Dependency-based Convolutional Neural Networks for Sentence Embedding
arXiv:1507.01839
Abstract
In sentence modeling and classification, convolutional neural network approaches have recently achieved state-of-the-art results, but all such efforts process word vectors sequentially and neglect long-distance dependencies. To exploit both deep learning and linguistic structures, we propose a tree-based convolutional neural network model which exploit various long-distance relationships between words. Our model improves the sequential baselines on all three sentiment and question classification tasks, and achieves the highest published accuracy on TREC.
this paper has been accepted by ACL 2015
References in corpus (6)
- Improving neural networks by preventing co-adaptation of feature detectors
- ADADELTA: An Adaptive Learning Rate Method
- Natural Language Processing (almost) from Scratch
- Seeing stars: Exploiting class relationships for sentiment categorization with respect to rating scales
- A Convolutional Neural Network for Modelling Sentences
- Long Short-Term Memory Over Tree Structures
Cited by in corpus (17)
- Deep Learning applied to NLP
- Jointly Learning Sentence Embeddings and Syntax with Unsupervised Tree-LSTMs
- Learning to Compose Words into Sentences with Reinforcement Learning
- Neural Models for Sequence Chunking
- Knowledge as a Teacher: Knowledge-Guided Structural Attention Networks
- Alzheimer's Disease Detection from Spontaneous Speech through Combining Linguistic Complexity and (Dis)Fluency Features with Pretrained Language Models
- Dependency Sensitive Convolutional Neural Networks for Modeling Sentences and Documents
- Jointly Trained Sequential Labeling and Classification by Sparse Attention Neural Networks
- Improving Medical Short Text Classification with Semantic Expansion Using Word-Cluster Embedding
- ASR error management for improving spoken language understanding
- Sentence Encoding with Tree-constrained Relation Networks
- Neural Semantic Role Labeling with Dependency Path Embeddings
- Hierarchical Neural Networks for Sequential Sentence Classification in Medical Scientific Abstracts
- Translations as Additional Contexts for Sentence Classification
- Group Sparse CNNs for Question Classification with Answer Sets
- Combining Generative and Discriminative Approaches to Unsupervised Dependency Parsing via Dual Decomposition
- Embedding Lexical Features via Low-Rank Tensors