Instituto de Física Enrique Gaviola, Consejo Nacional de Investigaciones Científicas y Técnicas(恩里克·加维奥拉物理研究所,国家科学技术研究委员会);Universidad Nacional de Córdoba(科尔多瓦国立大学);Centro Atómico Bariloche(巴里洛切原子能中心);Instituto Balseiro(巴尔塞iro研究所);Comisión Nacional de Energía Atómica(国家原子能委员会);Universidad Nacional de Cuyo(库约国立大学);Consejo Nacional de Investigaciones Científicas y Técnicas(国家科学技术研究委员会)
We analyze the frequency-rank relationship in sub-vocabularies corresponding to three different grammatical classes (nouns, verbs, and others) in a collection of literary works in English, whose words have been automatically tagged according to their grammatical role. Comparing with a null hypothesis which assumes that words belonging to each class are uniformly distributed across the frequency-ranked vocabulary of the whole work, we disclose statistically significant differences between the three classes. This results point to the fact that frequency-rank relationships may reflect linguistic features associated with grammatical function.
Allen Institute for AI(艾伦人工智能研究所);Bar Ilan University(巴伊兰大学)
We present a word-sense induction method based on pre-trained masked language models (MLMs), which can cheaply scale to large vocabularies and large corpora. The result is a corpus which is sense-tagged according to a corpus-derived sense inventory and where each sense is associated with indicative words. Evaluation on English Wikipedia that was sense-tagged using our method shows that both the induced senses, and the per-instance sense assignment, are of high quality even compared to WSD methods, such as Babelfy. Furthermore, by training a static word embeddings algorithm on the sense-tagged …
Heaps' law and Heaps functions in tagged texts: Evidences of their linguistic relevance
Instituto de Física Enrique Gaviola(恩里克·加维奥拉物理研究所);Consejo Nacional de Investigaciones Científicas y Técnicas(国家科学技术研究委员会);Universidad Nacional de Córdoba(科尔多瓦国立大学);Centro Atómico Bariloche(巴里洛切原子中心);Instituto Balseiro(巴尔塞罗研究所);Comisión Nacional de Energía Atómica(国家原子能委员会);Universidad Nacional de Cuyo(库约国立大学)
National Institute of Information and Communications Technology(国立信息与通信技术研究所)
Let $f (\cdot)$ be the absolute frequency of words and $r$ be the rank of words in decreasing order of frequency, then the following function can fit the rank-frequency relation \[ f (r;s,t) = \left(\frac{r_{\tt max}}{r}\right)^{1-s} \left(\frac{r_{\tt max}+t \cdot r_{\tt exp}}{r+t \cdot r_{\tt exp}}\right)^{1+(1+t)s} \] where $r_{\tt max}$ and $r_{\tt exp}$ are the maximum and the expectation of the rank, respectively; $s>0$ and $t>0$ are parameters estimated from data. On well-behaved data, there should be $s<1$ and $s \cdot t < 1$.
School of Business London South Bank University(伦敦南岸大学商学院);Sapienza University of Rome(罗马第一大学);School of Business University of Leicester(莱斯特大学商学院);Bucharest University of Economic Studies(布加勒斯特经济研究大学)
This paper deals with a quantitative analysis of the content of official political speeches. We study a set of about one thousand talks pronounced by the US Presidents, ranging from Washington to Trump. In particular, we search for the relevance of the rare words, i.e. those said only once in each speech -- the so-called hapaxes. We implement a rank-size procedure of Zipf-Mandelbrot type for discussing the hapaxes' frequencies regularity over the overall set of speeches. Starting from the obtained rank-size law, we define and detect the core of the hapaxes set by means of a procedure based on …
University of California Merced(加利福尼亚大学默塞德分校);University of California Los Angeles(加利福尼亚大学洛杉矶分校)
The availability of large linguistic data sets enables data-driven approaches to study linguistic change. The Google Books corpus unigram frequency data set is used to investigate the word rank dynamics in eight languages. We observed the rank changes of the unigrams from 1900 to 2008 and compared it to a Wright-Fisher inspired model that we developed for our analysis. The model simulates a neutral evolutionary process with the restriction of having no disappearing and added words. This work explains the mathematical framework of the model - written as a Markov Chain with multinomial transitio…
National University(国立大学);De La Salle University(德拉萨大学)
Assessing the proper difficulty levels of reading materials or texts in general is the first step towards effective comprehension and learning. In this study, we improve the conventional methodology of automatic readability assessment by incorporating the Word Mover's Distance (WMD) of ranked texts as an additional post-processing technique to further ground the difficulty level given by a model. Results of our experiments on three multilingual datasets in Filipino, German, and English show that the post-processing technique outperforms previous vanilla and ranking-based models using SVM.
Math word problem (MWP) is a challenging and critical task in natural language processing. Many recent studies formalize MWP as a generation task and have adopted sequence-to-sequence models to transform problem descriptions to mathematical expressions. However, mathematical expressions are prone to minor mistakes while the generation objective does not explicitly handle such mistakes. To address this limitation, we devise a new ranking task for MWP and propose Generate & Rank, a multi-task framework based on a generative pre-trained language model. By joint training with generation and rankin…
Linguistic complexity: English vs. Polish, text vs. corpus
Institute of Nuclear Physics, Polish Academy of Sciences(波兰科学院核物理研究所);Faculty of Mathematics and Natural Sciences, University of Rzeszów(热舒夫大学数学与自然科学学院)
National University of Singapore(新加坡国立大学);University of Southern California(南加州大学);The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳));Kriston AI(科通智能)
Word and sentence embeddings are useful feature representations in natural language processing. However, intrinsic evaluation for embeddings lags far behind, and there has been no significant update since the past decade. Word and sentence similarity tasks have become the de facto evaluation method. It leads models to overfit to such evaluations, negatively impacting embedding models' development. This paper first points out the problems using semantic similarity as the gold standard for word and sentence embedding evaluations. Further, we propose a new intrinsic evaluation method called EvalR…
Stanford University(斯坦福大学);University of Pennsylvania(宾夕法尼亚大学)
The word embedding association test (WEAT) is an important method for measuring linguistic biases against social groups such as ethnic minorities in large text corpora. It does so by comparing the semantic relatedness of words prototypical of the groups (e.g., names unique to those groups) and attribute words (e.g., 'pleasant' and 'unpleasant' words). We show that anti-black WEAT estimates from geo-tagged social media data at the level of metropolitan statistical areas strongly correlate with several measures of racial animus--even when controlling for sociodemographic covariates. However, we …
A Generative Word Embedding Model and its Low Rank Positive Semidefinite Solution
Joint NTU-UBC Research Centre of Excellence in Active Living for the Elderly (LILY)(南洋理工大学-不列颠哥伦比亚大学活跃老年生活卓越联合研究中心(LILY));Nanyang Technological University(南洋理工大学);Tsinghua University(清华大学)
Laboratoire de Physique Statistique et Systèmes Complexes, ISMANS(ISMANS统计物理与复杂系统实验室);Hua-Zhong Normal University(华中师范大学);Université du Maine(曼恩大学);Yerevan Physics Institute(埃里温物理研究所);University of Heilongjiang(黑龙江大学)
Informational Space of Meaning for Scientific Texts
University of Leicester(莱斯特大学)
在自然语言处理中,文本意义的自动提取是一个重要的问题。我们的重点是短的科学文本(摘要或简要报告)的意义的计算分析。本文提出了一种向量空间模型来量化词语和文本的意义。我们引入了意义空间,在这个意义空间中,一个词的意义由一个关于文本所属主题类别的相对信息增益(RIG)向量来表示,这些信息增益可以通过观察文本中的词来获得。基于莱斯特科学语料库(LSC)和莱斯特科学词典核心(LScDC),将该方法应用于语义空间的构建。LSC是一个包含1,673,350个摘要的科学语料库,LScDC是一个科学词典,其中的单词是从LSC中提取的。LSC中的每个文本至少属于Web of Science(WoS)的252个主题类别中的一个。这些类别用于构建信息增益的向量。的意义空间的描述和统计分析的LSC与LScDC。建议的表示模型的有用性进行评估,通过在每个类别中排名靠前的话。信息量最大的n个单词被排序。我们证明了基于RIG的单词排名比基于原始词频的排名在确定单词的科学特定含义和重要性方面更有用。该模型的基础上RIG被证明有能力脱颖而出的主题特定的词在类别中。最具信息性的词是252类。新的科学词典和103,998 x 252词类别RIG矩阵可在线获得。意义空间的分析为我们提供了一个工具,进一步探索量化的文本意义使用更复杂的和上下文相关的意义模型,使用词及其组合的共现。
Mangalore University(芒格洛尔大学);Instituto Politécnico Nacional (IPN)(墨西哥国立理工学院)
The task of automatically identifying a language used in a given text is called Language Identification (LI). India is a multilingual country and many Indians especially youths are comfortable with Hindi and English, in addition to their local languages. Hence, they often use more than one language to post their comments on social media. Texts containing more than one language are called "code-mixed texts" and are a good source of input for LI. Languages in these texts may be mixed at sentence level, word level or even at sub-word level. LI at word level is a sequence labeling problem where ea…