---
title: "Character-level Convolutional Networks for Text — Zhang 2015"
description: "Most text classifiers of the time worked on words or word n-grams."
authors: ["Xiang Zhang", "Junbo Zhao", "Yann LeCun"]
year: 2015
venue: "arXiv:1509.01626"
source: "https://arxiv.org/abs/1509.01626"
doi: "10.48550/arxiv.1509.01626"
arxiv: "1509.01626"
licence: "arXiv — non-exclusive licence to distribute"
licence_url: "http://arxiv.org/licenses/nonexclusive-distrib/1.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/zhang-2015-character-level-convolutional-networks-text/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/zhang-2015-character-level-convolutional-networks-text/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2015](https://md.research.elamur.ai/free/en/papers/2015/) / Character-level Convolutional Networks for Text Classification

# Character-level Convolutional Networks for Text Classification

**Authors:** Xiang Zhang, [Junbo Zhao](https://md.research.elamur.ai/free/en/authors/junbo-zhao/), [Yann LeCun](https://md.research.elamur.ai/free/en/authors/yann-lecun/) · **Year:** 2015 · **Venue:** arXiv:1509.01626 · **Licence:** [arXiv — non-exclusive licence to distribute](http://arxiv.org/licenses/nonexclusive-distrib/1.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/1509.01626) · [PDF](https://arxiv.org/pdf/1509.01626) · [DOI 10.48550/arxiv.1509.01626](https://doi.org/10.48550/arxiv.1509.01626) · [arXiv 1509.01626](https://arxiv.org/abs/1509.01626) · [OpenAlex](https://openalex.org/W2170240176)

**Citations:** 3205 citations (openalex-snapshot · 2026-10-14) · [1548](#cited-by) in our library, of the 140884 papers whose bibliographies we read

## Summary
Most text classifiers of the time worked on words or word n-grams. This paper asks whether a deep convolutional network can classify documents when it sees only raw characters, with no tokenization and no knowledge of words, syntax or semantics. Each character is one-hot encoded over a fixed 70-symbol alphabet, and documents are cut to 1014 characters. A 9-layer temporal ConvNet then processes the input: 6 convolutional layers followed by 3 fully-connected layers, in a large and a small version. ConvNets need a lot of training data, so the authors built several large datasets covering news topics, ontology categories, Q&A topics and review sentiment. They compared the model with bag-of-words, n-gram and TFIDF baselines, with word-based ConvNets and with an LSTM. The character-level model was competitive or best on the million-sample datasets. Classic n-gram TFIDF still won on smaller ones. The work matters because it showed that text can be treated as a raw signal. That could make one system usable across languages and robust to noisy user-generated text.

## Key points
- New benchmark datasets: AG News, Sogou News, DBPedia, Yelp Review (Polarity/Full), Yahoo! Answers and Amazon Review (Full/Polarity). Amazon Polarity has 1.8M training samples per class.
- Architecture: 70-character alphabet, input length 1014, 6 conv layers (1024 features in the large model, 256 in the small) and 3 FC layers with dropout 0.5. Temporal max-pooling made networks deeper than 6 layers trainable.
- Data augmentation replaces words with synonyms from a WordNet-derived thesaurus (LibreOffice mytheas). The number of replacements and the synonym chosen are both drawn from geometric distributions with p = q = 0.5.
- Dataset size decides the winner. n-gram TFIDF stays strong up to a few hundred thousand samples, and the character-level ConvNet pulls ahead at millions of samples. It also does relatively well on less-curated texts such as Amazon reviews.
- Treating upper- and lower-case letters as the same often helped on large datasets. Bag-of-means over word2vec clusters was the weakest model in every comparison.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

Fields: [Computing & GPUs](https://md.research.elamur.ai/free/en/shelves/computing/)

## Cited by

Cited by

1548 papers of our library cite it (of the 140884 whose bibliographies we read); 105 of them have a page here, the first 100 below, 1443 not yet.

- [Detecting Suicidality in Arabic Tweets Using Machine Learning and Deep Learning Techniques](https://md.research.elamur.ai/free/en/papers/abdulsalam-2023-detecting-suicidality-arabic-tweets-using/)
- [Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning](https://md.research.elamur.ai/free/en/papers/aghajanyan-2021-intrinsic-dimensionality-explains-effectiveness-language/)
- [Muppet: Massive Multi-task Representations with Pre-Finetuning](https://md.research.elamur.ai/free/en/papers/aghajanyan-2021-muppet-massive-multi-task-representations/)
- [Data Augmentation via Dependency Tree Morphing for Low-Resource Languages](https://md.research.elamur.ai/free/en/papers/ahin-2018-data-augmentation-dependency-tree-morphing/)
- [Adapting Pre-trained Language Models to African Languages via Multilingual Adaptive Fine-Tuning](https://md.research.elamur.ai/free/en/papers/alabi-2022-adapting-pre-trained-language-models/)
- [Dhati+: Fine-tuned Large Language Models for Arabic Subjectivity Evaluation](https://md.research.elamur.ai/free/en/papers/bellaouar-2025-dhati-fine-tuned-large-language/)
- [An Empirical Survey of Data Augmentation for Limited Data Learning in NLP](https://md.research.elamur.ai/free/en/papers/chen-2023-empirical-survey-data-augmentation-limited/)
- [Adapting Language Models to Compress Contexts](https://md.research.elamur.ai/free/en/papers/chevalier-2023-adapting-language-models-compress-contexts/)
- [A Character-level Decoder without Explicit Segmentation for Neural Machine Translation](https://md.research.elamur.ai/free/en/papers/chung-2016-character-level-decoder-without-explicit/)
- [Representations and Architectures in Neural Sentiment Analysis for Morphologically Rich Languages: A Case Study from Modern Hebrew](https://md.research.elamur.ai/free/en/papers/coling-2018-amram-representations-architectures-neural-sentiment-analysis/)
- [Very Deep Convolutional Networks for Text Classification](https://md.research.elamur.ai/free/en/papers/conneau-2017-very-deep-convolutional-networks-text/)
- [An Analysis of Simple Data Augmentation for Named Entity Recognition](https://md.research.elamur.ai/free/en/papers/dai-2020-analysis-simple-data-augmentation-named/)
- [Why Can GPT Learn In-Context? Language Models Secretly Perform Gradient Descent as Meta-Optimizers](https://md.research.elamur.ai/free/en/papers/dai-2023-why-can-gpt-learn-context/)
- [RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning](https://md.research.elamur.ai/free/en/papers/deng-2022-rlprompt-optimizing-discrete-text-prompts/)
- [Toxicity in chatgpt: Analyzing persona-assigned language models](https://md.research.elamur.ai/free/en/papers/deshpande-2023-toxicity-chatgpt-analyzing-persona-assigned/)
- [OpenPrompt: An Open-source Framework for Prompt-learning](https://md.research.elamur.ai/free/en/papers/ding-2022-openprompt-open-source-framework-prompt/)
- [A Survey on In-context Learning](https://md.research.elamur.ai/free/en/papers/dong-2023-survey-context-learning/)
- [A Survey of Data Augmentation Approaches for NLP](https://md.research.elamur.ai/free/en/papers/feng-2021-survey-data-augmentation-approaches-nlp/)
- [Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers](https://md.research.elamur.ai/free/en/papers/gao-2018-black-box-generation-adversarial-text/)
- [Time Travel in LLMs: Tracing Data Contamination in Large Language Models](https://md.research.elamur.ai/free/en/papers/golchin-2023-time-travel-llms-tracing-data/)
- [PPT: Pre-trained Prompt Tuning for Few-shot Learning](https://md.research.elamur.ai/free/en/papers/gu-2022-ppt-pre-trained-prompt-tuning/)
- [Gradient-based Adversarial Attacks against Text Transformers](https://md.research.elamur.ai/free/en/papers/guo-2021-gradient-based-adversarial-attacks-against/)
- [Unleashing the Power of Neural Discourse Parsers - A Context and Structure Aware Approach Using Large Scale Pretraining](https://md.research.elamur.ai/free/en/papers/guz-2020-unleashing-power-neural-discourse-parsers/)
- [Surface Form Competition: Why the Highest Probability Answer Isn't Always Right](https://md.research.elamur.ai/free/en/papers/holtzman-2021-surface-form-competition-why-highest/)
- [Few-shot Slot Tagging with Collapsed Dependency Transfer and Label-enhanced Task-adaptive Projection Network](https://md.research.elamur.ai/free/en/papers/hou-2020-few-shot-slot-tagging-collapsed/)
- [Knowledgeable Prompt-tuning: Incorporating Knowledge into Prompt Verbalizer for Text Classification](https://md.research.elamur.ai/free/en/papers/hu-2022-knowledgeable-prompt-tuning-incorporating-knowledge/)
- [MEGA RST Discourse Treebanks with Structure and Nuclearity from Scalable Distant Sentiment Supervision](https://md.research.elamur.ai/free/en/papers/huber-2020-mega-rst-discourse-treebanks-structure/)
- [Editing Models with Task Arithmetic](https://md.research.elamur.ai/free/en/papers/ilharco-2022-editing-models-task-arithmetic/)
- [Attention is not Explanation](https://md.research.elamur.ai/free/en/papers/jain-2019-attention-is-not-explanation/)
- [FastText.zip: Compressing text classification models](https://md.research.elamur.ai/free/en/papers/joulin-2016-fasttext-zip-compressing-text-classification/)
- [A Dataset of Peer Reviews (PeerRead): Collection, Insights and NLP Applications](https://md.research.elamur.ai/free/en/papers/kang-2018-dataset-peer-reviews-peerread-collection/)
- [Optimizing the Size of Subword Vocabularies in Dialect Classification](https://md.research.elamur.ai/free/en/papers/kanjirangat-2023-optimizing-size-subword-vocabularies-dialect/)
- [Character-Aware Neural Language Models](https://md.research.elamur.ai/free/en/papers/kim-2015-character-aware-neural-language-models/)
- [Contextual Augmentation: Data Augmentation by Words with Paradigmatic Relations](https://md.research.elamur.ai/free/en/papers/kobayashi-2018-contextual-augmentation-data-augmentation-words/)
- [An Empirical Study of Contextual Data Augmentation for Japanese Zero Anaphora Resolution](https://md.research.elamur.ai/free/en/papers/konno-2020-empirical-study-contextual-data-augmentation/)
- [GeDi: Generative Discriminator Guided Sequence Generation](https://md.research.elamur.ai/free/en/papers/krause-2021-gedi-generative-discriminator-guided-sequence/)
- [Submodular Optimization-based Diverse Paraphrasing and its Effectiveness in Data Augmentation](https://md.research.elamur.ai/free/en/papers/kumar-2019-submodular-optimization-based-diverse-paraphrasing/)
- [Weight Poisoning Attacks on Pretrained Models](https://md.research.elamur.ai/free/en/papers/kurita-2020-weight-poisoning-attacks-pretrained-models/)
- [Fully Character-Level Neural Machine Translation without Explicit Segmentation](https://md.research.elamur.ai/free/en/papers/lee-2017-fully-character-level-neural-machine/)
- [TextBugger: Generating Adversarial Text Against Real-world Applications](https://md.research.elamur.ai/free/en/papers/li-2018-textbugger-generating-adversarial-text-against/)
- [BERT-ATTACK: Adversarial Attack Against BERT Using BERT](https://md.research.elamur.ai/free/en/papers/li-2020-bert-attack-adversarial-attack-against/)
- [Modeling Local Contexts for Joint Dialogue Act Recognition and Sentiment Classification with Bi-channel Dynamic Convolutions](https://md.research.elamur.ai/free/en/papers/li-2020-modeling-local-contexts-joint-dialogue/)
- [Contextualized Perturbation for Textual Adversarial Attack](https://md.research.elamur.ai/free/en/papers/li-2021-contextualized-perturbation-textual-adversarial-attack/)
- [Target-Aware Data Augmentation for Stance Detection](https://md.research.elamur.ai/free/en/papers/li-2021-target-aware-data-augmentation-stance/)
- [Synthetic Data Generation with Large Language Models for Text Classification: Potential and Limitations](https://md.research.elamur.ai/free/en/papers/li-2023-synthetic-data-generation-large-language/)
- [Unified Demonstration Retriever for In-Context Learning](https://md.research.elamur.ai/free/en/papers/li-2023-unified-demonstration-retriever-context-learning/)
- [FastBERT: a Self-distilling BERT with Adaptive Inference Time](https://md.research.elamur.ai/free/en/papers/liu-2020-fastbert-self-distilling-bert-adaptive/)
- [Does DetectGPT Fully Utilize Perturbation? Bridging Selective Perturbation to Fine-tuned Contrastive Learning Detector would be Better](https://md.research.elamur.ai/free/en/papers/liu-2024-does-detectgpt-fully-utilize-perturbation/)
- [On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Survey](https://md.research.elamur.ai/free/en/papers/long-2024-llms-driven-synthetic-data-generation/)
- [Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity](https://md.research.elamur.ai/free/en/papers/lu-2022-fantastically-ordered-prompts-where-find/)
- [Achieving Open Vocabulary Neural Machine Translation with Hybrid Word-Character Models](https://md.research.elamur.ai/free/en/papers/luong-2016-achieving-open-vocabulary-neural-machine/)
- [Diff4TST: Masked Diffusion Language Model for Text Style Transfer](https://md.research.elamur.ai/free/en/papers/ma-2026-diff4tst-masked-diffusion-language-model/)
- [EmoNet: Fine-Grained Emotion Detection with Gated Recurrent Neural Networks](https://md.research.elamur.ai/free/en/papers/mageed-2017-emonet-fine-grained-emotion-detection/)
- [Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks](https://md.research.elamur.ai/free/en/papers/mahabadi-2021-parameter-efficient-multi-task-fine/)
- [Text Classification Using Label Names Only: A Language Model Self-Training Approach](https://md.research.elamur.ai/free/en/papers/meng-2020-text-classification-label-names-only/)
- [Noisy Channel Language Model Prompting for Few-Shot Text Classification](https://md.research.elamur.ai/free/en/papers/min-2021-noisy-channel-language-model-prompting/)
- [Adversarial Training Methods for Semi-Supervised Text Classification](https://md.research.elamur.ai/free/en/papers/miyato-2016-adversarial-training-methods-semi-supervised/)
- [Generative Representational Instruction Tuning](https://md.research.elamur.ai/free/en/papers/muennighoff-2024-generative-representational-instruction-tuning/)
- [Ranking Sentences for Extractive Summarization with Reinforcement Learning](https://md.research.elamur.ai/free/en/papers/narayan-2018-ranking-sentences-extractive-summarization-reinforcement/)
- [Neural Semantic Parsing by Character-based Translation: Experiments with Abstract Meaning Representations](https://md.research.elamur.ai/free/en/papers/noord-2017-neural-semantic-parsing-character-based/)
- [Nomic Embed: Training a Reproducible Long Context Text Embedder](https://md.research.elamur.ai/free/en/papers/nussbaum-2024-nomic-embed-training-reproducible-long/)
- [One-step and Two-step Classification for Abusive Language Detection on Twitter](https://md.research.elamur.ai/free/en/papers/park-2017-one-step-two-step-classification/)
- [Multilingual Part-of-Speech Tagging with Bidirectional Long Short-Term Memory Models and Auxiliary Loss](https://md.research.elamur.ai/free/en/papers/plank-2016-multilingual-part-speech-tagging-bidirectional/)
- [Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger](https://md.research.elamur.ai/free/en/papers/qi-2021-hidden-killer-invisible-textual-backdoor/)
- [Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer](https://md.research.elamur.ai/free/en/papers/qi-2021-mind-style-text-adversarial-backdoor/)
- [ONION: A Simple and Effective Defense Against Textual Backdoor Attacks](https://md.research.elamur.ai/free/en/papers/qi-2021-onion-simple-effective-defense-against/)
- [Implicit Discourse Relation Recognition with Context-aware Character-enhanced Embeddings](https://md.research.elamur.ai/free/en/papers/qin-2016-implicit-discourse-relation-recognition-context/)
- [Learning to Generate Reviews and Discovering Sentiment](https://md.research.elamur.ai/free/en/papers/radford-2017-learning-generate-reviews-discovering-sentiment/)
- [Truth of Varying Shades: Analyzing Language in Fake News and Political Fact-Checking](https://md.research.elamur.ai/free/en/papers/rashkin-2017-truth-varying-shades-analyzing-language/)
- [A Recipe For Arbitrary Text Style Transfer with Large Language Models](https://md.research.elamur.ai/free/en/papers/reif-2021-recipe-arbitrary-text-style-transfer/)
- [Generating Natural Language Adversarial Examples through Probability Weighted Word Saliency](https://md.research.elamur.ai/free/en/papers/ren-2019-generating-natural-language-adversarial-examples/)
- [Leveraging Large Language Models for Multiple Choice Question Answering](https://md.research.elamur.ai/free/en/papers/robinson-2022-leveraging-large-language-models-multiple/)
- [Simple and Effective Masked Diffusion Language Models](https://md.research.elamur.ai/free/en/papers/sahoo-2024-simple-effective-masked-diffusion-language/)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://md.research.elamur.ai/free/en/papers/sanh-2021-multitask-prompted-training-enables-zero/)
- [CARER: Contextualized Affect Representations for Emotion Recognition](https://md.research.elamur.ai/free/en/papers/saravia-2018-carer-contextualized-affect-representations-emotion/)
- [Exploiting Cloze-Questions for Few-Shot Text Classification and Natural Language Inference](https://md.research.elamur.ai/free/en/papers/schick-2021-exploiting-cloze-questions-few-shot/)
- [Learning Joint Multilingual Sentence Representations with Neural Machine Translation](https://md.research.elamur.ai/free/en/papers/schwenk-2017-learning-joint-multilingual-sentence-representations/)
- [Is Attention Interpretable?](https://md.research.elamur.ai/free/en/papers/serrano-2019-is-attention-interpretable/)
- [Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms](https://md.research.elamur.ai/free/en/papers/shen-2018-baseline-needs-more-love-simple/)
- [Fast and Accurate Entity Recognition with Iterated Dilated Convolutions](https://md.research.elamur.ai/free/en/papers/strubell-2017-fast-accurate-entity-recognition-iterated/)
- [One Embedder, Any Task: Instruction-Finetuned Text Embeddings](https://md.research.elamur.ai/free/en/papers/su-2022-one-embedder-any-task-instruction/)
- [Extracting Latent Steering Vectors from Pretrained Language Models](https://md.research.elamur.ai/free/en/papers/subramani-2022-extracting-latent-steering-vectors-pretrained/)
- [How to Fine-Tune BERT for Text Classification?](https://md.research.elamur.ai/free/en/papers/sun-2019-fine-tune-bert-text-classification/)
- [Text Classification via Large Language Models](https://md.research.elamur.ai/free/en/papers/sun-2023-text-classification-large-language-models/)
- [UL2: Unifying Language Learning Paradigms](https://md.research.elamur.ai/free/en/papers/tay-2022-ul2-unifying-language-learning-paradigms/)
- [Authorship Attribution for Neural Text Generation](https://md.research.elamur.ai/free/en/papers/uchendu-2020-authorship-attribution-neural-text-generation/)
- [Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model](https://md.research.elamur.ai/free/en/papers/ustun-2024-aya-model-instruction-finetuned-open/)
- [SPoT: Better Frozen Model Adaptation through Soft Prompt Transfer](https://md.research.elamur.ai/free/en/papers/vu-2022-spot-better-frozen-model-adaptation/)
- [“Liar, Liar Pants on Fire”: A New Benchmark Dataset for Fake News Detection](https://md.research.elamur.ai/free/en/papers/wang-2017-liar-liar-pants-fire-new/)
- [Want To Reduce Labeling Cost? GPT-3 Can Help](https://md.research.elamur.ai/free/en/papers/wang-2021-want-reduce-labeling-cost-gpt/)
- [Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning](https://md.research.elamur.ai/free/en/papers/wang-2023-label-words-anchors-information-flow/)
- [EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks](https://md.research.elamur.ai/free/en/papers/wei-2019-eda-easy-data-augmentation-techniques/)
- [Unsupervised Data Augmentation for Consistency Training](https://md.research.elamur.ai/free/en/papers/xie-2019-unsupervised-data-augmentation-consistency-training/)
- [Double Embeddings and CNN-based Sequence Labeling for Aspect Extraction](https://md.research.elamur.ai/free/en/papers/xu-2018-double-embeddings-cnn-based-sequence/)
- [Hierarchical Attention Networks for Document Classification](https://md.research.elamur.ai/free/en/papers/yang-2016-hierarchical-attention-networks-document-classification/)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://md.research.elamur.ai/free/en/papers/yang-2019-xlnet-generalized-autoregressive-pretraining-language/)
- [Generative Data Augmentation for Commonsense Reasoning](https://md.research.elamur.ai/free/en/papers/yang-2020-generative-data-augmentation-commonsense-reasoning/)
- [Benchmarking Zero-shot Text Classification: Datasets, Evaluation and Entailment Approach](https://md.research.elamur.ai/free/en/papers/yin-2019-benchmarking-zero-shot-text-classification/)
- [GPT3Mix: Leveraging Large-scale Language Models for Text Augmentation](https://md.research.elamur.ai/free/en/papers/yoo-2021-gpt3mix-leveraging-large-scale-language/)
- [QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension](https://md.research.elamur.ai/free/en/papers/yu-2018-qanet-combining-local-convolution-global/)

## Cite

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@misc{zhang2015character,
  title = {{Character-level Convolutional Networks for Text Classification}},
  author = {Zhang, Xiang and Zhao, Junbo and LeCun, Yann},
  year = {2015},
  doi = {10.48550/arxiv.1509.01626},
  eprint = {1509.01626},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.1509.01626}
}
```

- [← previous Character-Aware Neural Language Models](https://md.research.elamur.ai/free/en/papers/kim-2015-character-aware-neural-language-models/)
- [next → Chinese Event Coreference Resolution: An Unsupervised Probabilistic Model Rivaling Supervised Resolvers](https://md.research.elamur.ai/free/en/papers/chen-2015-chinese-event-coreference-resolution-unsupervised/)
- [↑ back to papers of 2015](https://md.research.elamur.ai/free/en/papers/2015/)

## References

32 references, 5 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. L. Bottou, F. Fogelman Soulié, P. Blanchet, and J. Lienard. Experiments with time delay networks and dynamic time warping for speaker independent isolated digit recognition. In Proceedings of EuroSpeech 89, volume 2, pages 537–540, Paris, France, 1989. [find](https://scholar.google.com/scholar?q=L%2E+Bottou%2C+F%2E+Fogelman+Soulie%CC%81%2C+P%2E+Blanchet%2C+and+J%2E+Lienard%2E+Experiments+with+time+delay+networks+and+dynamic+time+warping+for+speaker+independent+isolated+digit+recognition%2E+In+Proceedings+of+EuroSpe)
2. Y.-L. Boureau, F. Bach, Y. LeCun, and J. Ponce. Learning mid-level features for recognition. In Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on, pages 2559–2566. IEEE, 2010. [find](https://scholar.google.com/scholar?q=Y%2E%2DL%2E+Boureau%2C+F%2E+Bach%2C+Y%2E+LeCun%2C+and+J%2E+Ponce%2E+Learning+mid%2Dlevel+features+for+recognition%2E+In+Computer+Vision+and+Pattern+Recognition+%28CVPR%29%2C+2010+IEEE+Conference+on%2C+pages+2559%E2%80%932566%2E+IEEE%2C+2010%2E)
3. Y.-L. Boureau, J. Ponce, and Y. LeCun. A theoretical analysis of feature pooling in visual recognition. In Proceedings of the 27th International Conference on Machine Learning (ICML-10), pages 111–118, 2010. [find](https://scholar.google.com/scholar?q=Y%2E%2DL%2E+Boureau%2C+J%2E+Ponce%2C+and+Y%2E+LeCun%2E+A+theoretical+analysis+of+feature+pooling+in+visual+recognition%2E+In+Proceedings+of+the+27th+International+Conference+on+Machine+Learning+%28ICML%2D10%29%2C+pages+111%E2%80%93118)
4. R. Collobert, K. Kavukcuoglu, and C. Farabet. Torch7: A matlab-like environment for machine learning. In BigLearn, NIPS Workshop, number EPFL-CONF-192376, 2011. [find](https://scholar.google.com/scholar?q=R%2E+Collobert%2C+K%2E+Kavukcuoglu%2C+and+C%2E+Farabet%2E+Torch7%3A+A+matlab%2Dlike+environment+for+machine+learning%2E+In+BigLearn%2C+NIPS+Workshop%2C+number+EPFL%2DCONF%2D192376%2C+2011%2E)
5. R. Collobert, J. Weston, L. Bottou, M. Karlen, K. Kavukcuoglu, and P. Kuksa. Natural language processing (almost) from scratch. J. Mach. Learn. Res., 12:2493–2537, Nov. 2011. [find](https://scholar.google.com/scholar?q=R%2E+Collobert%2C+J%2E+Weston%2C+L%2E+Bottou%2C+M%2E+Karlen%2C+K%2E+Kavukcuoglu%2C+and+P%2E+Kuksa%2E+Natural+language+processing+%28almost%29+from+scratch%2E+J%2E+Mach%2E+Learn%2E+Res%2E%2C+12%3A2493%E2%80%932537%2C+Nov%2E+2011%2E) [our card](https://md.research.elamur.ai/free/en/papers/collobert-2011-natural-language-processing-almost-scratch/)
6. C. dos Santos and M. Gatti. Deep convolutional neural networks for sentiment analysis of short texts. In Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers, pages 69–78, Dublin, Ireland, August 2014. Dublin City University and Association for… [find](https://scholar.google.com/scholar?q=C%2E+dos+Santos+and+M%2E+Gatti%2E+Deep+convolutional+neural+networks+for+sentiment+analysis+of+short+texts%2E+In+Proceedings+of+COLING+2014%2C+the+25th+International+Conference+on+Computational+Linguistics%3A+Tec) [our card](https://md.research.elamur.ai/free/en/papers/santos-2014-deep-convolutional-neural-networks-sentiment/)
7. C. Fellbaum. Wordnet and wordnets. In K. Brown, editor, Encyclopedia of Language and Linguistics, pages 665–670, Oxford, 2005. Elsevier. [find](https://scholar.google.com/scholar?q=C%2E+Fellbaum%2E+Wordnet+and+wordnets%2E+In+K%2E+Brown%2C+editor%2C+Encyclopedia+of+Language+and+Linguistics%2C+pages+665%E2%80%93670%2C+Oxford%2C+2005%2E+Elsevier%2E)
8. A. Graves and J. Schmidhuber. Framewise phoneme classification with bidirectional lstm and other neural network architectures. Neural Networks, 18(5):602–610, 2005. [find](https://scholar.google.com/scholar?q=A%2E+Graves+and+J%2E+Schmidhuber%2E+Framewise+phoneme+classification+with+bidirectional+lstm+and+other+neural+network+architectures%2E+Neural+Networks%2C+18%285%29%3A602%E2%80%93610%2C+2005%2E)
9. K. Greff, R. K. Srivastava, J. Koutnı́k, B. R. Steunebrink, and J. Schmidhuber. LSTM: A search space odyssey. CoRR, abs/1503.04069, 2015. [find](https://scholar.google.com/scholar?q=K%2E+Greff%2C+R%2E+K%2E+Srivastava%2C+J%2E+Koutn%C4%B1%CC%81k%2C+B%2E+R%2E+Steunebrink%2C+and+J%2E+Schmidhuber%2E+LSTM%3A+A+search+space+odyssey%2E+CoRR%2C+abs%2F1503%2E04069%2C+2015%2E)
10. G. E. Hinton, N. Srivastava, A. Krizhevsky, I. Sutskever, and R. R. Salakhutdinov. Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580, 2012. [find](https://scholar.google.com/scholar?q=G%2E+E%2E+Hinton%2C+N%2E+Srivastava%2C+A%2E+Krizhevsky%2C+I%2E+Sutskever%2C+and+R%2E+R%2E+Salakhutdinov%2E+Improving+neural+networks+by+preventing+co%2Dadaptation+of+feature+detectors%2E+arXiv+preprint+arXiv%3A1207%2E0580%2C+2012%2E)
11. S. Hochreiter and J. Schmidhuber. Long short-term memory. Neural Comput., 9(8):1735–1780, Nov. 1997. [find](https://scholar.google.com/scholar?q=S%2E+Hochreiter+and+J%2E+Schmidhuber%2E+Long+short%2Dterm+memory%2E+Neural+Comput%2E%2C+9%288%29%3A1735%E2%80%931780%2C+Nov%2E+1997%2E)
12. T. Joachims. Text categorization with suport vector machines: Learning with many relevant features. In Proceedings of the 10th European Conference on Machine Learning, pages 137–142. Springer-Verlag, 1998. [find](https://scholar.google.com/scholar?q=T%2E+Joachims%2E+Text+categorization+with+suport+vector+machines%3A+Learning+with+many+relevant+features%2E+In+Proceedings+of+the+10th+European+Conference+on+Machine+Learning%2C+pages+137%E2%80%93142%2E+Springer%2DVerlag%2C+)
13. R. Johnson and T. Zhang. Effective use of word order for text categorization with convolutional neural networks. CoRR, abs/1412.1058, 2014. [find](https://scholar.google.com/scholar?q=R%2E+Johnson+and+T%2E+Zhang%2E+Effective+use+of+word+order+for+text+categorization+with+convolutional+neural+networks%2E+CoRR%2C+abs%2F1412%2E1058%2C+2014%2E) [our card](https://md.research.elamur.ai/free/en/papers/johnson-2015-effective-use-word-order-text/)
14. K. S. Jones. A statistical interpretation of term specificity and its application in retrieval. Journal of Documentation, 28(1):11–21, 1972. [find](https://scholar.google.com/scholar?q=K%2E+S%2E+Jones%2E+A+statistical+interpretation+of+term+specificity+and+its+application+in+retrieval%2E+Journal+of+Documentation%2C+28%281%29%3A11%E2%80%9321%2C+1972%2E)
15. I. Kanaris, K. Kanaris, I. Houvardas, and E. Stamatatos. Words versus character n-grams for anti-spam filtering. International Journal on Artificial Intelligence Tools, 16(06):1047–1067, 2007. [find](https://scholar.google.com/scholar?q=I%2E+Kanaris%2C+K%2E+Kanaris%2C+I%2E+Houvardas%2C+and+E%2E+Stamatatos%2E+Words+versus+character+n%2Dgrams+for+anti%2Dspam+filtering%2E+International+Journal+on+Artificial+Intelligence+Tools%2C+16%2806%29%3A1047%E2%80%931067%2C+2007%2E)
16. Y. Kim. Convolutional neural networks for sentence classification. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1746–1751, Doha, Qatar, October 2014. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Y%2E+Kim%2E+Convolutional+neural+networks+for+sentence+classification%2E+In+Proceedings+of+the+2014+Conference+on+Empirical+Methods+in+Natural+Language+Processing+%28EMNLP%29%2C+pages+1746%E2%80%931751%2C+Doha%2C+Qatar%2C+Octo) [our card](https://md.research.elamur.ai/free/en/papers/kim-2014-convolutional-neural-networks-sentence-classification/)
17. Y. LeCun, B. Boser, J. S. Denker, D. Henderson, R. E. Howard, W. Hubbard, and L. D. Jackel. Backpropagation applied to handwritten zip code recognition. Neural Computation, 1(4):541–551, Winter 1989. [find](https://scholar.google.com/scholar?q=Y%2E+LeCun%2C+B%2E+Boser%2C+J%2E+S%2E+Denker%2C+D%2E+Henderson%2C+R%2E+E%2E+Howard%2C+W%2E+Hubbard%2C+and+L%2E+D%2E+Jackel%2E+Backpropagation+applied+to+handwritten+zip+code+recognition%2E+Neural+Computation%2C+1%284%29%3A541%E2%80%93551%2C+Winter+1989%2E)
18. Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11):2278–2324, November 1998. [find](https://scholar.google.com/scholar?q=Y%2E+LeCun%2C+L%2E+Bottou%2C+Y%2E+Bengio%2C+and+P%2E+Haffner%2E+Gradient%2Dbased+learning+applied+to+document+recognition%2E+Proceedings+of+the+IEEE%2C+86%2811%29%3A2278%E2%80%932324%2C+November+1998%2E)
19. J. Lehmann, R. Isele, M. Jakob, A. Jentzsch, D. Kontokostas, P. N. Mendes, S. Hellmann, M. Morsey, P. van Kleef, S. Auer, and C. Bizer. DBpedia - a large-scale, multilingual knowledge base extracted from wikipedia. Semantic Web Journal, 2014. [find](https://scholar.google.com/scholar?q=J%2E+Lehmann%2C+R%2E+Isele%2C+M%2E+Jakob%2C+A%2E+Jentzsch%2C+D%2E+Kontokostas%2C+P%2E+N%2E+Mendes%2C+S%2E+Hellmann%2C+M%2E+Morsey%2C+P%2E+van+Kleef%2C+S%2E+Auer%2C+and+C%2E+Bizer%2E+DBpedia+%2D+a+large%2Dscale%2C+multilingual+knowledge+base+extracted+f)
20. G. Lev, B. Klein, and L. Wolf. In defense of word embedding for generic text representation. In C. Biemann, S. Handschuh, A. Freitas, F. Meziane, and E. Mtais, editors, Natural Language Processing and Information Systems, volume 9103 of Lecture Notes in Computer Science, pages 35–50. Springer Intern… [find](https://scholar.google.com/scholar?q=G%2E+Lev%2C+B%2E+Klein%2C+and+L%2E+Wolf%2E+In+defense+of+word+embedding+for+generic+text+representation%2E+In+C%2E+Biemann%2C+S%2E+Handschuh%2C+A%2E+Freitas%2C+F%2E+Meziane%2C+and+E%2E+Mtais%2C+editors%2C+Natural+Language+Processing+and)
21. D. D. Lewis, Y. Yang, T. G. Rose, and F. Li. Rcv1: A new benchmark collection for text categorization research. The Journal of Machine Learning Research, 5:361–397, 2004. [find](https://scholar.google.com/scholar?q=D%2E+D%2E+Lewis%2C+Y%2E+Yang%2C+T%2E+G%2E+Rose%2C+and+F%2E+Li%2E+Rcv1%3A+A+new+benchmark+collection+for+text+categorization+research%2E+The+Journal+of+Machine+Learning+Research%2C+5%3A361%E2%80%93397%2C+2004%2E) [our card](https://md.research.elamur.ai/free/en/papers/lewis-2004-rcv1-benchmark-collection-text-categorization/)
22. J. McAuley and J. Leskovec. Hidden factors and hidden topics: Understanding rating dimensions with review text. In Proceedings of the 7th ACM Conference on Recommender Systems, RecSys ’13, pages 165–172, New York, NY, USA, 2013. ACM. [find](https://scholar.google.com/scholar?q=J%2E+McAuley+and+J%2E+Leskovec%2E+Hidden+factors+and+hidden+topics%3A+Understanding+rating+dimensions+with+review+text%2E+In+Proceedings+of+the+7th+ACM+Conference+on+Recommender+Systems%2C+RecSys+%E2%80%9913%2C+pages+165%E2%80%931)
23. T. Mikolov, I. Sutskever, K. Chen, G. S. Corrado, and J. Dean. Distributed representations of words and phrases and their compositionality. In C. Burges, L. Bottou, M. Welling, Z. Ghahramani, and K. Weinberger, editors, Advances in Neural Information Processing Systems 26, pages 3111–3119. 2013. [find](https://scholar.google.com/scholar?q=T%2E+Mikolov%2C+I%2E+Sutskever%2C+K%2E+Chen%2C+G%2E+S%2E+Corrado%2C+and+J%2E+Dean%2E+Distributed+representations+of+words+and+phrases+and+their+compositionality%2E+In+C%2E+Burges%2C+L%2E+Bottou%2C+M%2E+Welling%2C+Z%2E+Ghahramani%2C+and+K%2E+W)
24. V. Nair and G. E. Hinton. Rectified linear units improve restricted boltzmann machines. In Proceedings of the 27th International Conference on Machine Learning (ICML-10), pages 807–814, 2010. [find](https://scholar.google.com/scholar?q=V%2E+Nair+and+G%2E+E%2E+Hinton%2E+Rectified+linear+units+improve+restricted+boltzmann+machines%2E+In+Proceedings+of+the+27th+International+Conference+on+Machine+Learning+%28ICML%2D10%29%2C+pages+807%E2%80%93814%2C+2010%2E)
25. R. Pascanu, T. Mikolov, and Y. Bengio. On the difficulty of training recurrent neural networks. In ICML 2013, volume 28 of JMLR Proceedings, pages 1310–1318. JMLR.org, 2013. [find](https://scholar.google.com/scholar?q=R%2E+Pascanu%2C+T%2E+Mikolov%2C+and+Y%2E+Bengio%2E+On+the+difficulty+of+training+recurrent+neural+networks%2E+In+ICML+2013%2C+volume+28+of+JMLR+Proceedings%2C+pages+1310%E2%80%931318%2E+JMLR%2Eorg%2C+2013%2E)
26. B. Polyak. Some methods of speeding up the convergence of iteration methods. {USSR} Computational Mathematics and Mathematical Physics, 4(5):1 – 17, 1964. [find](https://scholar.google.com/scholar?q=B%2E+Polyak%2E+Some+methods+of+speeding+up+the+convergence+of+iteration+methods%2E+%7BUSSR%7D+Computational+Mathematics+and+Mathematical+Physics%2C+4%285%29%3A1+%E2%80%93+17%2C+1964%2E)
27. D. Rumelhart, G. Hintont, and R. Williams. Learning representations by back-propagating errors. Nature, 323(6088):533–536, 1986. [find](https://scholar.google.com/scholar?q=D%2E+Rumelhart%2C+G%2E+Hintont%2C+and+R%2E+Williams%2E+Learning+representations+by+back%2Dpropagating+errors%2E+Nature%2C+323%286088%29%3A533%E2%80%93536%2C+1986%2E)
28. C. D. Santos and B. Zadrozny. Learning character-level representations for part-of-speech tagging. In Proceedings of the 31st International Conference on Machine Learning (ICML-14), pages 1818–1826, 2014. [find](https://scholar.google.com/scholar?q=C%2E+D%2E+Santos+and+B%2E+Zadrozny%2E+Learning+character%2Dlevel+representations+for+part%2Dof%2Dspeech+tagging%2E+In+Proceedings+of+the+31st+International+Conference+on+Machine+Learning+%28ICML%2D14%29%2C+pages+1818%E2%80%931826%2C+2)
29. Y. Shen, X. He, J. Gao, L. Deng, and G. Mesnil. A latent semantic model with convolutional-pooling structure for information retrieval. In Proceedings of the 23rd ACM International Conference on Conference on Information and Knowledge Management, pages 101–110. ACM, 2014. [find](https://scholar.google.com/scholar?q=Y%2E+Shen%2C+X%2E+He%2C+J%2E+Gao%2C+L%2E+Deng%2C+and+G%2E+Mesnil%2E+A+latent+semantic+model+with+convolutional%2Dpooling+structure+for+information+retrieval%2E+In+Proceedings+of+the+23rd+ACM+International+Conference+on+Confe)
30. I. Sutskever, J. Martens, G. E. Dahl, and G. E. Hinton. On the importance of initialization and momentum in deep learning. In S. Dasgupta and D. Mcallester, editors, Proceedings of the 30th International Conference on Machine Learning (ICML-13), volume 28, pages 1139–1147. JMLR Workshop and Conferen… [find](https://scholar.google.com/scholar?q=I%2E+Sutskever%2C+J%2E+Martens%2C+G%2E+E%2E+Dahl%2C+and+G%2E+E%2E+Hinton%2E+On+the+importance+of+initialization+and+momentum+in+deep+learning%2E+In+S%2E+Dasgupta+and+D%2E+Mcallester%2C+editors%2C+Proceedings+of+the+30th+Internatio)
31. A. Waibel, T. Hanazawa, G. Hinton, K. Shikano, and K. J. Lang. Phoneme recognition using time-delay neural networks. Acoustics, Speech and Signal Processing, IEEE Transactions on, 37(3):328–339, 1989. [find](https://scholar.google.com/scholar?q=A%2E+Waibel%2C+T%2E+Hanazawa%2C+G%2E+Hinton%2C+K%2E+Shikano%2C+and+K%2E+J%2E+Lang%2E+Phoneme+recognition+using+time%2Ddelay+neural+networks%2E+Acoustics%2C+Speech+and+Signal+Processing%2C+IEEE+Transactions+on%2C+37%283%29%3A328%E2%80%93339%2C+1989%2E)
32. C. Wang, M. Zhang, S. Ma, and L. Ru. Automatic online news issue construction in web environment. In Proceedings of the 17th International Conference on World Wide Web, WWW ’08, pages 457–466, New York, NY, USA, 2008. ACM. [find](https://scholar.google.com/scholar?q=C%2E+Wang%2C+M%2E+Zhang%2C+S%2E+Ma%2C+and+L%2E+Ru%2E+Automatic+online+news+issue+construction+in+web+environment%2E+In+Proceedings+of+the+17th+International+Conference+on+World+Wide+Web%2C+WWW+%E2%80%9908%2C+pages+457%E2%80%93466%2C+New+Yor)