |
Background | 2.3 Recursive Autoencoders |
Background | 9 9 Extending this idea, recursive autoencoders (RAE) allow the modelling of data of variable size. |
Experiments | In this paper we have brought a more formal notion of semantic compositionality to vector space models based on recursive autoencoders. |
Introduction | We present a novel class of recursive models, the Combinatory Categorial Autoencoders (CCAE), which marry a semantic process provided by a recursive autoencoder with the syntactic representations of the CCG formalism. |
Introduction | tions: Can recursive vector space models be reconciled with a more formal notion of compositionality; and is there a role for syntax in guiding semantics in these types of models? |
Introduction | In terms of learning complexity and space requirements, our models strike a balance between simpler greedy approaches (Socher et al., 201 lb) and the larger recursive vector-matrix models (Socher et al., 2012b). |
Model | The models in this paper combine the power of recursive , vector-based models with the linguistic intuition of the CCG formalism. |
Abstract | This paper presents a novel method for inducing phrase-based translation units directly from parallel data, which we frame as learning an inverse transduction grammar (ITG) using a recursive Bayesian prior. |
Analysis | We have presented a novel method for leam-ing a phrase-based model of translation directly from parallel data which we have framed as leam-ing an inverse transduction grammar (ITG) using a recursive Bayesian prior. |
Model | depending on 7“ This generative process is mutually recursive : P2 makes draws from P1 and P1 makes draws from P2. |
Model | where the conditioning of the second recursive call to P2 reflects that the counts 71‘ and K _ may be affected by the first draw from P2. |
Related Work | Additionally, we have extended the model to allow recursive nesting of adapted non-terminals, such that we end up with an infinitely recursive formulation where the top-level and base distributions are explicitly linked together. |
Conclusions and Future Work | We studied the internal structures of more than 37,382 Chinese words, analyzing their structures as the recursive combinations of characters. |
Introduction | (constituent) trees, adding recursive structures of characters for words. |
Word Structures and Syntax Trees | Multi-character words can also have recursive syntactic structures. |
Word Structures and Syntax Trees | Our annotations are binarized recursive word |