• Publications
  • Influence
Recurrent Neural Network for Text Classification with Multi-Task Learning
TLDR
We use the multi-task learning framework to jointly learn across multiple related tasks with the help of other related tasks. Expand
Adversarial Multi-task Learning for Text Classification
TLDR
In this paper, we propose an adversarial multi-task learning framework, alleviating the shared and private latent feature spaces from interfering with each other. Expand
Long Short-Term Memory Neural Networks for Chinese Word Segmentation
TLDR
We propose a novel neural network model for Chinese word segmentation, which adopts the long short-term memory (LSTM) neural network to keep the previous important information inmemory cell and avoids the limit of window size of local context. Expand
Gated Recursive Neural Network for Chinese Word Segmentation
TLDR
We propose a gated recursive neural network (GRNN) for Chinese word segmentation, which contains reset and update gates to incorporate the complicated combinations of the context characters. Expand
Convolutional Neural Tensor Network Architecture for Community-Based Question Answering
TLDR
In this paper, we propose a convolutional neural tensor network architecture to encode the sentences in semantic space and model their interactions with a tensor layer. Expand
Utilizing BERT for Aspect-Based Sentiment Analysis via Constructing Auxiliary Sentence
TLDR
We fine-tune the pre-trained model from BERT and achieve new state-of-the-art results on SentiHood and SemEval-2014 Task 4 datasets. Expand
Reinforced Mnemonic Reader for Machine Reading Comprehension
TLDR
We present a reattention mechanism that temporally memorizes past attentions and uses them to refine current attentions in a multi-round alignment architecture. Expand
GlossBERT: BERT for Word Sense Disambiguation with Gloss Knowledge
TLDR
We construct context-gloss pairs from glosses of all possible senses (in WordNet) of the target word and propose three BERT-based models for WSD. Expand
How to Fine-Tune BERT for Text Classification?
TLDR
We propose ULMFiT, a fine-tuning method for pre-trained language model that achieves state-of-the-art results on six widely studied text classification datasets. Expand
Adversarial Multi-Criteria Learning for Chinese Word Segmentation
TLDR
We propose adversarial multi-criteria learning for CWS by integrating shared knowledge from multiple heterogeneous segmentation criteria. Expand
...
1
2
3
4
5
...