Fine-tuned Language Models for Text Classification
Explore this paper's citation graph
Summary
Fine-tuned Language Models (FitLaM) is proposed, an effective transfer learning method that can be applied to any task in NLP, and techniques that are key for fine-tuning a state-of-the-art language model are introduced.
- Type
- preprint
- Published
- 2018-01-18
- Cited by
- 286
- References
- 67
- Access
- Open access
- OpenAlex
- https://openalex.org/W2784121710
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:195346829
Keywords
Computer science, Scratch, Task (project management), Artificial intelligence, Language model
References
- Deep Boltzmann Machines
- Estimation of Dependences Based on Empirical Data
- Convolutional Neural Networks for Sentence Classification
- Fully convolutional networks for semantic segmentation
- Hypercolumns for object segmentation and fine-grained localization
- CNN Features Off-the-Shelf: An Astounding Baseline for Recognition
- Detecting Automation of Twitter Accounts: Are You a Human, Bot, or Cyborg?
- The application of data mining techniques in financial fraud detection: A classification framework and an academic review of literature
- Learning Word Vectors for Sentiment Analysis
- Review spam detection
- Distributed Representations of Words and Phrases and their Compositionality
- Learning Transferable Features with Deep Adaptation Networks
- A Model of Inductive Bias Learning
- Biographies, Bollywood, Boom-boxes and Blenders: Domain Adaptation for Sentiment Classification
- ImageNet classification with deep convolutional neural networks
- A Survey on Transfer Learning
- UNITN: Training Deep Convolutional Neural Network for Twitter Sentiment Classification
- Character-level Convolutional Networks for Text Classification
- Deep Residual Learning for Image Recognition
- GloVe: Global Vectors for Word Representation
Cited by
- AllenNLP: A Deep Semantic Natural Language Processing Platform
- Meta-Learning a Dynamical Language Model
- Clinical Concept Embeddings Learned from Massive Sources of Medical Data
- NTUA-SLP at SemEval-2018 Task 1: Predicting Affective Content in Tweets with Deep Attentive RNNs and Transfer Learning
- Continuous Learning in a Hierarchical Multiscale Neural Network
- Clinical Concept Embeddings Learned from Massive Sources of Multimodal Medical Data
- A Simple Method for Commonsense Reasoning
- NILC at CWI 2018: Exploring Feature Engineering and Feature Learning
- Evaluation of sentence embeddings in downstream and linguistic probing tasks
- The Natural Language Decathlon: Multitask Learning as Question Answering
- Resolving Abstract Anaphora Implicitly in Conversational Assistants using a Hierarchically stacked RNN
- Large Scale Language Modeling: Converging on 40GB of Text in Four Hours
- Techniques for interpretable machine learning
- Deep Neural Networks for Multi-Label Text Classification: Application to Coding Electronic Medical Records
- Using Translated Data to Improve Deep Learning Author Profiling Models: Notebook for PAN at CLEF 2018
- All You Need is "Love": Evading Hate Speech Detection
- SHOMA at Parseme Shared Task on Automatic Identification of VMWEs: Neural Multiword Expression Tagging with High Generalisation
- NTUA-SLP at IEST 2018: Ensemble of Neural Transfer Methods for Implicit Emotion Classification
- XNLI: Evaluating Cross-lingual Sentence Representations
- Robotic Process Automation of Unstructured Data with Machine Learning
Related papers
- RoBERTa: A Robustly Optimized BERT Pretraining Approach
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
- Deep Contextualized Word Representations
- GloVe: Global Vectors for Word Representation
- Distributed Representations of Words and Phrases and their Compositionality
- Long Short-Term Memory
- Deep Residual Learning for Image Recognition