Generating Classical Chinese Poems from Vernacular Chinese

Yang, Zhichao; Cai, Pengshan; Feng, Yansong; Li, Fēi; Feng, Weijiang; Chiu, Elena Suet-Ying; Yu, Hong

doi:10.18653/v1/d19-1637

Cited by 15 publications

(8 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Reinforcement learning has been applied in various natural language generation tasks, including image caption (Rennie et al, 2017), automatic summarization (Paulus et al, 2018), machine translation (Kang et al, 2020) and poem generation (Yang et al, 2019). Specifically, when applying reinforcement learning in dialogue generation (Li et al, 2016;Zhao et al, 2019;Shi et al, 2019;Yamazaki and Aizawa, 2021;, self-play is often used to enable scoring multi-turn dialogues.…”

Section: Rl In Text Generationmentioning

confidence: 99%

Learning as Conversation: Dialogue Systems Reinforced for Information Acquisition

Cai¹,

Wan²,

Liu³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

We propose novel AI-empowered chat bots for learning as conversation where a user does not read a passage but gains information and knowledge through conversation with a teacher bot. Our information-acquisitionoriented dialogue system employs a novel adaptation of reinforced self-play so that the system can be transferred to various domains without in-domain dialogue data, and can carry out conversations both informative and attentive to users. Our extensive subjective and objective evaluations on three large public data corpora demonstrate the effectiveness of our system to deliver knowledge-intensive and attentive conversations and help end users substantially gain knowledge without reading passages. Our code and datasets are publicly available 1 for follow-up research.

show abstract

Section: Rl In Text Generationmentioning

confidence: 99%

Learning as Conversation: Dialogue Systems Reinforced for Information Acquisition

Cai¹,

Wan²,

Liu³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Our preliminary experiments on English showed that character-level models learn easily to generate acrostics by themselves, however do not follow the topic as coherently as word-level models. Zhang and Lapata (2014); Zhang et al (2017); ; Yi et al (2018a,c); Yang et al (2019) are other examples of work on generating Chinese poems, but did not focus on acrostics. Ghazvininejad et al (2016Ghazvininejad et al ( , 2017 built a model to generate poems based on topics in a similar fashion to ours.…”

Section: Related Workmentioning

confidence: 99%

Acrostic Poem Generation

Agarwal

Kann

2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

We propose a new task in the area of computational creativity: acrostic poem generation in English. Acrostic poems are poems that contain a hidden message; typically, the first letter of each line spells out a word or short phrase. We define the task as a generation task with multiple constraints: given an input word, 1) the initial letters of each line should spell out the provided word, 2) the poem's semantics should also relate to it, and 3) the poem should conform to a rhyming scheme. We further provide a baseline model for the task, which consists of a conditional neural language model in combination with a neural rhyming model. Since no dedicated datasets for acrostic poem generation exist, we create training data for our task by first training a separate topic prediction model on a small set of topic-annotated poems and then predicting topics for additional poems. Our experiments show that the acrostic poems generated by our baseline are received well by humans and do not lose much quality due to the additional constraints. Last, we confirm that poems generated by our model are indeed closely related to the provided prompts, and that pretraining on Wikipedia can boost performance.

show abstract

“…They report relatively high scores (between 3.6 and 4.06 on the average) for their best model. Yang et al (2019) model poem generation as an unsupervised machine translation problem. Their system takes text written in vernacular Chinese as input and produces a poem in classical Chinese as output.…”

Section: R Elated W Ork On P Oem G Enerationmentioning

confidence: 99%

Generating Creative Language - Theories, Practice and Evaluation

Hämäläinen

2020

Preprint

View full text Add to dashboard Cite

This thesis presents approaches to computationally creative natural language generation focusing on theoretical foundations, practical solutions and evaluation. I defend that a theoretical definition is crucial for computational creativity and that the practical solution must closely follow the theoretical definition. Finally, evaluation must be based on the underlying theory and what was actually modelled in the practical solution. A theoretical void in the existing theoretical work on computational creativity is identified. The existing theories do not explicitly take into account the communicative nature of natural language. Therefore, a new theoretical framework is elaborated that identifies how computational creativity can take place in a setting that has a clear communicative goal. This introduces a communicative-creative trade off that sets limits to creativity in such a communicative context. My framework divides creativity in three categories: message creativity, contextual creativity and communicative creativity. Any computationally creative NLG approach not taking communicativity into account is called mere surface generation.I propose a novel master-apprentice approach for creative language generation. The approach consists of a genetic algorithm, the fitness functions of which correspond to different parameters defined as important for the creative task in question from a theoretical perspective. The output of the genetic algorithm together with possible human authored data are used to train the apprentice, which is a sequence-to-sequence neural network model. The role of the apprentice in the system is to approximate creative autonomy.Evaluation is approached from three different perspectives in this work: ad-hoc and abstract, theory-based and abstract, and theory-based and concrete. The first perspective is the most common one in the current literature and its shortcomings are demonstrated and discussed. This starts a gradual shift towards more meaningful evaluation by first using proper theories to define the task being modelled and finally reducing the room for subjective interpretation by suggesting the use of concrete evaluation questions.

show abstract

Generating Classical Chinese Poems from Vernacular Chinese

Cited by 15 publications

References 16 publications

Learning as Conversation: Dialogue Systems Reinforced for Information Acquisition

Learning as Conversation: Dialogue Systems Reinforced for Information Acquisition

Acrostic Poem Generation

Generating Creative Language - Theories, Practice and Evaluation

Contact Info

Product

Resources

About