Modeling and Learning Semantic Co-Compositionality through Prototype Projections and Neural Networks
Modeling and Learning Semantic Co-Compositionality through Prototype Projections and Neural Networks
复制标题
DOI：
--
复制
发表时间：
2013-10
期刊：
影响因子：
--
通讯作者：
Masashi Tsubaki;Kevin Duh;M. Shimbo;Yuji Matsumoto
中科院分区：
文献类型：
--
作者：
Masashi Tsubaki;Kevin Duh;M. Shimbo;Yuji Matsumoto
提出了一种新的语义协同构件性向量空间模型。在生成词汇理论(Pustejovsky，1995)的启发下，我们的目标是建立一个构词模式，在这个模式中，谓词和论元都可以在生成整体语义的同时修改彼此的意义表征。这很容易解决当前向量空间模型的一些主要挑战，特别是一词多义问题和每种单词类型使用一个表示。我们使用谓词/论元上的原型投影来实现协同合成性，并表明这在适应它们的单词表示方面是有效的。我们进一步将该模型转化为神经网络，并提出了一种无监督算法来联合训练具有共构性的词表示。到目前为止，该模型在及物动词的语义相似性任务上取得了最好的结果(ρ=0.47)。
We present a novel vector space model for semantic co-compositionality. Inspired by Generative Lexicon Theory (Pustejovsky, 1995), our goal is a compositional model where both predicate and argument are allowed to modify each others’ meaning representations while generating the overall semantics. This readily addresses some major challenges with current vector space models, notably the polysemy issue and the use of one representation per word type. We implement cocompositionality using prototype projections on predicates/arguments and show that this is effective in adapting their word representations. We further cast the model as a neural network and propose an unsupervised algorithm to jointly train word representations with co-compositionality. The model achieves the best result to date (ρ = 0.47) on the semantic similarity task of transitive verbs (Grefenstette and Sadrzadeh, 2011).