[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$f0C7v03PlRuvZYO7TWp2aq2EzbAV7JSiEDzxsStv6YeE":3},{"answer":4,"createTime":5,"id":6,"options":7,"origin":12,"question":19,"related":20,"source":30,"type":31},[],"2026-01-13 14:23:34",311318058,[8,9,10,11],"编码器和解码器","自注意力和前馈网络","卷积层和池化层","循环层和全连接层",{"count":13,"courseId":14,"courseImg":15,"courseName":16,"workId":17,"workName":18},14,"53e1d2ef4961cca8eea3e23969ad2cb9","https:\u002F\u002Ftihai-oss-cloud.itihey.com\u002Fimg\u002F03a579384a6dc297c89809b582fcc767.png","默认课程","9425d18261444a8f8c3b3c56f00d0690","单元测试","Seq2Seq 模型的核心组成是( )",[21,32,41,49,58,67,76,85,94,103],{"answer":22,"createTime":5,"id":23,"options":24,"question":29,"source":30,"type":31},[],311318048,[25,26,27,28],"一个完整的句子","分词后的最小处理单位","词向量的维度","文本的语义标签","自然语言处理(NLP)中,"Token" 的本质是( )","v1",0,{"answer":33,"createTime":5,"id":34,"options":35,"question":40,"source":30,"type":31},[],311318049,[36,37,38,39],"余弦相似度","欧式距离","均方误差(MSE)","Jaccard 相似度","以下哪种不属于文本相似度的计算方法?( )",{"answer":42,"createTime":5,"id":43,"options":44,"question":48,"source":30,"type":31},[],311318050,[45,8,46,47],"CBOW 和 Skip-Gram","BERT 和 GPT","词袋模型和 Seq2Seq","Word2Vec 包含的两种核心模型是( )",{"answer":50,"createTime":5,"id":51,"options":52,"question":57,"source":30,"type":31},[],311318051,[53,54,55,56],"循环结构","卷积操作","自注意力机制","池化层","Transformer 模型的核心创新是( )",{"answer":59,"createTime":5,"id":60,"options":61,"question":66,"source":30,"type":31},[],311318052,[62,63,64,65],"GPT","BERT","Seq2Seq","T5","仅采用编码器结构,擅长语义理解任务的模型是( )",{"answer":68,"createTime":5,"id":69,"options":70,"question":75,"source":30,"type":31},[],311318053,[71,72,73,74],"无法处理长文本","忽略词语的顺序和上下文关系","词向量维度过高","训练效率低","词袋模型(BoW)的主要缺陷是( )",{"answer":77,"createTime":5,"id":78,"options":79,"question":84,"source":30,"type":31},[],311318054,[80,81,82,83],"词性标注","图像分割","机器翻译","命名实体识别","以下哪种不属于 NLP 的典型任务?( )",{"answer":86,"createTime":5,"id":87,"options":88,"question":93,"source":30,"type":31},[],311318055,[89,90,91,92],"语义理解","自然语言生成","多模态处理","并行计算效率","GPT 系列模型的核心优势是( )",{"answer":95,"createTime":5,"id":96,"options":97,"question":102,"source":30,"type":31},[],311318056,[98,99,100,101],"我","爱","北京","安门","文本 "我爱北京天安门" 分词后,按词分的 Token 不包括( )",{"answer":104,"createTime":5,"id":105,"options":106,"question":111,"source":30,"type":31},[],311318057,[107,108,109,110],"完全不同的概念","词向量是技术,词嵌入是数据存在形式","词嵌入是词向量的子集","词向量维度高于词嵌入","词向量和词嵌入的关系是( )"]