In this paper we take a state-of-the-art model for distributed word representation that explicitly factorizes the positive pointwise mutual information (PPMI) matrix using window sampling and negative sampling and address two of its shortcomings. We improve syntactic performance by using positional contexts, and solve the need to store the PPMI matrix in memory by working on aggregate data in e...

Pointwise mutual information (PMI), a simple measure of lexical association, is part of several algorithms used as models of lexical semantic memory. Typically, it is used as a component of more complex distributional models rather than in isolation. We show that when two simple techniques are applied—(1) down-weighting co-occurrences involving lowfrequency words in order to address PMI’s so-ca...

中文的方位詞組主要可以前飾詞(以、之)與後綴詞(邊、面、頭),結合明確的方向指引 (如:前後、上下、左右、裡外等)組合而成。這樣的組成在實際使用上,卻會有避免使 用或不存在的組合邏輯,同時這樣的現象亦發生在方位短語構成上。本研究試使用計算 統計方法,分析在 Sketch Engine 中取得的方位名詞組的概念合成模式。在詞彙概念方 面,我們使用具知識層級架構的中文同義詞詞林[1]進行將詞彙的概念探索,並計算方 位短句裡所包含的知識概念組成模式,最後試從統計方法上尋得詮釋概念與方位詞組組 合模式的實證資訊。在本研究之中,我們使用了資訊度量方法中的互斥資訊(Point-wise Mutual Information, PMI)進行統計分析兩個詞組概念間的相關性,並使用多變數互斥資 訊 (Multivariate Mutual Information, MMI)[2]進行三個概念間的相關分...

We describe our submission to SemEval-2016 Task 3 on Community Question Answering. We participated in subtask A, which asks to rerank the comments from the thread for a given forum question from good to bad. Our approach focuses on the generation and use of goodness polarity lexicons, similarly to the sentiment polarity lexicons, which are very popular in sentiment analysis. In particular, we u...

Recent exploratory efforts in discourse-level language modeling have relied heavily on calculating Pointwise Mutual Information (PMI), which involves significant computation when done over large collections. Prior work has required aggressive pruning or independence assumptions to compute scores on large collections. We show the method of Conditional Random Sampling, thus far an underutilized t...

We review lexical Association Measures (AMs) that have been employed by past work in extracting multiword expressions. Our work contributes to the understanding of these AMs by categorizing them into two groups and suggesting the use of rank equivalence to group AMs with the same ranking performance. We also examine how existing AMs can be adapted to better rank English verb particle constructi...

Neural encoding and decoding focus on the question: " What does the response of a neuron tell us about a stimulus ". In this chapter we consider a related but different question: " How much does the neural response tell us about a stimulus ". The techniques of information theory allow us to answer this question in a quantitative manner. Furthermore, we can use them to ask what forms of neural r...

Abstract Hyperspectral images (HSI) present a wealth of information. It is distinguished by its high dimensionality. served humanity in many fields. The quantity HSI information represents double-edged sword. As consequence, their dimensionality must be reduced. Nowadays, several methods are proposed to overcome duress. most useful and essential solution selection approaches hyperspectral bands...