paper-with-me

Papers

All Birds with One Stone: Multi-task Text Classification for Efficient Inference with One Forward Pass

2022-05-22 · Jiaxin Huang, Tianqi Liu, Jialu Liu, Adam D. Lelkes, Cong Yu, Jiawei Han

Multi-Task Learning (MTL) models have shown their robustness, effectiveness, and efficiency for transferring learned knowledge across tasks. In real industrial applications such as web content classification, multiple classification tasks are predicted from the same input text such as a web article. However, at the serving time, the existing multitask transformer models such as prompt or adaptor based approaches need to conduct N forward passes for N tasks with O(N) computation cost. To tackle this problem, we propose a scalable method that can achieve stronger performance with close to O(1) computation cost via only one forward pass. To illustrate real application usage, we release a multitask dataset on news topic and style classification. Our experiments show that our proposed method outperforms strong baselines on both the GLUE benchmark and our news dataset. Our code and dataset are publicly available at https://bit.ly/mtop-code.

📄 PDF Abstract BibTeX arXiv:2205.10744

Code (0)

등록된 구현이 없습니다.

Tasks

AllClassificationMulti-Task Learningtext-classificationText Classification

Similar Papers 제목 키워드 기반

ECNU: One Stone Two Birds: Ensemble of Heterogenous Measures for Semantic Relatedness and Textual Entailment

2014-08-01 · SEMEVAL 2014 8 · Jiang Zhao, Tiantian Zhu, Man Lan
Natural Language InferenceSemantic Textual Similarity

Two Birds, One Stone: A Simple, Unified Model for Text Generation from Structured and Unstructured Data

2019-09-23 · ACL 2020 6 · Hamidreza Shahidi, Ming Li, Jimmy Lin

A number of researchers have recently questioned the necessity of increasingly complex neural network (NN) architectures. In particular, several recent papers have shown that simpler, properly tuned models are at least c…

Question GenerationQuestion-GenerationTable-to-Text GenerationText Generation

Killing Four Birds with Two Stones: Multi-Task Learning for Non-Literal Language Detection

2018-08-01 · COLING 2018 8 · Erik-L{\^a}n Do Dinh, Steffen Eger, Iryna Gurevych

Non-literal language phenomena such as idioms or metaphors are commonly studied in isolation from each other in NLP. However, often similar definitions and features are being used for different phenomena, challenging the…

General ClassificationMulti-Task Learning

280 Birds with One Stone: Inducing Multilingual Taxonomies from Wikipedia using Character-level Classification

2017-04-25 · Amit Gupta, Rémi Lebret, Hamza Harkous, Karl Aberer

We propose a simple, yet effective, approach towards inducing multilingual taxonomies from Wikipedia. Given an English taxonomy, our approach leverages the interlanguage links of Wikipedia followed by character-level cla…

General Classification

Transduction with Matrix Completion: Three Birds with One Stone

2010-12-01 · NeurIPS 2010 12 · Andrew Goldberg, Ben Recht, Jun-Ming Xu, Robert Nowak 외

We pose transductive classification as a matrix completion problem. By assuming the underlying matrix has a low rank, our formulation is able to handle three problems simultaneously: i) multi-label learning, where each i…

General ClassificationMatrix CompletionMulti-Label Learning