In this work, we revisit the problem of semi-supervised named entity
recognition (NER) focusing on extremely light supervision, consisting of a
lexicon containing only 10 examples per class. We introduce ELLEN, a simple,
fully modular, neuro-symbolic method that blends fine-tuned language models
with linguistic rules. These rules include insights such as ''One Sense Per
Discourse'', using a Masked Language Model as an unsupervised NER, leveraging
part-of-speech tags to identify and eliminate unlabeled entities as false
negatives, and other intuitions about classifier confidence scores in local and
global context. ELLEN achieves very strong performance on the CoNLL-2003
dataset when using the minimal supervision from the lexicon above. It also
outperforms most existing (and considerably more complex) semi-supervised NER
methods under the same supervision settings commonly used in the literature
(i.e., 5% of the training data). Further, we evaluate our CoNLL-2003 model in a
zero-shot scenario on WNUT-17 where we find that it outperforms GPT-3.5 and
achieves comparable performance to GPT-4. In a zero-shot setting, ELLEN also
achieves over 75% of the performance of a strong, fully supervised model
trained on gold data. Our code is available at:
this https URL

在这项工作中，我们重新审视了半监督命名实体识别（NER）问题，重点是极度轻量级的监督，包括每类仅包含 10 个示例的词典。我们介绍了 ELLEN，这是一种简单、完全模块化的神经符号方法，将经过微调的语言模型与语言规则相结合。ELLEN 在使用以上词典中的最小监督时，在 CoNLL-2003 数据集上取得了非常强的性能。它在文献中通常使用的相同监督设置下，也优于大多数现有的（并且相对复杂得多）半监督 NER 方法。此外，我们在 WNUT-17 上以零样本场景评估了我们的 CoNLL-2003 模型，发现它的性能优于 GPT-3.5，并且实现了与 GPT-4 相当的性能。在零样本设置下，ELLEN 的性能也达到了基于金标数据训练的强有力、完全监督模型性能的 75% 以上。