New York Times
Related Papers
REFRACTIVE: An Open Source Tool to Extract Knowledge from Syntactic and Semantic Relations
AbstractThe extraction of semantic propositions has proven instrumental in applications like IBM Watson and in Google’s knowledge graph . One of the core components of IBM Watson is the PRISMATIC …...
Distant Supervision Relation Extraction with Intra-Bag and Inter-Bag Attentions
AbstractThis paper presents a neural relation extraction method to deal with the noisy training data generated by distant supervision. Previous studies mainly focus on sentence-level de-noising by designing neural networks …...
HIBERT: Document Level Pre-training of Hierarchical Bidirectional Transformers for Document Summarization
AbstractNeural extractive summarization models usually employ a hierarchical encoder for document encoding and they are trained using sentence-level labels, which are created heuristically using rule-based methods. Training the hierarchical encoder …...
Knowledge Graph-Augmented Abstractive Summarization with Semantic-Driven Cloze Reward
AbstractSequence-to-sequence models for abstractive summarization have been studied extensively, yet the generated summaries commonly suffer from fabricated content, and are often found to be near-extractive. We argue that, to address …...
Modeling Content Importance for Summarization with Pre-trained Language Models
AbstractModeling content importance is an essential yet challenging task for summarization. Previous work is mostly based on statistical methods that estimate word-level salience, which does not consider semantics and larger …...
Unsupervised Extractive Summarization by Pre-training Hierarchical Transformers
AbstractUnsupervised extractive document summarization aims to select important sentences from a document without using labeled summaries during training. Existing methods are mostly graph-based with sentences as nodes and edge weights …...