paper-with-me

홈 › Papers

Syntactic Relevance XLNet Word Embedding Generation in Low-Resource Machine Translation

2021-01-01 · Nier Wu, Yatu Ji, Hongxu Hou

Semantic understanding is an important factor affecting the quality of machine translation of low resource agglutination language. The common methods(sub-word modeling, pre-training word embedding, etc.) will increase the length of the sequence, which leads to a surge in computation. At the same time, the pre-training word embedding with rich context is also the precondition to improve the semantic understanding. Although BERT uses masked language model to generate dynamic embedding in parallel, however, the fine-tuning strategy without mask will make it inconsistent with the training data, which produced human error. Therefore, we proposed a word embedding generation method based on improved XLNet, it corrects the defects of the BERT model, and improves the sampling redundancy issues in traditional XLNet. Experiments are carried out on CCMT2019 Mongolian-Chinese, Uyghur-Chinese and Tibetan-Chinese tasks, the results show that the generalization ability and BLEU scores of our method are improved compared with the baseline, which fully verifies the effectiveness of the method.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingMachine TranslationTranslation

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
WordPiece 설명 없음
Multi-Head Attention 설명 없음
Weight Decay 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

Part-of-Speech Relevance Weights for Learning Word Embeddings

2016-03-24 · Quan Liu, Zhen-Hua Ling, Hui Jiang, Yu Hu

This paper proposes a model to learn word embeddings with weighted contexts based on part-of-speech (POS) relevance weights. POS is a fundamental element in natural language. However, state-of-the-art word embedding mode…

Learning Word EmbeddingsPOSPositionWord Embeddings+1

Relevance-based Word Embedding

2017-05-09 · Hamed Zamani, W. Bruce Croft

Learning a high-dimensional dense representation for vocabulary terms, also known as a word embedding, has recently attracted much attention in natural language processing and information retrieval tasks. The embedding v…

General ClassificationInformation RetrievalRetrievalSemantic Similarity+1

XLNET-GRU Sentiment Regression Model for Cryptocurrency News in English and Malay

2022-06-01 · FNP (LREC) 2022 6 · Nur Azmina Mohamad Zamani, Jasy Suet Yan Liew, Ahmad Muhyiddin Yusof

Contextual word embeddings such as the transformer language models are gaining popularity in text classification and analytics but have rarely been explored for sentiment analysis on cryptocurrency news particularly on l…

regressionSentiment Analysistext-classificationText Classification+1

CogNLP-Sheffield at CMCL 2021 Shared Task: Blending Cognitively Inspired Features with Transformer-based Language Models for Predicting Eye Tracking Patterns

2021-06-01 · NAACL (CMCL) 2021 6 · Peter Vickers, Rosa Wainwright, Harish Tayyar Madabushi, Aline Villavicencio

The CogNLP-Sheffield submissions to the CMCL 2021 Shared Task examine the value of a variety of cognitively and linguistically inspired features for predicting eye tracking patterns, as both standalone model inputs and a…

Word Embeddings

Word Embeddings for Sentiment Analysis: A Comprehensive Empirical Survey

2019-02-02 · Erion Çano, Maurizio Morisio

This work investigates the role of factors like training method, training corpus size and thematic relevance of texts in the performance of word embedding features on sentiment analysis of tweets, song lyrics, movie revi…

Sentiment AnalysisSurveyWord Embeddings