Design Challenges in Named Entity Transliteration (C18-1)

Copied to clipboard

Challenge: Named entity transliteration is an important component in many search and language understanding tasks.
Approach: They empirically evaluate a named entity transliteration task using traditional methods . they use a stack of convolutional layers to create a neural network with a new approach .
Outcome: The proposed system outperforms two neural approaches in the named entity transliteration task.

Similar Papers

Cross-lingual Named Entity List Search via Transliteration (2020.lrec-1)

Copied to clipboard

Challenge: a common way to adapt out-of-vocabulary words is a challenge in cross-lingual tasks . intrinsic evaluation, i.e comparison to a single gold standard, might not be appropriate in the task of transliteration due to its high variability.
Approach: They propose to train Transformer-based multilingual transliteration models on 6 high- and 4 less-resourced languages and compare them with bilingual models.
Outcome: The proposed model outperforms bilingual models on less-resourced languages.
What Matters for Neural Cross-Lingual Named Entity Recognition: An Empirical Analysis (D19-1)

Copied to clipboard

Challenge: Named entity recognition models are challenging for languages with little training data.
Approach: They propose a simple and efficient neural architecture for cross-lingual named entity recognition models.
Outcome: The proposed model achieves competitive performance with the state-of-the-art on two transferable factors: sequential order and multilingual embedding.
Towards a Broad Coverage Named Entity Resource: A Data-Efficient Approach for Many Diverse Languages (2022.lrec-1)

Copied to clipboard

Challenge: Existing methods to extract named entity datasets from parallel corpora require large monolingual corporata or word aligners that are unavailable or perform poorly for underresourced languages.
Approach: They propose a method for creating a multilingual named entity resource from parallel corpora and apply it to the Parallel Bible Corpus, a corpus of more than 1000 languages.
Outcome: The proposed method outperforms existing methods in two tasks.
TRANSLIT: A Large-scale Name Transliteration Resource (2020.lrec-1)

Copied to clipboard

Challenge: Transliteration is the process of expressing a proper name from a source language in the characters of a target language.
Approach: They present a large-scale corpus of transliterated names in 180 languages . they use machine learning to train automatic transliteration .
Outcome: The proposed system achieves 92% accuracy on identification of transliterated pairs.
Investigation on Data Adaptation Techniques for Neural Named Entity Recognition (2021.acl-srw)

Copied to clipboard

Challenge: Existing methods for named entity recognition use only a limited number of samples . data augmentation and selftraining are popular methods to generate additional synthetic data .
Approach: They investigate the impact of data augmentation and data augmented on named entity recognition tasks.
Outcome: The proposed methods improve the performance of three named entity recognition tasks.
A Myanmar (Burmese)-English Named Entity Transliteration Dictionary (2020.lrec-1)

Copied to clipboard

Challenge: Currently, there are no data available for the transcription of borrowed English words in Myanmar . lack of resources is a problem for many understudied languages .
Approach: They construct a dictionary of Myanmar-English transliteration instances using a CC BY-NC-SA license.
Outcome: The proposed model outperforms the statistical model significantly on the character level.
ParaNames 1.0: Creating an Entity Name Corpus for 400+ Languages Using Wikidata (2024.lrec-main)

Copied to clipboard

Challenge: ParaNames is a massively multilingual parallel name resource . it provides names for 16.8 million entities in over 400 languages .
Approach: They propose a massively multilingual parallel name resource with 140 million names . they use Wikidata to standardize the data and perform canonical name translation .
Outcome: The proposed resource is the largest of its type to date and performs well on 10 languages.
Sources of Transfer in Multilingual Named Entity Recognition (2020.acl-main)

Copied to clipboard

Challenge: naive training of named-entity recognition models using annotated data from multiple languages consistently underperforms monolingual models.
Approach: They propose a polyglot named-entity recognition model where one model is trained using annotated data drawn from multiple languages.
Outcome: The proposed model outperforms models trained on monolingual data despite more training data . the proposed model shares many parameters across languages and fine-tunes them to outperFORM monolingual models.
An Analysis of Simple Data Augmentation for Named Entity Recognition (2020.coling-main)

Copied to clipboard

Challenge: Recent studies have focused on using data augmentation techniques on sentence-level and sentence-pair natural language processing tasks such as text classification.
Approach: They propose to use data augmentation techniques for named entity recognition to increase model performance.
Outcome: The proposed techniques boost performance for both recurrent and transformer-based models, especially for small training sets.
Entity Linking in 100 Languages (2020.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to multilingual entity linking are cross-lingual, with a focus on zero-shot evaluation.
Approach: They propose a new formulation for multilingual entity linking where language-specific mentions resolve to a language-agnostic Knowledge Base.
Outcome: The proposed model outperforms state-of-the-art models on a large multilingual dataset and shows that frequency-based analysis provided key insights for the model and training enhancements.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations