AI NEWS.ccAI正在发生 未来正在更新
♡ 我的收藏 0
AI 模型库/indolem/indobertweet-base-uncased
MODEL PROFILE · 模型档案

indobertweet-base-uncased

indolem · indobertweet-base-uncased

Fajri Koto, Jey Han Lau, and Timothy Baldwin. _IndoBERTweet: A Pretrained Language Model for Indonesian Twitter with Effective Domain-Specific Vocabulary Initialization_. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (**EMNLP 2021**), Dominican Republic (virtual). In this paper, we show that initializing domain-specific vocabulary with average-pooling of BERT subword embeddings is more efficient than pretraining from scratch, and more effective than initializing based on word2vec projections. We crawl Indonesian tweets over a 1-year period using the official Twitter API, from December 2019 to December 2020, with 60 keywords covering 4 main topics: economy, health, education, and government. We obtain in total of **409M word tokens**, two times larger than the training data used to pretrain IndoBERT. Due to Twitter policy, this pretraining data will not be released to public.

译文排队中，当前展示来源原文。

填空与掩码license:apache-2.0
上下文窗口来源未披露
输入 → 输出文本 → 文本
模型权重待核验
档案更新时间2026/11/2 19:16:57
OVERVIEW

模型介绍

Fajri Koto, Jey Han Lau, and Timothy Baldwin. _IndoBERTweet: A Pretrained Language Model for Indonesian Twitter with Effective Domain-Specific Vocabulary Initialization_. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (**EMNLP 2021**), Dominican Republic (virtual). In this paper, we show that initializing domain-specific vocabulary with average-pooling of BERT subword embeddings is more efficient than pretraining from scratch, and more effective than initializing based on word2vec projections. We crawl Indonesian tweets over a 1-year period using the official Twitter API, from December 2019 to December 2020, with 60 keywords covering 4 main topics: economy, health, education, and government. We obtain in total of **409M word tokens**, two times larger than the training data used to pretrain IndoBERT. Due to Twitter policy, this pretraining data will not be released to public.

主要特点

特点摘要待依据来源补齐，不凭模型名称推断能力。

局限与注意事项

暂无足够来源支持具体缺点结论。请重点验证实际任务表现、时延、数据政策、许可与版本生命周期。

PRICING & COST

来源报价与费用分析

同一模型在不同渠道、地区和配置下可能采用不同价格。下表独立保留各渠道报价，不将渠道价格视为厂商官方统一价格。

来源 / 渠道输入输出计费单位采集时间
暂未取得可核验报价，请查阅来源渠道。

按月估算基础 Token 费用

—

预估不包含缓存优惠、阶梯定价、多模态附加费用、网络检索、税费及推理额外输出。

INDEPENDENT BENCHMARKS

公开评测与运行配置

暂无已采集的可核验公开评分。模型未上榜不代表能力较低。

查看完整已收录榜单 →

常见问题

开放权重是否代表可以免费商用？

不一定。应核对具体版本许可证、商用门槛和使用政策。自部署还会产生算力和维护成本。

这些价格是实时结算价格吗？

不是实时结算价格，而是带采集时间的来源报价快照。请到对应渠道核对当前版本、区域、折扣和计费方式。

资料来源与可追溯记录

huggingface · indolem/indobertweet-base-uncased ↗2026/10/31 23:06:05
huggingface · enrich:6753e536-e547-48cd-9920-efd09378a0c3 ↗2026/10/29 19:00:32

许可证：apache-2.0。模型介绍与第三方评测均以原来源的具体版本和方法为准。