• Publications
  • Influence
AFET: Automatic Fine-Grained Entity Typing by Hierarchical Partial-Label Embedding
TLDR
This paper proposes a novel embedding method to separately model “clean” and “noisy” mentions, and incorporates the given type hierarchy to induce loss functions. Expand
Cosmos QA: Machine Reading Comprehension with Contextual Commonsense Reasoning
TLDR
This paper introduces Cosmos QA, a large-scale dataset of 35,600 problems that require commonsense-based reading comprehension, formulated as multiple-choice questions, and proposes a new architecture that improves over the competitive baselines. Expand
Tracking State Changes in Procedural Text: a Challenge Dataset and Models for Process Paragraph Comprehension
TLDR
A new dataset and models for comprehending paragraphs about processes, an important genre of text describing a dynamic world, are presented and two new neural models that exploit alternative mechanisms for state prediction are introduced, in particular using LSTM input encoding and span prediction. Expand
Liberal Event Extraction and Event Schema Induction
TLDR
A brand new “Liberal” Event Extraction paradigm to extract events and discover event schemas from any input corpus simultaneously is proposed and it is shown that extraction performance using discovered schemas is comparable to supervised models trained from a large amount of data labeled according to predefined event types. Expand
A language-independent neural network for event detection
TLDR
A language-independent neural network is developed to capture both sequence and chunk information from specific contexts and use them to train an event detector for multiple languages without any manually encoded features. Expand
Biomedical Event Extraction based on Knowledge-driven Tree-LSTM
TLDR
A novel knowledge base (KB)-driven tree-structured long short-term memory networks (Tree-LSTM) framework is proposed, incorporating two new types of features: dependency structures to capture wide contexts and entity properties from external ontologies via entity linking. Expand
Genre Separation Network with Adversarial Training for Cross-genre Relation Extraction
TLDR
A genre-separation network is designed, which applies two encoders, one genre-independent and onegenre-shared, to explicitly extract genre-specific and genre-agnostic features, and which outperforms the state-of-the-art by 1.7% absolute F1 gain. Expand
Bridge Text and Knowledge by Learning Multi-Prototype Entity Mention Embedding
TLDR
A novel Multi-Prototype Mention Embedding model is proposed, which learns multiple sense embeddings for each mention by jointly modeling words from textual contexts and entities derived from a knowledge base, and an efficient language model based approach to disambiguate each mention to a specific sense. Expand
Zero-Shot Transfer Learning for Event Extraction
TLDR
A transferable architecture of structural and compositional neural networks is designed to jointly represent and map event mentions and types into a shared semantic space and can select, for each event mention, the event type which is semantically closest in this space as its type. Expand
...
1
2
3
4
5
...