Related papers: Shakespeare, Entropy and Educated Monkeys
We consider the problem of making machine translation more robust to character-level variation at the source side, such as typos. Existing methods achieve greater coverage by applying subword models such as byte-pair encoding (BPE) and…
Recently, it has been claimed that a linear relationship between a measure of information content and word length is expected from word length optimization and it has been shown that this linearity is supported by a strong correlation…
Human languages expand vocabularies by combining existing morphemes rather than inventing arbitrary forms. Communicative efficiency shapes lexical systems at multiple levels (Gibson et al., 2019), yet morphological composition -- combining…
The amount of dialogue history to include in a conversational agent is often underestimated and/or set in an empirical and thus possibly naive way. This suggests that principled investigations into optimal context windows are urgently…
Automated writing evaluation (AWE) has been shown to be an effective mechanism for quickly providing feedback to students. It has already seen wide adoption in enterprise-scale applications and is starting to be adopted in large-scale…
Cerny's conjecture is a longstanding open problem in automata theory. We study two different concepts, which allow to approach it from a new angle. The first one is the triple rendezvous time, i.e., the length of the shortest word mapping…
This study investigates whether professional translators without prior specialized training can reliably identify short stories generated in Italian by artificial intelligence (AI). Sixty-nine translators took part in an in-person…
In open-domain dialogue intelligent agents should exhibit the use of knowledge, however there are few convincing demonstrations of this to date. The most popular sequence to sequence models typically "generate and hope" generic utterances…
Generating high-quality and diverse essays with a set of topics is a challenging task in natural language generation. Since several given topics only provide limited source information, utilizing various topic-related knowledge is essential…
An automaton is synchronizing if there is a word that maps all states onto the same state. \v{C}ern\'{y}'s conjecture on the length of the shortest such word is probably the most famous open problem in automata theory. We consider the…
We review some recent endeavors and add some new results to characterize and understand underlying mechanisms in Wikipedia (WP), the paradigmatic example of collaborative value production. We analyzed the statistics of editorial activity in…
We obtain an index of the complexity of a random sequence by allowing the role of the measure in classical probability theory to be played by a function we call the generating mechanism. Typically, this generating mechanism will be a finite…
Metaphors are a distinctive feature of literary language, yet they remain less studied experimentally than everyday metaphors. Moreover, previous psycholinguistic and computational approaches overlooked the temporal dimension, although many…
If a macroscopic (random) classical system is put into a random state in phase space, it will of course the most likely have an almost maximal entropy according to second law of thermodynamics. We will show, however, the following theorem:…
English as foreign language_EFL_students' use of text generated from artificial intelligence_AI_natural language generation_NLG_tools may improve their writing quality. However, it remains unclear to what extent AI-generated text in these…
In this paper, we try to explore the evolution of language through case calculations. First, we chose the novels of eleven British writers from 1400 to 2005 and found the corresponding works; Then, we use the natural language processing…
The paper explores stylometry as a method to distinguish between texts created by Large Language Models (LLMs) and humans, addressing issues of model attribution, intellectual property, and ethical AI use. Stylometry has been used…
Artificial agents have been shown to learn to communicate when needed to complete a cooperative task. Some level of language structure (e.g., compositionality) has been found in the learned communication protocols. This observed structure…
Artificial intelligence has made significant progress in natural language processing, with models like GPT-3 demonstrating impressive capabilities. However, these models still have limitations when it comes to complex tasks that require an…
Painting captions are often dry and simplistic which motivates us to describe a painting creatively in the style of Shakespearean prose. This is a difficult problem, since there does not exist a large supervised dataset from paintings to…