paper-with-me

홈 › Papers

High Quality ELMo Embeddings for Seven Less-Resourced Languages

2019-11-22 · Matej Ulčar, Marko Robnik-Šikonja

Recent results show that deep neural networks using contextual embeddings significantly outperform non-contextual embeddings on a majority of text classification task. We offer precomputed embeddings from popular contextual ELMo model for seven languages: Croatian, Estonian, Finnish, Latvian, Lithuanian, Slovenian, and Swedish. We demonstrate that the quality of embeddings strongly depends on the size of training set and show that existing publicly available ELMo embeddings for listed languages shall be improved. We train new ELMo embeddings on much larger training sets and show their advantage over baseline non-contextual FastText embeddings. In evaluation, we use two benchmarks, the analogy task and the NER task.

📄 PDF Abstract BibTeX arXiv:1911.10049

Code (0)

등록된 구현이 없습니다.

Tasks

NERtext-classificationText ClassificationVocal Bursts Intensity Prediction

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
fastText fastText embeddings exploit subword information to construct word embeddings. Representations are learnt of character $n$-grams, and words represented as the sum of the…
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…
BiLSTM A Bidirectional LSTM, or biLSTM, is a sequence processing model that consists of two LSTMs: one taking the input in a forward direction, and the other in a backwards…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
ELMo Embeddings from Language Models, or ELMo, is a type of deep contextualized word representation that models both (1) complex characteristics of word use (e.g., syntax and…

Similar Papers 제목 키워드 기반

High Quality ELMo Embeddings for Seven Less-Resourced Languages

2020-05-01 · LREC 2020 5 · Matej Ul{\v{c}}ar, Marko Robnik-{\v{S}}ikonja

Recent results show that deep neural networks using contextual embeddings significantly outperform non-contextual embeddings on a majority of text classification task. We offer precomputed embeddings from popular context…

NERtext-classificationText ClassificationVocal Bursts Intensity Prediction

Cross-lingual alignments of ELMo contextual embeddings

2021-06-30 · Matej Ulčar, Marko Robnik-Šikonja

Building machine learning prediction models for a specific NLP task requires sufficient training data, which can be difficult to obtain for less-resourced languages. Cross-lingual embeddings map word embeddings from a le…

Dependency Parsingnamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)+3

Evaluation of contextual embeddings on less-resourced languages

2021-07-22 · Matej Ulčar, Aleš Žagar, Carlos S. Armendariz, Andraž Repar 외

The current dominance of deep neural networks in natural language processing is based on contextual embeddings such as ELMo, BERT, and BERT derivatives. Most existing work focuses on English; in contrast, we present here…

Dependency Parsing

Gender Bias in Contextualized Word Embeddings

2019-04-05 · NAACL 2019 6 · Jieyu Zhao, Tianlu Wang, Mark Yatskar, Ryan Cotterell 외

In this paper, we quantify, analyze and mitigate gender bias exhibited in ELMo's contextualized word vectors. First, we conduct several intrinsic analyses and find that (1) training data for ELMo contains significantly m…

Word Embeddings

Shallow Syntax in Deep Water

2019-08-29 · Swabha Swayamdipta, Matthew Peters, Brendan Roof, Chris Dyer 외

Shallow syntax provides an approximation of phrase-syntactic structure of sentences; it can be produced with high accuracy, and is computationally cheap to obtain. We investigate the role of shallow syntax-aware represen…