Pith. sign in

REVIEW 30 cited by

FastText.zip: Compressing text classification models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1612.03651 v1 pith:ETVPW5JV submitted 2016-12-12 cs.CL cs.LG

FastText.zip: Compressing text classification models

classification cs.CL cs.LG
keywords accuracymemoryclassificationfasttextmethodquantizationtextwhile
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We consider the problem of producing compact architectures for text classification, such that the full model fits in a limited amount of memory. After considering different solutions inspired by the hashing literature, we propose a method built upon product quantization to store word embeddings. While the original technique leads to a loss in accuracy, we adapt this method to circumvent quantization artefacts. Our experiments carried out on several benchmarks show that our approach typically requires two orders of magnitude less memory than fastText while being only slightly inferior with respect to accuracy. As a result, it outperforms the state of the art by a good margin in terms of the compromise between memory usage and accuracy.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 30 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. From Anatomy to Smells: An Empirical Study of SKILL.md in Agent Skills

    cs.SE 2026-07 unverdicted novelty 7.0

    Empirical study of 238 SKILL.md files finds over 99% contain skill smells that rarely disappear, revealing a gap between recommended and actual authoring practices for agent skills.

  2. Nonsense Helps: Prompt Space Perturbation Broadens Reasoning Exploration

    cs.AI 2026-05 unverdicted novelty 7.0

    Prepending stochastic sequences from Lorem Ipsum vocabulary to prompts during GRPO resampling broadens reasoning exploration and outperforms standard resampling on hard tasks for 1.7B-7B models.

  3. Multi-modal Reasoning with LLMs for Visual Semantic Arithmetic

    cs.AI 2026-04 unverdicted novelty 7.0

    SAri-RFT applies GRPO-based reinforcement fine-tuning to LVLMs on novel two-term and three-term visual semantic arithmetic tasks, reaching SOTA on the new IRPD dataset and Visual7W-Telling.

  4. Polyglot Teachers: Evaluating Language Models for Multilingual Synthetic Data Generation

    cs.CL 2026-04 unverdicted novelty 7.0

    Gemma 3 27B and Aya Expanse 32B are effective multilingual teachers; data qualities such as diversity and fluency explain over 93% of variance in student performance rather than model size.

  5. On The Effectiveness-Fluency Trade-Off In LLM Conditioning: A Systematic Study

    cs.CL 2026-06 unverdicted novelty 6.0

    Systematic experiments reveal that activation steering trades fluency for concept control, is less effective on instruction-tuned models, and that prompting/SFT excel at injection but not removal, with textual metrics...

  6. Language-Aware Token Boosting: LLM Language Confusion Reduction Without Tuning

    cs.CL 2026-06 unverdicted novelty 6.0

    LATB reduces LLM language confusion via language-specific token probability boosts at inference without model tuning while preserving summarization quality.

  7. Steering Vectors are an Adversarial Attack Surface

    cs.LG 2026-06 unverdicted novelty 6.0

    Poisoning 4-6% of tokens in activation steering datasets produces vectors that jailbreak LLMs with 20-55% attack success rate while preserving benign steering effects.

  8. Multilingual Steering by Design: Multilingual Sparse Autoencoders and Principled Layer Selection

    cs.CL 2026-05 unverdicted novelty 6.0

    Multilingual SAEs strengthen cross-lingual representations for reliable steering and an intersection-based rule selects effective layers without exhaustive search.

  9. TeraGram: A Structured Longitudinal Dataset of the Telegram Messenger

    physics.soc-ph 2026-05 unverdicted novelty 6.0

    A large-scale longitudinal dataset of public Telegram content is introduced to enable studies of engagement patterns and network evolution without algorithmic curation.

  10. DocAtlas: Multilingual Document Understanding Across 80+ Languages

    cs.CL 2026-05 unverdicted novelty 6.0

    DocAtlas introduces model-free rendering pipelines to create DocTag-annotated datasets across 82 languages and shows DPO adaptation improves multilingual performance without base-language degradation.

  11. DocAtlas: Multilingual Document Understanding Across 80+ Languages

    cs.CL 2026-05 unverdicted novelty 6.0

    DocAtlas creates multilingual document datasets across 82 languages and shows DPO with rendered ground truth improves model accuracy by 1.7-1.9% without degrading base-language performance, unlike supervised fine-tuning.

  12. Synthetic Pre-Pre-Training Improves Language Model Robustness to Noisy Pre-Training Data

    cs.CL 2026-05 unverdicted novelty 6.0

    Synthetic pre-pre-training on structured data improves LLM robustness to noisy pre-training, matching baseline loss with up to 49% fewer natural tokens for a 1B model.

  13. A Comparative Study of Semantic Log Representations for Software Log-based Anomaly Detection

    cs.SE 2026-04 unverdicted novelty 6.0

    QTyBERT matches or exceeds BERT-based log anomaly detection effectiveness while reducing embedding generation time to near static word embedding levels.

  14. The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale

    cs.CL 2024-06 unverdicted novelty 6.0

    FineWeb is a curated 15T-token web dataset that produces stronger LLMs than prior open collections, while its educational subset sharply improves performance on MMLU and ARC benchmarks.

  15. DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence

    cs.SE 2024-06 unverdicted novelty 6.0

    An open-source MoE code model matches GPT-4 Turbo on coding and math benchmarks while expanding to 338 languages and 128K context length.

  16. DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

    cs.CL 2024-02 unverdicted novelty 6.0

    DeepSeekMath 7B reaches 51.7% on MATH via continued pretraining on curated web math data and Group Relative Policy Optimization.

  17. Studying Lobby Influence in the European Parliament

    cs.CL 2023-09 unverdicted novelty 6.0

    NLP comparison of lobby papers and MEP speeches discovers influence links validated indirectly via retweets and meetings, achieving AUC 0.77 and ideological alignment in aggregate analysis.

  18. The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only

    cs.CL 2023-06 unverdicted novelty 6.0

    Properly filtered web data from CommonCrawl alone trains LLMs that significantly outperform models trained on The Pile, with 600 billion tokens and 1.3B/7.5B parameter models released.

  19. Gated Embeddings in End-to-End Speech Recognition for Conversational-Context Fusion

    cs.CL 2019-06 unverdicted novelty 6.0

    Gated fusion of fastText and BERT embeddings into an end-to-end ASR model captures multi-sentence conversational context and lowers word error rate on the Switchboard corpus.

  20. Structural Under-Representation of Women in News: Nonparametric Bayesian Mixtures Capture Time-Dependent Dynamics

    stat.AP 2026-06 unverdicted novelty 5.0

    Nonparametric Bayesian mixtures on Canadian news data reveal structural under-representation of women as sources, driven more by topic than region, with over 85% of series showing no improvement toward parity and stab...

  21. Exploring the Effectiveness of Using LLMs for Automated Assessment of Student Self Explanations in Programming Education

    cs.HC 2026-05 unverdicted novelty 5.0

    Compares LLMs against semantic similarity for binary classification of student self-explanations in programming education.

  22. Cross-lingual Comparison of Research Funding Projects with Multilingual Sentence-BERT: Evidence from KAKENHI, NIH, NSF, and UKRI

    cs.DL 2026-04 unverdicted novelty 5.0

    Multilingual Sentence-BERT places original Japanese and machine-translated English versions of the same KAKENHI projects closer together than to native English projects from other agencies, yet nearest-neighbor overla...

  23. Language as a Latent Variable for Reasoning Optimization

    cs.CL 2026-04 unverdicted novelty 5.0

    Treating language as a latent variable via polyGRPO RL improves Qwen2.5-7B-Instruct by 6.72% on English reasoning benchmarks and 6.89% on multilingual ones, with cross-task gains on commonsense reasoning from math-onl...

  24. Emerging Properties in Unified Multimodal Pretraining

    cs.CV 2025-05 unverdicted novelty 5.0

    BAGEL is a unified decoder-only model that develops emerging complex multimodal reasoning abilities after pretraining on large-scale interleaved data and outperforms prior open-source unified models.

  25. SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model

    cs.CL 2025-02 unverdicted novelty 5.0

    SmolLM2 is a 1.7B-parameter language model that outperforms Qwen2.5-1.5B and Llama3.2-1B after overtraining on 11 trillion tokens using custom FineMath, Stack-Edu, and SmolTalk datasets in a multi-stage pipeline.

  26. MOSS-Audio Technical Report

    cs.SD 2026-06 unverdicted novelty 4.0

    MOSS-Audio is an audio-language model using a 12.5 Hz encoder, DeepStack cross-layer injection, time markers, and an event-preserving annotation pipeline for unified audio understanding.

  27. Toward LLMs Beyond English-Centric Development

    cs.CL 2026-05 unverdicted novelty 4.0

    Analysis of open-weight LLMs reveals strong English bias in generated sequences, with continual pre-training providing no cost benefit over from-scratch training for non-English adaptation.

  28. Human-Machine Co-Boosted Bug Report Identification with Mutualistic Neural Active Learning

    cs.SE 2026-04 unverdicted novelty 4.0

    MNAL reduces human effort in bug report labeling by up to 95.8% for readability and 196% for identifiability while improving identification performance and working with various neural models.

  29. PortBERT: Navigating the Depths of Portuguese Language Models

    cs.CL 2026-06 unverdicted novelty 3.0

    PortBERT releases two RoBERTa models for Portuguese that match or beat prior monolingual and multilingual models on translated GLUE/SuperGLUE tasks while reporting training and inference times.

  30. Cross-lingual Data Transformation and Combination for Text Classification

    cs.IR 2019-06 unverdicted novelty 3.0

    Cross-lingual data combined via translation or aligned embeddings can improve performance of CNN and RNN text classifiers.