Event Transition Planning for Open-ended Text Generation

Li, Qintong; Li, Piji; Bi, Weihong; Zhang, Ren; Lai, Yongqing; Kong, Lingpeng

doi:10.18653/v1/2022.findings-acl.269

Cited by 4 publications

(4 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To handle the task of story ending generation, Huang et al (2021) propose a context-aware multi-level graph convolutional network dependency analysis tree to capture dependencies and context clues more efficiently. Li et al (2022b) propose a novel coarse-grained to fine-grained two-stage approach that more explicitly generates subsequent events in open-ended text generation. Another task related to script events is event process typing which we focus on in this paper, Chen et al (2020) propose a model that utilizes a pretrained language model to encode the entire process and action labels into process feature vectors and action label vectors, respectively, and then predicts the action whose feature vector is closest to the process as the action label of the process.…”

Section: Script Event Learningmentioning

confidence: 99%

Event Process Typing via Hierarchical Optimal Transport

Zhang

Chen

Liu

et al. 2023

AAAI

View full text Add to dashboard Cite

Understanding intention behind event processes in texts is important to many applications. One challenging task in this line is event process typing, which aims to tag the process with one action label and one object label describing the overall action of the process and object the process likely affects respectively. To tackle this task, existing methods mainly rely on the matching of the event process level and label level representation, which ignores two important characteristics: Process Hierarchy and Label Hierarchy. In this paper, we propose a Hierarchical Optimal Transport (HOT) method to address the above problem. Specifically, we first explicitly extract the process hierarchy and label hierarchy. Then the HOT optimally matches the two types of hierarchy. Experimental results show that our model outperforms the baseline models, illustrating the effectiveness of our model.

show abstract

Section: Script Event Learningmentioning

confidence: 99%

Event Process Typing via Hierarchical Optimal Transport

Zhang

Chen

Liu

et al. 2023

AAAI

View full text Add to dashboard Cite

show abstract

“…Early approaches to automatic story generation relied on graph-based planning and hand-crafted rules to structure narratives (Meehan, 1977;Callaway and Lester, 2002;Riedl and Young, 2004;Li et al, 2013). More recent works generate stories by finetuning on large-scale PLMs (See et al, 2019) to improve its fluency and incorporating structured knowledge such as planned events Fang et al, 2021;Li et al, 2022), summaries (Yao et al, 2019Tan et al, 2021;Sun et al, 2020), and external knowledge (Guan et al, 2019;Xu et al, 2020b;Guan et al, 2020) to enhance its coherence and consistency. Our story generation models are also finetuned on the large-scale PLMs to generate text following the given summaries.…”

Section: Related Workmentioning

confidence: 99%

Fiction-Writing Mode: An Effective Control for Human-Machine Collaborative Writing

Zhong,

Naradowsky,

Takamura

et al. 2023

Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics

View full text Add to dashboard Cite

We explore the idea of incorporating concepts from writing skills curricula into humanmachine collaborative writing scenarios, focusing on adding writing modes as a control for text generation models. Using crowd-sourced workers, we annotate a corpus of narrative text paragraphs with writing mode labels. Classifiers trained on this data achieve an average accuracy of ∼ 87% on held-out data. We finetune a set of large language models to condition on writing mode labels, and show that the generated text is recognized as belonging to the specified mode with high accuracy.To study the ability of writing modes to provide fine-grained control over generated text, we devise a novel turn-based text reconstruction game to evaluate the difference between the generated text and the author's intention. We show that authors prefer text suggestions made by writing mode-controlled models on average 61.1% of the time, with satisfaction scores 0.5 higher on a 5-point ordinal scale. When evaluated by humans, stories generated via collaboration with writing mode-controlled models achieve high similarity with the professionally written target story. We conclude by identifying the most common mistakes found in the generated stories. The datasets and codes are available at the Github 1 .

show abstract

“…These unrelated nodes are distracting and can even disturb the subsequent generation. To drop the redundant nodes in the interaction graph, we propose a Graph Pruning (GP) mechanism similar to the Dynamic Graph Pruning (DGP) [39] mechanism. The GP employs the gate mechanism to parse the connection between the schema node s i ∈ S = T ∪ C based on its relevance with the question node in the heterogeneous graph to achieve graph pruning.…”

Section: Graph Pruningmentioning

confidence: 99%

Integrating Relational Structure to Heterogeneous Graph for Chinese NL2SQL Parsers

Zhang

Huang

et al. 2023

Electronics

View full text Add to dashboard Cite

The existing models for NL2SQL tasks are mainly oriented toward English text and cannot solve the problems of column name reuse in Chinese text data, description in natural language query, and inconsistent representation of data stored in the database. To address this problem, this paper proposes a Chinese cross-domain NL2SQL model based on a heterogeneous graph and relative position attention mechanism. This model introduces relational structure information defined by the expert to construct initial heterogeneous graphs for database schemas and natural language questions. The heterogeneous graph is pruned based on natural language questions, and the multi-head relative position attention mechanism is used to encode the database schema and natural language questions. The target SQL statement is generated using a tree-structured decoder with predefined SQL syntax. Experimental results on the CSpider dataset demonstrate that our model better aligns database schema with natural language questions and understands the semantic information in natural language queries, effectively improving the matching accuracy of Chinese multi-table SQL statement generation.

show abstract

Event Transition Planning for Open-ended Text Generation

Cited by 4 publications

References 19 publications

Event Process Typing via Hierarchical Optimal Transport

Event Process Typing via Hierarchical Optimal Transport

Fiction-Writing Mode: An Effective Control for Human-Machine Collaborative Writing

Integrating Relational Structure to Heterogeneous Graph for Chinese NL2SQL Parsers

Contact Info

Product

Resources

About