Leveraging Pre-Trained Embeddings for Welsh Taggers
Leveraging Pre-Trained Embeddings for Welsh Taggers
复制标题
DOI：
10.18653/v1/w19-4332
复制
发表时间：
2019-08
期刊：
影响因子：
--
通讯作者：
I. Ezeani;S. Piao;Steven Neale;Paul Rayson;Dawn Knight
中科院分区：
文献类型：
--
作者：
I. Ezeani;S. Piao;Steven Neale;Paul Rayson;Dawn Knight
虽然单词嵌入模型在下游自然语言处理（NLP）任务中的应用已被证明是成功的，但由于缺乏足够的数据来训练模型，低资源语言的好处在一定程度上受到限制。然而，针对低资源语言的NLP研究工作一直专注于不断寻求利用预训练模型的方法，以提高为处理这些语言而构建的NLP系统的性能，而无需重新发明轮子。其中一种语言是威尔士语，因此，在本文中，我们提出了我们的实验结果，使用FastText的预训练嵌入模型学习一个简单的多任务神经网络模型，用于威尔士语的词性和语义标记。我们的模型的性能进行了比较，与现有的基于规则的独立标记部分的语音和语义标记。尽管它的简单性和能力，同时执行这两项任务，我们的tagger相比，非常好与现有的taggers。
While the application of word embedding models to downstream Natural Language Processing (NLP) tasks has been shown to be successful, the benefits for low-resource languages is somewhat limited due to lack of adequate data for training the models. However, NLP research efforts for low-resource languages have focused on constantly seeking ways to harness pre-trained models to improve the performance of NLP systems built to process these languages without the need to re-invent the wheel. One such language is Welsh and therefore, in this paper, we present the results of our experiments on learning a simple multi-task neural network model for part-of-speech and semantic tagging for Welsh using a pre-trained embedding model from FastText. Our model’s performance was compared with those of the existing rule-based stand-alone taggers for part-of-speech and semantic taggers. Despite its simplicity and capacity to perform both tasks simultaneously, our tagger compared very well with the existing taggers.