Related papers: Universal versus system-specific features of punct…
Selection through iterated learning explains no more than other non-functional accounts, such as universal grammar, why language is so well-designed for communicative efficiency. It does not predict several distinctive features of language…
This paper describes a hybrid system for WSD, presented to the English all-words and lexical-sample tasks, that relies on two different unsupervised approaches. The first one selects the senses according to mutual information proximity…
Automatic annotation of temporal expressions is a research challenge of great interest in the field of information extraction. In this report, I describe a novel rule-based architecture, built on top of a pre-existing system, which is able…
Authorship attribution models fine-tuned with the same pretrained encoder, data, and loss can differ four-fold in performance depending only on their scoring mechanism. We use mechanistic interpretability tools to explain this gap.…
Natural languages are described in this paper in terms of networks of synonyms: a word is identified with a node, and synonyms are connected by undirected links. Our statistical analysis of the network of synonyms in Polish language showed…
A prefix normal word is a binary word with the property that no substring has more 1s than the prefix of the same length. This class of words is important in the context of binary jumbled pattern matching. In this paper we present an…
Of basic interest is the quantification of the long term growth of a language's lexicon as it develops to more completely cover both a culture's communication requirements and knowledge space. Here, we explore the usage dynamics of words in…
Statistics pedagogy values using a variety of examples. Thanks to text resources on the Web, and since statistical packages have the ability to analyze string data, it is now easy to use language-based examples in a statistics class. Three…
Understanding the reasons behind the exceptional success of transformers requires a better analysis of why attention layers are suitable for NLP tasks. In particular, such tasks require predictive models to capture contextual meaning which…
Human language has a distinct systematic structure, where utterances break into individually meaningful words which are combined to form phrases. We show that natural-language-like systematicity arises in codes that are constrained by a…
Zipf's law seems to be ubiquitous in human languages and appears to be a universal property of complex communicating systems. Following the early proposal made by Zipf concerning the presence of a tension between the efforts of speaker and…
Unsupervised learning objectives like autoregressive and masked language modeling constitute a significant part in producing pre-trained representations that perform various downstream applications from natural language understanding to…
The aim of this article is to determine a new six-parameter Beta Weibull distribution and its various associated functions, namely the cumulative distribution, survival, probability density and hazard functions. Next, we determine the…
Human lexicons contain many different words that speakers can use to refer to the same object, e.g., "purple" or "magenta" for the same shade of color. On the one hand, studies on language use have explored how speakers adapt their…
We focus on the statistics of word occurrences and of the waiting times between such occurrences in Blogs. Due to the heterogeneity of words' frequencies, the empirical analysis is performed by studying classes of "frequently-equivalent"…
An important body of quantitative linguistics is constituted by a series of statistical laws about language usage. Despite the importance of these linguistic laws, some of them are poorly formulated, and, more importantly, there is no…
The relationship between the length of a word and the maximum length of its unbordered factors is investigated in this paper. Consider a finite word w of length n. We call a word bordered, if it has a proper prefix which is also a suffix of…
Sentences are important semantic units of natural language. A generic, distributional representation of sentences that can capture the latent semantics is beneficial to multiple downstream applications. We observe a simple geometry of…
Classically in combinatorics on words one studies unavoidable regularities that appear in sufficiently long strings of symbols over a fixed size alphabet. In this paper we take another viewpoint and focus on combinatorial properties of long…
A pattern $\alpha$ is a string of variables and terminal letters. We say that $\alpha$ matches a word $w$, consisting only of terminal letters, if $w$ can be obtained by replacing the variables of $\alpha$ by terminal words. The matching…