Latent Variable Sentiment Grammar
Neural models have been investigated for sentiment classification over constituent trees. They learn phrase composition automatically by encoding tree structures but do not explicitly model sentiment composition, which requires to encode sentiment class labels. To this end, we investigate two formalisms with deep sentiment representations that capture sentiment subtype expressions by latent variables and Gaussian mixture vectors, respectively. Experiments on Stanford Sentiment Treebank (SST) show the effectiveness of sentiment grammar over vanilla neural encoders. Using ELMo embeddings, our method gives the best results on this benchmark.
Code (1)
Tasks
General ClassificationSentiment AnalysisSentiment ClassificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Interpreting Sentiment Composition with Latent Semantic Tree
As the key to sentiment analysis, sentiment composition considers the classification of a constituent via classifications of its contained sub-constituents and rules operated on them. Such compositionality has been widel…
ClassificationDomain AdaptationSentiment AnalysisCompound Probabilistic Context-Free Grammars for Grammar Induction
We study a formalization of the grammar induction problem that models sentences as being generated by a compound probabilistic context-free grammar. In contrast to traditional formulations which learn a single stochastic…
Constituency Grammar InductionSentenceVariational InferenceGaussian Mixture Latent Vector Grammars
We introduce Latent Vector Grammars (LVeGs), a new framework that extends latent variable grammars such that each nonterminal symbol is associated with a continuous vector space representing the set of (infinitely many) …
Constituency ParsingPart-Of-Speech TaggingLatent Variable Grammars for Discontinuous Parsing
Growing Better Graphs With Latent-Variable Probabilistic Graph Grammars
Recent work in graph models has found that probabilistic hyperedge replacement grammars (HRGs) can be extracted from graphs and used to generate new random graphs with graph properties and substructures close to the orig…