从给定的问题和上下文中提取答案。基于 SQuAD（斯坦福问答数据集）微调的 DistilBERT 模型。

    let qa_model = QuestionAnsweringModel::new(Default::default ()) ?;

let question = String::from("Amy住在哪儿？");
let context = String::from("Amy住在阿姆斯特丹");

let answers = qa_model.predict( & [QaInput { question, context }], 1, 32);

输出：

[Answer { score: 0.9976, start: 13, end: 21, answer: "阿姆斯特丹" }]

支持广泛源语言和目标语言的翻译流水线。利用两种主要架构进行翻译任务：

• 基于 Marian 的模型，适用于特定的源语言/目标语言组合；
• M2M100 模型允许在 100 种语言之间直接翻译（但对于某些选定的语言，计算成本较高且性能较低）。

该库中提供了以下语言对的 Marian 预训练模型，用户也可以导入任何基于 PyTorch 的模型来进行预测：

• 英语 <-> 法语
• 英语 <-> 西班牙语
• 英语 <-> 葡萄牙语
• 英语 <-> 意大利语
• 英语 <-> 加泰罗尼亚语
• 英语 <-> 德语
• 英语 <-> 俄语
• 英语 <-> 中文
• 英语 <-> 荷兰语
• 英语 <-> 瑞典语
• 英语 <-> 阿拉伯语
• 英语 <-> 希伯来语
• 英语 <-> 印地语
• 法语 <-> 德语

对于所提出的 Marian 预训练模型不支持的语言，用户可以使用 M2M100 模型，该模型支持 100 种语言之间的直接翻译（无需经过英语中转）。完整支持的语言列表可在crate 文档中找到。

use rust_bert::pipelines::translation::{Language, TranslationModelBuilder};
fn main() -> anyhow::Result<()> {
    let model = TranslationModelBuilder::new()
        .with_source_languages(vec![Language::English])
        .with_target_languages(vec![Language::Spanish, Language::French, Language::Italian])
        .create_model()?;
    let input_text = "This is a sentence to be translated";
    let output = model.translate(&[input_text], None, Language::French)?;
    for sentence in output {
        println!("{}", sentence);
    }
    Ok(())
}

输出：

Il s'agit d'une phrase à traduire

使用预训练的 BART 模型进行摘要生成。

    let summarization_model = SummarizationModel::new(Default::default ()) ?;

let input = ["In findings published Tuesday in Cornell University's arXiv by a team of scientists \
from the University of Montreal and a separate report published Wednesday in Nature Astronomy by a team \
from University College London (UCL), the presence of water vapour was confirmed in the atmosphere of K2-18b, \
a planet circling a star in the constellation Leo. This is the first such discovery in a planet in its star's \
habitable zone — not too hot and not too cold for liquid water to exist. The Montreal team, led by Björn Benneke, \
used data from the NASA's Hubble telescope to assess changes in the light coming from K2-18b's star as the planet \
passed between it and Earth. They found that certain wavelengths of light, which are usually absorbed by water, \
weakened when the planet was in the way, indicating not only does K2-18b have an atmosphere, but the atmosphere \
contains water in vapour form. The team from UCL then analyzed the Montreal team's data using their own software \
and confirmed their conclusion. This was not the first time scientists have found signs of water on an exoplanet, \
but previous discoveries were made on planets with high temperatures or other pronounced differences from Earth. \
\"This is the first potentially habitable planet where the temperature is right and where we now know there is water,\" \
said UCL astronomer Angelos Tsiaras. \"It's the best candidate for habitability right now.\" \"It's a good sign\", \
said Ryan Cloutier of the Harvard–Smithsonian Center for Astrophysics, who was not one of either study's authors. \
\"Overall,\" he continued, \"the presence of water in its atmosphere certainly improves the prospect of K2-18b being \
a potentially habitable planet, but further observations will be required to say for sure. \"
K2-18b was first identified in 2015 by the Kepler space telescope. It is about 110 light-years from Earth and larger \
but less dense. Its star, a red dwarf, is cooler than the Sun, but the planet's orbit is much closer, such that a year \
on K2-18b lasts 33 Earth days. According to The Guardian, astronomers were optimistic that NASA's James Webb space \
telescope — scheduled for launch in 2021 — and the European Space Agency's 2028 ARIEL program, could reveal more \
about exoplanets like K2-18b."];

let output = summarization_model.summarize( & input);

（示例来自： WikiNews)

输出：

"科学家在距离地球110光年的行星K2-18b上发现了水蒸气。这是首次在恒星宜居带内的行星上发现此类现象。该行星的温度既不太热也不太冷，适合液态水存在。"

基于微软的 DialoGPT 的对话模型。此管道允许生成人类与模型之间的一轮或多轮对话。DialoGPT 的页面指出：

人类评估结果显示，在单轮对话图灵测试中，DialoGPT 生成的回复质量可与人类回复相媲美。 (DialoGPT 仓库)

该模型使用 ConversationManager 来跟踪正在进行的对话并为其生成回复。

use rust_bert::pipelines::conversation::{ConversationModel, ConversationManager};

let conversation_model = ConversationModel::new(Default::default ());
let mut conversation_manager = ConversationManager::new();

let conversation_id = conversation_manager.create("Going to the movies tonight - any suggestions?");
let output = conversation_model.generate_responses( & mut conversation_manager);

示例输出：

"The Big Lebowski."

根据提示生成语言。提供 GPT2 和 GPT 作为基础模型。包含束搜索、top-k 采样、核采样、温度设置和重复惩罚等技术。支持从多个提示批量生成句子。如果模型有填充标记，则序列将用填充标记左填充；否则将用未知标记填充。这可能会影响结果，建议提交长度相近的提示以获得最佳效果。

    let model = GPT2Generator::new(Default::default ()) ?;

let input_context_1 = "The dog";
let input_context_2 = "The cat was";

let generate_options = GenerateOptions {
max_length: 30,
..Default::default ()
};

let output = model.generate(Some( & [input_context_1, input_context_2]), generate_options);

示例输出：

[
    "然而，这只狗的主人不愿透露姓名。根据诉讼文件，该动物的主人是一位29岁的"
    "这只狗一直都是家庭的一员。‘他一直都会是我的狗，也一直都在照顾我’"
    "这只狗现在已经能在家里待了三个多月了。‘它是一只非常好的狗。她’"
    "这只猫本月早些时候在死者的一位亲属家中被发现。猫的主人希望匿名，"
    "这只猫是由两岁的贾兹敏从街上救回来的。‘我不知道该怎么办，’她说"
    "这只猫遭到两只流浪狗的袭击，随后被送往医院。另外两只猫也在此次袭击中受伤，正在接受治疗。"
]

使用针对自然语言推理任务微调的模型，对输入句子进行零样本分类，并提供标签。

    let sequence_classification_model = ZeroShotClassificationModel::new(Default::default ()) ?;

let input_sentence = "您在2020年会投票给谁？";
let input_sequence_2 = "首相宣布了一项刺激计划，该计划受到了反对派的广泛批评。";
let candidate_labels = & ["政治", "公共卫生", "经济", "体育"];

let output = sequence_classification_model.predict_multilabel(
& [input_sentence, input_sequence_2],
candidate_labels,
None,
128,
);

输出：

[
  [ Label { "政治", score: 0.972 }, Label { "公共卫生", score: 0.032 }, Label {"经济", score: 0.006 }, Label {"体育", score: 0.004 } ],
  [ Label { "政治", score: 0.975 }, Label { "公共卫生", score: 0.0818 }, Label {"经济", score: 0.852 }, Label {"体育", score: 0.001 } ],
]

预测句子的二元情感。基于SST-2数据集微调的DistilBERT模型。

    let sentiment_classifier = SentimentModel::new(Default::default ()) ?;

let input = [
"这可能是我最喜欢的电影，讲述的是无私、牺牲和为崇高事业奉献的故事，但它并不说教或枯燥。",
"这部电影试图同时成为太多东西：辛辣的政治讽刺、好莱坞大片、俗气的爱情喜剧、宣扬家庭价值观的宣传片……",
"如果你喜欢原汁原味、直击心灵的笑声，你一定会喜欢这部电影。无论你年轻还是年长，都会爱上这部电影，甚至连我妈妈都喜欢。",
];

let output = sentiment_classifier.predict( & input);

（示例来自IMDb）

输出：

[
    Sentiment { polarity: Positive, score: 0.9981985493795946 },
    Sentiment { polarity: Negative, score: 0.9927982091903687 },
    Sentiment { polarity: Positive, score: 0.9997248985164333 }
]

从文本中提取实体（人名、地点、组织、其他）。基于CoNNL03数据集微调的BERT cased large模型，由巴伐利亚州立图书馆的MDZ数字图书馆团队贡献。目前提供英语、德语、西班牙语和荷兰语版本。

    let ner_model = NERModel::new( default::default ()) ?;

let input = [
"我叫艾米。我住在巴黎。",
"巴黎是法国的一座城市。"
];

let output = ner_model.predict( & input);

输出：

[
  [
    Entity { word: "艾米", score: 0.9986, label: "I-PER" }
    Entity { word: "巴黎", score: 0.9985, label: "I-LOC" }
  ],
  [
    Entity { word: "巴黎", score: 0.9988, label: "I-LOC" }
    Entity { word: "法国", score: 0.9993, label: "I-LOC" }
  ]
]

从输入文档中提取关键词和关键短语。

fn main() -> anyhow::Result<()> {
    let keyword_extraction_model = KeywordExtractionModel::new(Default::default())?;

    let input = "Rust是一种多范式、通用的编程语言。\
       Rust强调性能、类型安全和并发性。Rust通过强制内存安全——即确保所有引用都指向有效的内存——来实现这一点，而无需像其他内存安全语言那样使用垃圾回收器或引用计数。为了同时保证内存安全并防止并发数据竞争，Rust的借用检查器会在编译时跟踪程序中所有引用的对象生命周期和变量作用域。Rust在系统编程领域很受欢迎，同时也提供了包括函数式编程结构在内的高级特性。";

    let output = keyword_extraction_model.predict(&[input])?;
}

输出：

"rust" - 0.50910604
"programming" - 0.35731024
"concurrency" - 0.33825397
"concurrent" - 0.31229728
"program" - 0.29115444

从文本中提取词性标签（名词、动词、形容词等）。

    let pos_model = POSModel::new( default::default ()) ?;

let input = ["我的名字是鲍勃"];

let output = pos_model.predict( & input);

输出：

[
    Entity { word: "My", score: 0.1560, label: "PRP" }
    Entity { word: "name", score: 0.6565, label: "NN" }
    Entity { word: "is", score: 0.3697, label: "VBZ" }
    Entity { word: "Bob", score: 0.7460, label: "NNP" }
]

生成句子嵌入（向量表示）。这些可以用于密集信息检索等应用。

    let model = SentenceEmbeddingsBuilder::remote(
SentenceEmbeddingsModelType::AllMiniLmL12V2
).create_model() ?;

let sentences = [
"这是一个示例句子",
"每个句子都会被转换"
];

let output = model.encode( & sentences) ?;

输出：

[
    [-0.000202666, 0.08148022, 0.03136178, 0.002920636 ...],
    [0.064757116, 0.048519745, -0.01786038, -0.0479775 ...]
]

预测输入句子中的掩码词汇。

    let model = MaskedLanguageModel::new(Default::default ()) ?;

let sentences = [
"你好，我是一名<mask>学生",
"巴黎是法国的<mask>。它位于欧洲的<mask>。"
];

let output = model.predict( & sentences);

输出：

[
    [MaskedToken { text: "college", id: 2267, score: 8.091}],
    [
        MaskedToken { text: "capital", id: 3007, score: 16.7249}, 
        MaskedToken { text: "located", id: 2284, score: 9.0452}
    ]
]