LSTM-based language models have been shown effective in Word Sense Disambiguation (WSD). In particular, the technique proposed by Yuan et al. (2016) returned state-of-the-art performance in several benchmarks, but neither the training data nor the source code was released. This paper presents the results of a reproduction study and analysis of this technique using only openly available datasets (GigaWord, SemCor, OMSTI) and software (TensorFlow). Our study showed that similar results can be obtained with much less data than hinted at by Yuan et al. (2016). Detailed analyses shed light on the strengths and weaknesses of this method. First, adding more unannotated training data is useful, but is subject to diminishing returns. Second, the model can correctly identify both popular and unpopular meanings. Finally, the limited sense coverage in the annotated datasets is a major limitation. All code and trained models are made freely available.
展开▼
机译：基于LSTM的语言模型已在Word Sense Dismigation（WSD）中有效。特别是袁等人提出的技术。 （2016）在几个基准中返回最先进的性能，但训练数据和源代码都没有发布。本文仅使用公开可用的数据集（GigaWord，Semcor，OMSTI）和软件（TensorFlow）来介绍对该技术的再现研究和分析的结果。我们的研究表明，可以获得类似的结果，这些结果比Yuan等人暗示。 （2016）。详细分析了这种方法的优点和弱点的阐明。首先，添加更多未解除的培训数据是有用的，但须逐渐减少。其次，该模型可以正确识别流行和不受欢迎的含义。最后，注释数据集中的有限意义覆盖率是一个重大限制。所有代码和培训的型号都是免费提供的。
展开▼
