Multi-task Domain Adaptation for Sequence Tagging

By Nanyun Peng, Mark Dredze. 2016

96 citations recorded by the source corpus.

Many domain adaptation approaches rely on learning cross domain shared representations to transfer the knowledge learned in one domain to other domains. Traditional domain adaptation only considers adapting for one task. In this paper, we explore multi-task representation learning under the domain adaptation scenario. We propose a neural network framework that supports domain adaptation for multiple tasks simultaneously, and learns shared representations that better generalize for domain adaptation. We apply the proposed framework to domain adaptation for sequence tagging problems considering two tasks: Chinese word segmentation and named entity recognition. Experiments show that multi-task domain adaptation works better than disjoint domain adaptation for each task, and achieves the state-of-the-art results for both tasks in the social media domain.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

Citations in the corpus

A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference (2017, background): “, 2007), including sequence and part-of-speech tagging (Blitzer et al., 2006; Peng and Dredze, 2017).”
Multi-Domain Multi-Task Rehearsal for Lifelong Learning (2020, methodology): “By considering both multiple domains and multiple tasks, Multi-domain multi-task (MDMT) learning was first proposed in (Yang and Hospedales 2014), and has been applied to classification (Peng and Dredze 2016) and semantic segmentation (Fourure et al. 2017), etc..”
A Survey on Deep Learning for Named Entity Recognition (2018, background): “Peng and Dredze [161] explored transfer learning in a multi-task learning setting, where they considered two domains: news and social media, for two tasks: word segmentation and NER.”
Neural Unsupervised Domain Adaptation in NLP—A Survey (2020, unknown): “, 2019) Cross-domain LM 3 (Cui and Bollegala, 2019) SelfAdapt (pivots+co-training) 3 (Peng and Dredze, 2017) Multi-task-DA 3 3 (Guo et al.”
Multi-task Learning for Universal Sentence Embeddings: A Thorough Evaluation using Transfer and Auxiliary Tasks (2018, background): “ wide-range of natural language processing (NLP) applications, including text classiﬁcation (Liu et al.,2017), machine translation (Luong et al.,2016), sequence labeling (Rei,2017), sequence tagging (Peng and Dredze, 2017), dependency parsing (Peng et al.,2017) etc. Recently,Mou et al.(2016) evaluat”