Several language applications often require word semantics as a core part of their processing pipeline, either as precise meaning inference or semantic similarity. Multi-sense embeddings (M-SE) can be exploited for this important requirement. M-SE seeks to represent each word by their distinct senses in order to resolve the conflation of meanings of words as used in different contexts. Previous works usually approach this task by training a model on a large corpus and often ignore the effect and usefulness of the semantic relations offered by lexical resources. However, even with large training data, coverage of all possible word senses is still an issue. In addition, a considerable percentage of contextual semantic knowledge are never learned because a huge amount of possible distributional semantic structures are never explored. In this paper, we leverage the rich semantic structures in WordNet using a graph-theoretic walk technique over word senses to enhance the quality of multi-sense embeddings. This algorithm composes enriched texts from the original texts. Furthermore, we derive new distributional semantic similarity measures for M-SE from prior ones. We adapt these measures to word sense disambiguation (WSD) aspect of our experiment. We report evaluation results on 11 benchmark datasets involving WSD and Word Similarity tasks and show that our method for enhancing distributional semantic structures improves embeddings quality on the baselines. Despite the small training data, it achieves state-of-the-art performance on some of the datasets.
翻译:多个语言应用程序通常要求以文字语义作为处理管道的核心部分, 无论是作为精确含义的推断或语义相似性, 都需要用文字语义学作为处理管道的核心部分。 多语义嵌入( M- SE) 可用于此重要要求 。 M- SE 试图用不同的感知来代表每个单词。 M- SE 试图用它们不同的感知来解决不同背景中使用的词义含义的混和。 以前的工作通常会通过在大文体上培训一个模型来完成这项任务, 并常常忽视词汇学资源提供的语义关系的影响和有用性。 然而, 即便有了大量的培训数据, 对所有可能的字义感的覆盖仍然是一个问题。 此外, 大量背景语义嵌入( M- SE) 知识从未被利用过。 在本文中, 我们利用WordNet 中丰富的语义语义学结构, 来提高多语义嵌入的质量 。 这种算法将原始文本中的文字内容丰富起来。 此外, 我们从先前的M- SE- SE 的新的分布相似度测量度测量度测量度测量方法, 将SE- streal laveal laveal ad lavel lave lave lave dal lave lave lave lave laved dal dal dal dal dal dal laveal laveal laved dal dal daldal lavealdaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldalddsdsdsdsdddsdsdsdaldaldalddsdaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldaldalddddaldaldaldaldaldaldaldaldaldd