This paper describes the architecture and systems built towards solving the
SemEval 2023 Task 2: MultiCoNER II (Multilingual Complex Named Entity
Recognition) [1]. We evaluate two approaches (a) a traditional Conditional
Random Fields model and (b) a Large Language Model (LLM) fine-tuned with a
customized head and compare the two approaches. The novel ideas explored are:
1) Decaying auxiliary loss (with residual) - where we train the model on an
auxiliary task of Coarse-Grained NER and include this task as a part of the
loss function 2) Triplet token blending - where we explore ways of blending the
embeddings of neighboring tokens in the final NER layer prior to prediction 3)
Task-optimal heads - where we explore a variety of custom heads and learning
rates for the final layer of the LLM. We also explore multiple LLMs including
GPT-3 and experiment with a variety of dropout and other hyperparameter
settings before arriving at our final model which achieves micro & macro f1 of
0.85/0.84 (on dev) and 0.67/0.61 on the test data . We show that while
pre-trained LLMs, by themselves, bring about a large improvement in scores as
compared to traditional models, we also demonstrate that tangible improvements
to the Macro-F1 score can be made by augmenting the LLM with additional
feature/loss/model engineering techniques described above.

本文描述了解决 SemEval 2023 Task 2：MultiCoNER II（多语言复杂命名实体识别）问题所构建的体系结构和系统。我们评估了两种方法：传统的条件随机场模型和经过自定义头部微调的大型语言模型（LLM），并比较了这两种方法。我们探索的新想法有：1）衰减辅助损失（带剩余项）- 在模型上训练粗粒度 NER 的辅助任务并将其包括在损失函数的一部分中；2）三元标记混合 - 探索在最终 NER 层中预测之前混合相邻标记的嵌入方式；3）任务最优头部 - 探索各种用于 LLM 最终层的自定义头部和学习率。我们还尝试了多个 LLM，包括 GPT-3，并在最终模型中使用了多种 dropout 和其他超参数设置，该模型在开发数据上达到了 0.85/0.84 的微观和宏观 F1 值，并在测试数据上达到了 0.67/0.61。我们证明，虽然预训练的 LLM 本身相对传统模型带来了很大的改进，但通过上述额外特征 / 损失 / 模型工程技术的增强，我们还可以显著提高宏观 F1 分数。

大型语言模型不是你所需的全部

Large Language Models aren't all that you need

The MultiCoNER II task aims to detect complex, ambiguous, and fine-grained
named entities in low-context situations and noisy scenarios like the presence
of spelling mistakes and typos for multiple languages. The task poses
significant challenges due to the scarcity of contextual information, the high
granularity of the entities(up to 33 classes), and the interference of noisy
data. To address these issues, our team {\bf PAI} proposes a universal Named
Entity Recognition (NER) system that integrates external entity information to
improve performance. Specifically, our system retrieves entities with
properties from the knowledge base (i.e. Wikipedia) for a given text, then
concatenates entity information with the input sentence and feeds it into
Transformer-based models. Finally, our system wins 2 first places, 4 second
places, and 1 third place out of 13 tracks. The code is publicly available at
https://github.com/diqiuzhuanzhuan/semeval-2023.

本文介绍了一个通用的命名实体识别系统，其利用来自于 Wikipedia 的知识库信息，将其与输入文本进行拼接并使用 Transformer 模型进行训练，用于解决多语言、低上下文、存在拼写错误或者错别字的情况下进行的 MultiCoNER II 任务，取得了 13 个赛道中 2 个第一名、4 个第二名、1 个第三名的成绩。