A Hierarchical Multi-task Approach for Learning Embeddings from Semantic Tasks

@inproceedings{Sanh2018AHM,
  title={A Hierarchical Multi-task Approach for Learning Embeddings from Semantic Tasks},
  author={Victor Sanh and Thomas Wolf and Sebastian Ruder},
  booktitle={AAAI},
  year={2018}
}
Much effort has been devoted to evaluate whether multi-task learning can be leveraged to learn rich representations that can be used in various Natural Language Processing (NLP) down-stream applications. [...] Key Method The model is trained in a hierarchical fashion to introduce an inductive bias by supervising a set of low level tasks at the bottom layers of the model and more complex tasks at the top layers of the model. This model achieves state-of-the-art results on a number of tasks, namely Named Entity…Expand Abstract

Citations

Publications citing this paper.
SHOWING 1-10 OF 34 CITATIONS

DeepGeneMD: A Joint Deep Learning Model for Extracting Gene Mutation-Disease Knowledge from PubMed Literature

VIEW 10 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Reevaluating Argument Component Extraction in Low Resource Settings

VIEW 5 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Span-Level Model for Relation Extraction

VIEW 1 EXCERPT
CITES METHODS
HIGHLY INFLUENCED

Product Knowledge Graph Embedding for E-commerce

VIEW 1 EXCERPT
CITES METHODS

References

Publications referenced by this paper.
SHOWING 1-10 OF 44 REFERENCES

A Joint Model for Entity Analysis: Coreference, Typing, and Linking

VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Named Entity Recognition with Bidirectional LSTM-CNNs

VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

Incremental Joint Extraction of Entity Mentions and Relations

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL