• Publications
  • Influence
Linguistically-Informed Self-Attention for Semantic Role Labeling
TLDR
We present linguistically-informed self-attention with multi-task learning across dependency parsing, part-of-speech tagging, predicate detection and SRL. Expand
  • 201
  • 36
  • PDF
Fast and Accurate Entity Recognition with Iterated Dilated Convolutions
TLDR
This paper proposes a faster alternative to Bi-LSTMs for NER: Iterated Dilated Convolutional Neural Networks, which have better capacity than traditional CNNs for large context and structured prediction. Expand
  • 180
  • 30
  • PDF
Simultaneously Self-Attending to All Mentions for Full-Abstract Biological Relation Extraction
TLDR
We propose a model which simultaneously predicts relationships between all mention pairs in a document. Expand
  • 115
  • 26
  • PDF
Unsupervised Latent Tree Induction with Deep Inside-Outside Recursive Autoencoders
TLDR
We introduce the deep inside-outside recursive autoencoder (DIORA), a fully-unsupervised method for discovering syntax that simultaneously learns representations for constituents within the induced tree. Expand
  • 37
  • 14
  • PDF
Hierarchical Losses and New Resources for Fine-grained Entity Typing and Linking
TLDR
This paper presents new methods using real and complex bilinear mappings for integrating hierarchical information, yielding substantial improvement over flat predictions in entity linking and fine-grained entity typing and achieving new state-of-the-art results for end-to-end models on the benchmark FIGER dataset. Expand
  • 45
  • 11
  • PDF
Sleep promotes consolidation and generalization of extinction learning in simulated exposure therapy for spider fear.
Simulated exposure therapy for spider phobia served as a clinically naturalistic model to study effects of sleep on extinction. Spider-fearing, young adult women (N = 66), instrumented for skinExpand
  • 85
  • 7
  • PDF
Multilingual Relation Extraction using Compositional Universal Schema
TLDR
Universal schema builds a knowledge base (KB) of entities and relations by jointly embedding all relation types from input KBs as well as textual patterns expressing relations from raw text. Expand
  • 74
  • 5
  • PDF
Marginal Likelihood Training of BiLSTM-CRF for Biomedical Named Entity Recognition from Disjoint Label Sets
TLDR
We propose a method for training a single CRF extractor from multiple datasets with disjoint or partially overlapping sets of entity types. Expand
  • 37
  • 4
  • PDF
Fast and Accurate Sequence Labeling with Iterated Dilated Convolutions
TLDR
This paper proposes an alternative to Bi-LSTMs for this purpose: iterated dilated convolutional neural networks (ID-CNNs), which have better capacity than traditional CNNs for large context and structured prediction. Expand
  • 31
  • 3
  • PDF
Generalizing to Unseen Entities and Entity Pairs with Row-less Universal Schema
TLDR
Universal schema predicts the types of entities and relations in a knowledge base (KB) by jointly embedding the union of all available schema types. Expand
  • 38
  • 3
  • PDF