Our software system simulates the classical collaborative Japanese poetry form, renga, made of linked haikus. We used NLP methods wrapped up as web services. This approach is suitable for collaborative human-AI generation, as well as purely computer-generated poetry. Evaluation included a blind survey comparing AI and human haiku. To gather ideas for future work, we examine related research in ...

546 doi: 10.1097/ALN.0000000000001289 Instead of dance, Erato (“beloved”) governed romance as the Muse of Love Poetry. On this Italian card advertising a company cofounded by chloroform pioneer Justus von Liebig (1803 to 1873), a seated Erato (right) is pictured playing the cithara, the musical and etymological precursor to today’s guitar. If a 20th-century actor portrayed Erato poorly, that th...

Although sentiment analysis in Chinese social media has attracted a lot of interest in recent years, it has been less explored in traditional Chinese literature (e.g., classical Chinese poetry) due to the lack of sentiment lexicon resources. In this paper, we propose a weakly supervised approach based on Weighted Personalized PageRank (WPPR) to create a sentiment lexicon for classical Chinese p...

Identical rhymes (right/write, attire/retire) are considered satisfactory and even artistic in French poetry but are considered unsatisfactory in English. This has been a consistent generalization over the course of centuries, a surprising fact given that other aspects of poetic form in French were happily applied in English. This paper puts forward the hypothesis that this difference is not me...

Several poetry generation systems that are in some way inspired or motivated by existing articles such as newspaper stories have recently appeared. However, most if not all of them employ template-based generation, which limits both the expressiveness of the system and the ability to faithfully convey the message of the source article. In this paper we present our work on a poetry generation sy...

Due to differences in form, style and culture between the original and the translated version of ancient Chinese poetry, the meaning of translated ancient Chinese poems is bound to differ from that of the originals. Therefore, to certain extent some ancient Chinese poems can never be completely translated; but it is possible that they can be better translated so that the reader of the translate...

In this paper we describe the difficulties of poetry generation, particularly in contrast to traditional informative natural language generation. We then point out deficiencies of previous attempts at poetry generation, and propose a stochastic hillclimbing search model which addresses these deficiencies. We present both conceptual and implemented details of the most important aspects of such a...

Many years ago I received an urgent Friday afternoon consult from the surgery service. ‘‘Incipient DTs,’’ the resident told me. ‘‘We’ve got this guy, status-post pancreatitis, post-op cholecystectomy, he’s going down the tube.’’ It turned out that the patient was an irascible middle-aged man named Chuck Benderton who a day or so after surgery had gotten agitated and started to swear at his doct...

We present SPARSAR, a system for the automatic analysis of poetry(and text) style which makes use of NLP tools like tokenizers, sentence splitters, NER (Name Entity Recognition) tools, and taggers. Our system in addition to the tools listed above which aim at obtaining the same results of quantitative linguistics, adds a number of additional tools for syntactic and semantic structural analysis ...

The ultimate goal of the poetry assistant currently under development in our lab is an application to be used either as a poetry game or as a teaching tool for both poetry and grammar, including the complex relationships between sound and meaning. Until now we focused on the automatic classification of poems and the suggestion of the ending word for a verse. The classification module is based o...