conftrace_

2018 ACL ACL 2018

IIT (BHU) Submission for the ACL Shared Task on Named Entity Recognition on Code-switched Data

Abstract

AbstractThis paper describes the best performing system for the shared task on Named Entity Recognition (NER) on code-switched data for the language pair Spanish-English (ENG-SPA). We introduce a gated neural architecture for the NER task. Our final model achieves an F1 score of 63.76%, outperforming the baseline by 10%.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Natural Language Processing

Authors

Shashwat Trivedi, Harsh Rangwani, Anil Kumar Singh

Topics

Deep Learning > Architectures > Neural Networks Natural Language Processing > Understanding > Named Entity Recognition Natural Language Processing > Resources & Methods > Multilingual NLP Deep Learning > Architectures > Recurrent Neural Networks

Keywords

named entity recognition deep learning code-switched data gated neural architecture multilingual ner ner task gated neural network neural network

More from ACL 2018

All ACL 2018 papers →

Tackling Code-Switched NER: Participation of CMU

Multilingual Named Entity Recognition on Spanish-English Code-switched Tweets using Support Vector Machines

Named Entity Recognition on Code-Switched Data: Overview of the CALCS 2018 Shared Task

Code-Switched Named Entity Recognition with Embedding Attention

Getting the subtext without the text: Scalable multimodal sentiment classification from visual and acoustic modalities

Recognizing Emotions in Video Using Multimodal DNN Feature Fusion