Extraction of Salient Sentences from Labelled Documents
arXiv:1412.6815
Abstract
We present a hierarchical convolutional document model with an architecture designed to support introspection of the document structure. Using this model, we show how to use visualisation techniques from the computer vision literature to identify and extract topic-relevant sentences. We also introduce a new scalable evaluation technique for automatic sentence extraction systems that avoids the need for time consuming human annotation of validation data.
arXiv commentarXiv admin note: substantial text overlap with arXiv:1406.3830
References in corpus (9)
- Distributed Representations of Words and Phrases and their Compositionality
- Neural Machine Translation by Jointly Learning to Align and Translate
- Sequence to Sequence Learning with Neural Networks
- Natural Language Processing (almost) from Scratch
- Convolutional Neural Network Architectures for Matching Natural Language Sentences
- Visualizing and Understanding Convolutional Networks
- Deep Learning for Answer Sentence Selection
- Knowledge Matters: Importance of Prior Information for Optimization
- Question Answering with Subgraph Embeddings
Cited by in corpus (13)
- Ask the GRU: Multi-Task Learning for Deep Text Recommendations
- "What is Relevant in a Text Document?": An Interpretable Machine Learning Approach
- Self-Explaining Structures Improve NLP Models
- Interpreting Deep Learning Models in Natural Language Processing: A Review
- Automatic text summarization: What has been done and what has to be done
- Evaluating Saliency Methods for Neural Language Models
- Are Interpretations Fairly Evaluated? A Definition Driven Pipeline for Post-Hoc Interpretability
- Evaluating Explanation Methods for Neural Machine Translation
- Attribution Analysis of Grammatical Dependencies in LSTMs
- On Attribution of Recurrent Neural Network Predictions via Additive Decomposition
- SalKG: Learning From Knowledge Graph Explanations for Commonsense Reasoning
- Distilling neural networks into skipgram-level decision lists
- An Investigation of Language Model Interpretability via Sentence Editing