paper-with-me

홈 › Papers

Practical Text Classification With Large Pre-Trained Language Models

2018-12-04 · Neel Kant, Raul Puri, Nikolai Yakovenko, Bryan Catanzaro

Multi-emotion sentiment classification is a natural language processing (NLP) problem with valuable use cases on real-world data. We demonstrate that large-scale unsupervised language modeling combined with finetuning offers a practical solution to this task on difficult datasets, including those with label class imbalance and domain-specific context. By training an attention-based Transformer network (Vaswani et al. 2017) on 40GB of text (Amazon reviews) (McAuley et al. 2015) and fine-tuning on the training set, our model achieves a 0.69 F1 score on the SemEval Task 1:E-c multi-dimensional emotion classification problem (Mohammad et al. 2018), based on the Plutchik wheel of emotions (Plutchik 1979). These results are competitive with state of the art models, including strong F1 scores on difficult (emotion) categories such as Fear (0.73), Disgust (0.77) and Anger (0.78), as well as competitive results on rare categories such as Anticipation (0.42) and Surprise (0.37). Furthermore, we demonstrate our application on a real world text classification task. We create a narrowly collected text dataset of real tweets on several topics, and show that our finetuned model outperforms general purpose commercially available APIs for sentiment and multidimensional emotion classification on this dataset by a significant margin. We also perform a variety of additional studies, investigating properties of deep learning architectures, datasets and algorithms for achieving practical multidimensional sentiment classification. Overall, we find that unsupervised language modeling and finetuning is a simple framework for achieving high quality results on real-world sentiment classification.

📄 PDF Abstract BibTeX arXiv:1812.01207

Code (1)

NVIDIA/sentiment-discovery pytorch

Tasks

ClassificationEmotion ClassificationGeneral ClassificationLanguage ModelingLanguage ModellingSentiment AnalysisSentiment Classificationtext-classificationText Classification

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Residual Connection 설명 없음
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…
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…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…

Similar Papers 제목 키워드 기반

Go Simple and Pre-Train on Domain-Specific Corpora: On the Role of Training Data for Text Classification

2020-12-01 · COLING 2020 8 · Aleksandra Edwards, Jose Camacho-Collados, H{\'e}l{\`e}ne De Ribaupierre, Alun Preece

Pre-trained language models provide the foundations for state-of-the-art performance across a wide range of natural language processing tasks, including text classification. However, most classification datasets assume a…

ClassificationLanguage ModelingLanguage Modellingtext-classification+2

Adversarial Evasion Attack Efficiency against Large Language Models

2024-06-12 · João Vitorino, Eva Maia, Isabel Praça

Large Language Models (LLMs) are valuable for text classification, but their vulnerabilities must not be disregarded. They lack robustness against adversarial examples, so it is pertinent to understand the impacts of dif…

Adversarial DefenseClassificationSentiment AnalysisSentiment Classification+2

DocSCAN: Unsupervised Text Classification via Learning from Neighbors

2021-05-09 · KONVENS (WS) 2022 9 · Dominik Stammbach, Elliott Ash

We introduce DocSCAN, a completely unsupervised text classification approach using Semantic Clustering by Adopting Nearest-Neighbors (SCAN). For each document, we obtain semantically informative vectors from a large pre-…

ClassificationClusteringGeneral ClassificationLanguage Modeling+6

C-3DPO: Constrained Controlled Classification for Direct Preference Optimization

2025-02-22 · Kavosh Asadi, Julien Han, Xingzi Xu, Dominique Perrault-Joncas 외

Direct preference optimization (DPO)-style algorithms have emerged as a promising approach for solving the alignment problem in AI. We present a novel perspective that formulates these algorithms as implicit classificati…

Classification

Vocabulary-free Image Classification and Semantic Segmentation

2024-04-16 · Alessandro Conti, Enrico Fini, Massimiliano Mancini, Paolo Rota 외

Large vision-language models revolutionized image classification and semantic segmentation paradigms. However, they typically assume a pre-defined set of categories, or vocabulary, at test time for composing textual prom…

Classificationimage-classificationImage ClassificationLanguage Modeling+4