Fine-tuning Tree-LSTM for phrase-level sentiment classification on a Polish dependency treebank. Submission to PolEval task 2

2017/11/03 by Tomasz Korbak, Korbak, Tomasz, Paulina Żak +1 · 2 citations
Computer Science · Mathematics · #Artificial intelligence #Computation and Language (cs.CL) #Computer science #Dependency (UML) #Dependency grammar #FOS: Computer and information sciences #Linguistics #Mathematics #Natural Language Processing Techniques #Natural language processing #Phrase #Regularization (linguistics) #Sentiment analysis #Speech Recognition and Synthesis #Task (project management) #Topic Modeling #Tree (set theory) #Treebank #Word (group theory) #cs.CL

paper · pdf · doi:10.48550/arxiv.1711.01985

published in arXiv (Cornell University) (Cornell University)

arxiv created 2017/11/03 · openalex publication_date 2017/11/03 · arxiv updated 2017/11/07 · openalex created_date 2017/11/17 · openalex updated_date 2026/07/28

Abstract

We describe a variant of Child-Sum Tree-LSTM deep neural network (Tai et al, 2015) fine-tuned for working with dependency trees and morphologically rich languages using the example of Polish. Fine-tuning included applying a custom regularization technique (zoneout, described by (Krueger et al., 2016), and further adapted for Tree-LSTMs) as well as using pre-trained word embeddings enhanced with sub-word information (Bojanowski et al., 2016). The system was implemented in PyTorch and evaluated on phrase-level sentiment labeling task as part of the PolEval competition.

Citations

• Enriching Word Vectors with Subword Information

Related

• Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks
• LyS_ACoruña at SemEval-2022 Task 10: Repurposing Off-the-Shelf Tools for Sentiment Analysis as Semantic Dependency Parsing
• Linguistically Regularized LSTMs for Sentiment Classification
• Dependency-based Convolutional Neural Networks for Sentence Embedding
• Bidirectional Tree-Structured LSTM with Head Lexicalization