论文标题
NFLAT：中文命名实体识别的非静电变压器
NFLAT: Non-Flat-Lattice Transformer for Chinese Named Entity Recognition
论文作者
论文摘要
最近，Flat-Battice Transformer（Flat）在中国名称实体识别（NER）中取得了巨大的成功。 Flat通过构建平坦的晶格来执行词汇增强，从而减轻了模糊的单词边界和缺乏单词语义的困难。在公寓中，使用和结束字符的位置用于连接匹配的单词。但是，此方法在处理长文本时可能会匹配更多单词，从而导致长输入序列。因此，它大大增加了自我发项模块的记忆和计算成本。为了解决这个问题，我们提倡一种新型的词汇增强方法Interformer，该方法通过构造非灯泡晶格有效地降低了计算和内存成本的量。此外，以Interformer为骨干，我们为中文NFLAT实施NFLAT。 NFLAT将词汇融合和上下文特征编码。与平面相比，它减少了“单词字符”和“单词字”中不必要的注意计算。这将记忆使用量减少了约50％，可以使用更广泛的词典或更高的批次进行网络培训。在几个众所周知的基准上获得的实验结果证明了所提出的方法比最先进的混合（字符词）模型的优越性。
Recently, Flat-LAttice Transformer (FLAT) has achieved great success in Chinese Named Entity Recognition (NER). FLAT performs lexical enhancement by constructing flat lattices, which mitigates the difficulties posed by blurred word boundaries and the lack of word semantics. In FLAT, the positions of starting and ending characters are used to connect a matching word. However, this method is likely to match more words when dealing with long texts, resulting in long input sequences. Therefore, it significantly increases the memory and computational costs of the self-attention module. To deal with this issue, we advocate a novel lexical enhancement method, InterFormer, that effectively reduces the amount of computational and memory costs by constructing non-flat lattices. Furthermore, with InterFormer as the backbone, we implement NFLAT for Chinese NER. NFLAT decouples lexicon fusion and context feature encoding. Compared with FLAT, it reduces unnecessary attention calculations in "word-character" and "word-word". This reduces the memory usage by about 50% and can use more extensive lexicons or higher batches for network training. The experimental results obtained on several well-known benchmarks demonstrate the superiority of the proposed method over the state-of-the-art hybrid (character-word) models.
