Revisiting the Importance of Encoding Logic Rules in Sentiment Classification

  title={Revisiting the Importance of Encoding Logic Rules in Sentiment Classification},
  author={Kalpesh Krishna and P. Jyothi and Mohit Iyyer},
  • Kalpesh Krishna, P. Jyothi, Mohit Iyyer
  • Published 2018
  • Computer Science
  • ArXiv
  • We analyze the performance of different sentiment classification models on syntactically complex inputs like A-but-B sentences. [...] Key Result Finally, a crowdsourced analysis reveals how ELMo outperforms baseline models even on sentences with ambiguous sentiment labels.Expand Abstract

    Figures, Tables, and Topics from this paper.


    Publications referenced by this paper.
    Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank
    • 3,817
    • Highly Influential
    • PDF
    Deep Unordered Composition Rivals Syntactic Methods for Text Classification
    • 499
    • PDF
    Seeing Stars: Exploiting Class Relationships for Sentiment Categorization with Respect to Rating Scales
    • 1,869
    • PDF
    Baselines and Bigrams: Simple, Good Sentiment and Topic Classification
    • 886
    • PDF
    Deep contextualized word representations
    • 4,146
    • PDF
    Dissecting Contextual Word Embeddings: Architecture and Representation
    • 151
    • Highly Influential
    • PDF
    Reporting Score Distributions Makes a Difference: Performance Study of LSTM-networks for Sequence Tagging
    • 266
    • PDF
    Glove: Global Vectors for Word Representation
    • 14,616
    • PDF
    Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks
    • 1,848
    • PDF
    Harnessing Deep Neural Networks with Logic Rules
    • 310
    • Highly Influential
    • PDF