paper-with-me

Papers

Lessons Learned from Applying off-the-shelf BERT: There is no Silver Bullet

2020-09-15 · Victor Makarenkov, Lior Rokach

One of the challenges in the NLP field is training large classification models, a task that is both difficult and tedious. It is even harder when GPU hardware is unavailable. The increased availability of pre-trained and off-the-shelf word embeddings, models, and modules aim at easing the process of training large models and achieving a competitive performance. We explore the use of off-the-shelf BERT models and share the results of our experiments and compare their results to those of LSTM networks and more simple baselines. We show that the complexity and computational cost of BERT is not a guarantee for enhanced predictive performance in the classification tasks at hand.

📄 PDF Abstract BibTeX arXiv:2009.07238

Code (0)

등록된 구현이 없습니다.

Tasks

ClassificationGeneral ClassificationGPUWord Embeddings

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
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 $x$…
Sigmoid Activation 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Tanh Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…
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

Building astroBERT, a language model for Astronomy & Astrophysics

2021-12-01 · Felix Grezes, Sergi Blanco-Cuaresma, Alberto Accomazzi, Michael J. Kurtz 외

The existing search tools for exploring the NASA Astrophysics Data System (ADS) can be quite rich and empowering (e.g., similar and trending operators), but researchers are not yet allowed to fully leverage semantic sear…

AstronomyLanguage ModelingLanguage Modellingmodel+3

NILC at SR’20: Exploring Pre-Trained Models in Surface Realisation

2020-12-01 · MSR (COLING) 2020 12 · Marco Antonio Sobrevilla Cabezudo, Thiago Pardo

This paper describes the submission by the NILC Computational Linguistics research group of the University of S ̃ao Paulo/Brazil to the English Track 2 (closed sub-track) at the Surface Realisation Shared Task 2020. The …

Data-to-Text GenerationText Generation

Incorporating Compositionality and Morphology into End-to-End Models

2021-08-01 · ACL (IWPT) 2021 8 · Emily Pitler

Many neural end-to-end systems today do not rely on syntactic parse trees, as much of the information that parse trees provide is encoded in the parameters of pretrained models. Lessons learned from parsing technologies …

Reading ComprehensionSemantic Parsing

Lessons Learned on Information Retrieval in Electronic Health Records: A Comparison of Embedding Models and Pooling Strategies

2024-09-23 · Skatje Myers, Timothy A. Miller, Yanjun Gao, Matthew M. Churpek 외

Objective: Applying large language models (LLMs) to the clinical domain is challenging due to the context-heavy nature of processing medical records. Retrieval-augmented generation (RAG) offers a solution by facilitating…

Information RetrievalRAGRetrievalRetrieval-augmented Generation

Coming to its senses: Lessons learned from Approximating Retrofitted BERT representations for Word Sense information

2021-05-16 · ACL ARR May 2021 5 · Anonymous

Retrofitting static vector space word representations using external knowledge bases has yielded substantial improvements in their lexical-semantic capacities but is non-trivial to apply to contextual word embeddings (CW…

Word Embeddings