paper-with-me

홈 › Papers

Same Representation, Different Attentions: Shareable Sentence Representation Learning from Multiple Tasks

2018-04-22 · Renjie Zheng, Junkun Chen, Xipeng Qiu

Distributed representation plays an important role in deep learning based natural language processing. However, the representation of a sentence often varies in different tasks, which is usually learned from scratch and suffers from the limited amounts of training data. In this paper, we claim that a good sentence representation should be invariant and can benefit the various subsequent tasks. To achieve this purpose, we propose a new scheme of information sharing for multi-task learning. More specifically, all tasks share the same sentence representation and each task can select the task-specific information from the shared sentence representation with attention mechanism. The query vector of each task's attention could be either static parameters or generated dynamically. We conduct extensive experiments on 16 different text classification tasks, which demonstrate the benefits of our architecture.

📄 PDF Abstract BibTeX arXiv:1804.08139

Code (0)

등록된 구현이 없습니다.

Tasks

General ClassificationMulti-Task LearningRepresentation LearningSentencetext-classificationText Classification

Similar Papers 제목 키워드 기반

Distant Supervision Relation Extraction with Intra-Bag and Inter-Bag Attentions

2019-03-30 · NAACL 2019 6 · Zhi-Xiu Ye, Zhen-Hua Ling

This paper presents a neural relation extraction method to deal with the noisy training data generated by distant supervision. Previous studies mainly focus on sentence-level de-noising by designing neural networks with …

RelationRelation ExtractionSentenceSentence Embeddings

Multi-Player Multi-Armed Bandits with Finite Shareable Resources Arms: Learning Algorithms & Applications

2022-04-28 · Xuchuang Wang, Hong Xie, John C. S. Lui

Multi-player multi-armed bandits (MMAB) study how decentralized players cooperatively play the same multi-armed bandit so as to maximize their total cumulative rewards. Existing MMAB models mostly assume when more than o…

Edge-computingMulti-Armed Bandits

Exemplar Based Deep Discriminative and Shareable Feature Learning for Scene Image Classification

2015-08-21 · Zhen Zuo, Gang Wang, Bing Shuai, Lifan Zhao 외

In order to encode the class correlation and class specific information in image representation, we propose a new local feature learning approach named Deep Discriminative and Shareable Feature Learning (DDSFL). DDSFL ai…

General Classificationimage-classificationImage Classification

Cascading Multiway Attentions for Document-level Sentiment Classification

2017-11-01 · IJCNLP 2017 11 · Dehong Ma, Sujian Li, Xiaodong Zhang, Houfeng Wang 외

Document-level sentiment classification aims to assign the user reviews a sentiment polarity. Previous methods either just utilized the document content without consideration of user and product information, or did not c…

ClassificationGeneral ClassificationProduct RecommendationSentence+2

Multiple-Play Stochastic Bandits with Shareable Finite-Capacity Arms

2022-06-17 · Xuchuang Wang, Hong Xie, John C. S. Lui

We generalize the multiple-play multi-armed bandits (MP-MAB) problem with a shareable arm setting, in which several plays can share the same arm. Furthermore, each shareable arm has a finite reward capacity and a ''per-l…

Multi-Armed Bandits