arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1405.7908cs.CLcs.AIcs.LG
收藏

语义合成与分解:从识别到生成

Semantic Composition and Decomposition: From Recognition to Generation

National Research Council Canada(加拿大国家研究委员会)

Peter D. Turney

摘要:

语义合成是通过对文本中单个词的意义进行合成来理解文本意义的任务。语义分解是通过将单个单词分解为单词含义中潜在的各个方面(因素,成分,组件)来理解单词含义的任务。我们采取分布式的方法来语义,其中一个词表示的上下文向量。最近的工作已经考虑了识别组合和分解的问题,但我们解决了更困难的生成问题。为了简单起见,我们专注于名词修饰语二元语法和名词一元语法。语义组合的测试是,给定名词-修饰语二元语法(“red salmon”)中的名词和修饰语的上下文向量,生成与给定二元语法(“sockeye”)同义的名词一元语法。语义分解的一个测试是,给定一个名词单字(“snifter”)的上下文向量,生成一个与给定单字(“brandy glass”)同义的名词修饰语二元语法。在WordNet中有大约73,000个一元词的词汇表,对于一个二元词有73,000个候选一元词组合,对于一个一元词有5,300,000,000个(73,000平方)候选二元词分解。我们在两个过程中生成潜在解决方案的排名列表。快速无监督学习算法生成候选者的初始列表,然后较慢的监督学习算法细化该列表。我们通过将候选解决方案与WordNet同义词集进行比较来评估候选解决方案。对于分解(unigram到bigram),排名最高的前100个bigram在50.7%的时间内包含给定unigram的WordNet同义词。对于组合(bigram到unigram),排名最高的前100个unigram包括给定bigram的WordNet同义词,占77.8%。

英文摘要:

Semantic composition is the task of understanding the meaning of text by composing the meanings of the individual words in the text. Semantic decomposition is the task of understanding the meaning of an individual word by decomposing it into various aspects (factors, constituents, components) that are latent in the meaning of the word. We take a distributional approach to semantics, in which a word is represented by a context vector. Much recent work has considered the problem of recognizing compositions and decompositions, but we tackle the more difficult generation problem. For simplicity, we focus on noun-modifier bigrams and noun unigrams. A test for semantic composition is, given context vectors for the noun and modifier in a noun-modifier bigram ("red salmon"), generate a noun unigram that is synonymous with the given bigram ("sockeye"). A test for semantic decomposition is, given a context vector for a noun unigram ("snifter"), generate a noun-modifier bigram that is synonymous with the given unigram ("brandy glass"). With a vocabulary of about 73,000 unigrams from WordNet, there are 73,000 candidate unigram compositions for a bigram and 5,300,000,000 (73,000 squared) candidate bigram decompositions for a unigram. We generate ranked lists of potential solutions in two passes. A fast unsupervised learning algorithm generates an initial list of candidates and then a slower supervised learning algorithm refines the list. We evaluate the candidate solutions by comparing them to WordNet synonym sets. For decomposition (unigram to bigram), the top 100 most highly ranked bigrams include a WordNet synonym of the given unigram 50.7% of the time. For composition (bigram to unigram), the top 100 most highly ranked unigrams include a WordNet synonym of the given bigram 77.8% of the time.

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。

↑