Learning Multilingual Meta-Embeddings for Code-Switching Named Entity Recognition

2019-08-01 · WS 2019 8 · Genta Indra Winata, Zhaojiang Lin, Pascale Fung

In this paper, we propose Multilingual Meta-Embeddings (MME), an effective method to learn multilingual representations by leveraging monolingual pre-trained embeddings. MME learns to utilize information from these embeddings via a self-attention mechanism without explicit language identification. We evaluate the proposed embedding method on the code-switching English-Spanish Named Entity Recognition dataset in a multilingual and cross-lingual setting. The experimental results show that our proposed method achieves state-of-the-art performance on the multilingual setting, and it has the ability to generalize to an unseen language task.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Language IdentificationMMEnamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)

Are Multilingual Models Effective in Code-Switching?

2021-03-24 · NAACL (CALCS) 2021 6 · Genta Indra Winata, Samuel Cahyawijaya, Zihan Liu, Zhaojiang Lin 외

Multilingual language models have shown decent performance in multilingual and cross-lingual natural language understanding tasks. However, the power of these multilingual models in code-switching tasks has not been full…

named-entity-recognition Named Entity Recognition Named Entity Recognition (NER)Natural Language Understanding+1

Hierarchical Meta-Embeddings for Code-Switching Named Entity Recognition

2019-09-18 · IJCNLP 2019 11 · Genta Indra Winata, Zhaojiang Lin, Jamin Shin, Zihan Liu 외

In countries that speak multiple main languages, mixing up different languages within a conversation is commonly called code-switching. Previous works addressing this challenge mainly focused on word-level aspects such a…

named-entity-recognition Named Entity Recognition Named Entity Recognition (NER)Word Embeddings

Multilingual Transfer Learning for Code-Switched Language and Speech Neural Modeling

2021-04-13 · Genta Indra Winata

In this thesis, we address the data scarcity and limitations of linguistic theory by proposing language-agnostic multi-task training methods. First, we introduce a meta-learning-based approach, meta-transfer learning, in…

Data Augmentation Language Modelling Meta-Learning Multi-Task Learning+1

GLUECoS: An Evaluation Benchmark for Code-Switched NLP

2020-07-01 · ACL 2020 6 · Simran Khanuja, D, S apat, ipan 외

Code-switching is the use of more than one language in the same conversation or utterance. Recently, multilingual contextual embedding models, trained on multiple monolingual corpora, have shown promising results on cros…

Language Identification named-entity-recognition Named Entity Recognition Named Entity Recognition (NER)+5

GLUECoS : An Evaluation Benchmark for Code-Switched NLP

2020-04-26 · Simran Khanuja, Sandipan Dandapat, Anirudh Srinivasan, Sunayana Sitaram 외