CLJan 31, 2019

Multi-Task Deep Neural Networks for Natural Language Understanding

arXiv:1901.11504v21648 citationsHas Code
Originality Incremental advance
AI Analysis

This work addresses the challenge of domain adaptation and generalization in NLU for researchers and practitioners, showing incremental improvements over existing methods.

The paper tackles the problem of learning general representations for natural language understanding across multiple tasks by extending a previous model with BERT, achieving new state-of-the-art results on ten NLU tasks, including an absolute improvement of 2.2% on the GLUE benchmark to 82.7%.

In this paper, we present a Multi-Task Deep Neural Network (MT-DNN) for learning representations across multiple natural language understanding (NLU) tasks. MT-DNN not only leverages large amounts of cross-task data, but also benefits from a regularization effect that leads to more general representations in order to adapt to new tasks and domains. MT-DNN extends the model proposed in Liu et al. (2015) by incorporating a pre-trained bidirectional transformer language model, known as BERT (Devlin et al., 2018). MT-DNN obtains new state-of-the-art results on ten NLU tasks, including SNLI, SciTail, and eight out of nine GLUE tasks, pushing the GLUE benchmark to 82.7% (2.2% absolute improvement). We also demonstrate using the SNLI and SciTail datasets that the representations learned by MT-DNN allow domain adaptation with substantially fewer in-domain labels than the pre-trained BERT representations. The code and pre-trained models are publicly available at https://github.com/namisan/mt-dnn.

Code Implementations7 repos

Data from Papers with Code (CC-BY-SA-4.0)

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes