paper-with-me

홈 › Papers

BERTRAM: Improved Word Embeddings Have Big Impact on Contextualized Model Performance

2019-10-16 · ACL 2020 6 · Timo Schick, Hinrich Schütze

Pretraining deep language models has led to large performance gains in NLP. Despite this success, Schick and Sch\"utze (2020) recently showed that these models struggle to understand rare words. For static word embeddings, this problem has been addressed by separately learning representations for rare words. In this work, we transfer this idea to pretrained language models: We introduce BERTRAM, a powerful architecture based on BERT that is capable of inferring high-quality embeddings for rare words that are suitable as input representations for deep language models. This is achieved by enabling the surface form and contexts of a word to interact with each other in a deep architecture. Integrating BERTRAM into BERT leads to large performance increases due to improved representations of rare and medium frequency words on both a rare word probing task and three downstream tasks.

📄 PDF Abstract BibTeX arXiv:1910.07181

Code (1)

timoschick/bertram 공식 구현 pytorch

Tasks

Language ModellingWord Embeddings

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Weight Decay 설명 없음
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
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…
Adam 설명 없음

Similar Papers 제목 키워드 기반

drsphelps at SemEval-2022 Task 2: Learning idiom representations using BERTRAM

2022-04-06 · SemEval (NAACL) 2022 7 · Dylan Phelps

This paper describes our system for SemEval-2022 Task 2 Multilingual Idiomaticity Detection and Sentence Embedding sub-task B. We modify a standard BERT sentence transformer by adding embeddings for each idioms, which ar…

SentenceSentence EmbeddingSentence-EmbeddingTask 2

Sample Efficient Approaches for Idiomaticity Detection

2022-05-23 · LREC (MWE) 2022 6 · Dylan Phelps, Xuan-Rui Fan, Edward Gow-Smith, Harish Tayyar Madabushi 외

Deep neural models, in particular Transformer-based pre-trained language models, require a significant amount of data to train. This need for data tends to lead to problems when dealing with idiomatic multiword expressio…

Unsupervised Morphological Expansion of Small Datasets for Improving Word Embeddings

2017-11-15 · Syed Sarfaraz Akhtar, Arihant Gupta, Avijit Vajpayee, Arjit Srivastava 외

We present a language independent, unsupervised method for building word embeddings using morphological expansion of text. Our model handles the problem of data sparsity and yields improved word embeddings by relying on …

Word EmbeddingsWord Similarity

Improving the Accuracy of Pre-trained Word Embeddings for Sentiment Analysis

2017-11-23 · Seyed Mahdi Rezaeinia, Ali Ghodsi, Rouhollah Rahmani

Sentiment analysis is one of the well-known tasks and fast growing research areas in natural language processing (NLP) and text classifications. This technique has become an essential part of a wide range of applications…

MarketingPart-Of-Speech TaggingPOSPOS Tagging+3

Evaluating the Underlying Gender Bias in Contextualized Word Embeddings

2019-04-18 · WS 2019 8 · Christine Basta, Marta R. Costa-jussà, Noe Casas

Gender bias is highly impacting natural language processing applications. Word embeddings have clearly been proven both to keep and amplify gender biases that are present in current data sources. Recently, contextualized…

SentenceWord Embeddings