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

Aguilar, Gustavo; AlGhamdi, Fahad; Soto, Víctor; Diab, Mona; Hirschberg, Julia; Solorio, Thamar

doi:10.18653/v1/w18-3219

Cited by 60 publications

(69 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Besides, CRF mainly focuses on the transition probability of each word, and it does not pay enough attention to the name entity attributes of the word. Now, most of the NER methods are based on sequence labelling [12,16,17,18,19,20]. These methods classify every word in the corpus into different categories.…”

Section: Named Entity Recognitionmentioning

confidence: 99%

ASTRAL: Adversarial Trained LSTM-CNN for Named Entity Recognition

Wang

et al. 2020

Knowledge-Based Systems

View full text Add to dashboard Cite

Named Entity Recognition (NER) is a challenging task that extracts named entities from unstructured text data, including news, articles, social comments, etc. The NER system has been studied for decades. Recently, the development of Deep Neural Networks and the progress of pre-trained word embedding have become a driving force for NER. Under such circumstances, how to make full use of the information extracted by word embedding requires more in-depth research. In this paper, we propose an Adversarial Trained LSTM-CNN (ASTRAL) system to improve the current NER method from both the model structure and the training process. In order to make use of the spatial information between adjacent words, Gated-CNN is introduced to fuse the information of adjacent words. Besides, a specific Adversarial training method is proposed to deal with the overfitting problem in NER. We add perturbation to variables in the network during the training process, making the variables more diverse, improving the generalization and robustness of the model. Our model is evaluated on three benchmarks, CoNLL-03, OntoNotes 5.0, and WNUT-17, achieving state-of-theart results. Ablation study and case study also show that our system can converge faster and is less prone to overfitting.

show abstract

Section: Named Entity Recognitionmentioning

confidence: 99%

ASTRAL: Adversarial Trained LSTM-CNN for Named Entity Recognition

Wang

et al. 2020

Knowledge-Based Systems

View full text Add to dashboard Cite

show abstract

“…For our experiment, we use English-Spanish tweets data provided by Aguilar et al (2018). There are nine entity labels.…”

Section: Experiments 41 Datasetmentioning

confidence: 99%

“…Code-Switching is produced in both written text and speech in a discourse. Recent studies in code-switching has been mainly focused on natural language tasks, such as language modeling (Winata et al, 2018a;Pratapa et al, 2018;Garg et al, 2018), named entity recognition (Aguilar et al, 2018), and language identification (Solorio et al, 2014;Molina et al, 2016;Barman et al, 2014). Code-Switching is considered as a challenging task because words from different languages may co-exist within a sequence, and models are required to recognize the context of mixed-language sentences.…”

Section: Introductionmentioning

confidence: 99%

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

Winata¹,

Lin²,

Fung³

2019

Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019)

View full text Add to dashboard Cite

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.

show abstract

“…2016; Aguilar et al . 2018), and distinguishing between very similar languages, or varieties and/or dialects of the same language, as for example, pursued in the VarDial/DSL series of workshops and shared tasks (Zampieri et al . 2014; Zampieri et al .…”

Section: Introductionmentioning

confidence: 99%

Domain bias in distinguishing Flemish and Dutch subtitles

Halteren

2019

Nat. Lang. Eng.

View full text Add to dashboard Cite

This paper describes experiments in which I tried to distinguish between Flemish and Netherlandic Dutch subtitles, as originally proposed in the VarDial 2018 Dutch–Flemish Subtitle task. However, rather than using all data as a monolithic block, I divided them into two non-overlapping domains and then investigated how the relation between training and test domains influences the recognition quality. I show that the best estimate of the level of recognizability of the language varieties is derived when training on one domain and testing on another. Apart from the quantitative results, I also present a qualitative analysis, by investigating in detail the most distinguishing features in the various scenarios. Here too, it is with the out-of-domain recognition that some genuine differences between Flemish and Netherlandic Dutch can be found.

show abstract

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

Cited by 60 publications

References 24 publications

ASTRAL: Adversarial Trained LSTM-CNN for Named Entity Recognition

ASTRAL: Adversarial Trained LSTM-CNN for Named Entity Recognition

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

Domain bias in distinguishing Flemish and Dutch subtitles

Contact Info

Product

Resources

About