语义关系的并行学习
Concurrent Learning of Semantic Relations
摘要：
发现单词是否在语义上相关并识别它们之间的特定语义关系对于NLP至关重要，因为它对于IR中的查询扩展等任务至关重要。在这种情况下，已经提出了不同的方法，或者专门关注单个词汇关系，（例如，上位关系对随机关系）或学习能够识别多个语义关系的特定分类器（例如，上位关系对同义关系对随机关系）。在本文中，我们提出了另一种方法来看待依赖于多任务学习范式的问题。特别是，我们想研究是否可以通过并行学习另一个语义关系（例如，共同上下义关系）的学习过程中，一个给定的语义关系（例如，上位关系）得到改善。在此背景下，我们特别研究了半监督学习的好处，其中预测函数的训练是在少数标记数据和许多未标记数据上进行的。基于简单的学习策略和最先进的分布特征表示的初步结果表明，并行学习可以导致绝大多数测试情况下的改进。
英文摘要：
Discovering whether words are semantically related and identifying the specific semantic relation that holds between them is of crucial importance for NLP as it is essential for tasks like query expansion in IR. Within this context, different methodologies have been proposed that either exclusively focus on a single lexical relation (e.g. hypernymy vs. random) or learn specific classifiers capable of identifying multiple semantic relations (e.g. hypernymy vs. synonymy vs. random). In this paper, we propose another way to look at the problem that relies on the multi-task learning paradigm. In particular, we want to study whether the learning process of a given semantic relation (e.g. hypernymy) can be improved by the concurrent learning of another semantic relation (e.g. co-hyponymy). Within this context, we particularly examine the benefits of semi-supervised learning where the training of a prediction function is performed over few labeled data jointly with many unlabeled ones. Preliminary results based on simple learning strategies and state-of-the-art distributional feature representations show that concurrent learning can lead to improvements in a vast majority of tested situations.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
