Early work on narrative modeling used explicit plans and goals to generate stories, but the language generation itself was restricted and inflexible. Modern methods use language models for more robust generation, but often lack an explicit representation of the scaffolding and dynamics that guide a coherent narrative. This paper introduces a new model that integrates explicit narrative structure with neural language models, formalizing narrative modeling as a Switching Linear Dynamical System (SLDS). A SLDS is a dynamical system in which the latent dynamics of the system (i.e. how the state vector transforms over time) is controlled by top-level discrete switching variables. The switching variables represent narrative structure (e.g., sentiment or discourse states), while the latent state vector encodes information on the current state of the narrative. This probabilistic formulation allows us to control generation, and can be learned in a semi-supervised fashion using both labeled and unlabeled data. Additionally, we derive a Gibbs sampler for our model that can fill in arbitrary parts of the narrative, guided by the switching variables. Our filled-in (English language) narratives outperform several baselines on both automatic and human evaluations.
CSWBench: Evaluating Context-Sensitive Code-Switching in Creative Writing
School of Artificial Intelligence, Jilin University（吉林大学人工智能学院）；College of Software, Jilin University（吉林大学软件学院）；Xingchen AGI Lab, China Telecom Artificial Intelligence Technology (Beijing) Co., Ltd.（中国电信人工智能技术（北京）有限公司星辰AGI实验室）；Bilibili Inc.（哔哩哔哩公司）；University of Ottawa（渥太华大学）；International Center of Future Science, Jilin University（吉林大学未来科学国际中心）
Research Training Group AIPHES（AIPHES研究培训小组）；Heidelberg University（海德堡大学）
Despite recent successes of large pre-trained language models in solving reasoning tasks, their inference capabilities remain opaque. We posit that such models can be made more interpretable by explicitly generating interim inference rules, and using them to guide the generation of task-specific textual outputs. In this paper we present COINS, a recursive inference framework that i) iteratively reads context sentences, ii) dynamically generates contextualized inference rules, encodes them, and iii) uses them to guide task-specific output generation. We apply COINS to a Narrative Story Completi…
Tsinghua University（清华大学）；Guangdong OPPO Mobile Telecommunications Corp., Ltd.（广东OPPO移动通信有限公司）；NetEase Inc.（网易公司）
Despite advances in generating fluent texts, existing pretraining models tend to attach incoherent event sequences to involved entities when generating narratives such as stories and news. We conjecture that such issues result from representing entities as static embeddings of superficial words, while neglecting to model their ever-changing states, i.e., the information they carry, as the text unfolds. Therefore, we extend the Transformer model to dynamically conduct entity state updates and sentence realization for narrative generation. We propose a contrastive framework to learn the state re…
We propose a method for controlled narrative/story generation where we are able to guide the model to produce coherent narratives with user-specified target endings by interpolation: for example, we are told that Jim went hiking and at the end Jim needed to be rescued, and we want the model to incrementally generate steps along the way. The core of our method is an interpolation model based on GPT-2 which conditions on a previous sentence and a next sentence in a narrative and fills in the gap. Additionally, a reranker helps control for coherence of the generated text. With human evaluation, w…
Northeastern University（东北大学）；King’s College London（伦敦国王学院）
We consider the problem of automatically generating a narrative biomedical evidence summary from multiple trial reports. We evaluate modern neural models for abstractive summarization of relevant article abstracts from systematic reviews previously conducted by members of the Cochrane collaboration, using the authors conclusions section of the review abstract as our target. We enlist medical professionals to evaluate generated summaries, and we find that modern summarization systems yield consistently fluent and relevant synopses, but that they are not always factual. We propose new approaches…
Generating long form narratives such as stories and procedures from multiple modalities has been a long standing dream for artificial intelligence. In this regard, there is often crucial subtext that is derived from the surrounding contexts. The general seq2seq training methods render the models shorthanded while attempting to bridge the gap between these neighbouring contexts. In this paper, we tackle this problem by using \textit{infilling} techniques involving prediction of missing steps in a narrative while generating textual descriptions from a sequence of images. We also present a new la…
Ohio University（俄亥俄大学）；University of North Carolina at Charlotte（北卡罗来纳大学夏洛特分校）
We introduce the task of changing the narrative point of view, where characters are assigned a narrative perspective that is different from the one originally used by the writer. The resulting shift in the narrative point of view alters the reading experience and can be used as a tool in fiction writing or to generate types of text ranging from educational to self-help and self-diagnosis. We introduce a benchmark dataset containing a wide range of types of narratives annotated with changes in point of view from deictic (first or second person) to anaphoric (third person) and describe a pipelin…
GPT-4 Generated Narratives of Life Events using a Structured Narrative Prompt: A Validation Study
Virginia Modeling, Analysis, and Simulation Center（弗吉尼亚建模、分析与仿真中心）；Old Dominion University（奥多明尼昂大学）；College of Engineering, Montana State University（蒙大拿州立大学工程学院）
From Model to Classroom: Evaluating Generated MCQs for Portuguese with Narrative and Difficulty Concerns
Faculdade de Engenharia, Universidade do Porto（工程学院，葡萄牙波尔图大学）；Departamento de Investigação e Tecnologia（研究与技术部门）；Divisão de Tecnologias Educativas（教育技术部门）；Escola Básica Mirante dos Sonhos（梦想之镜初级学校）
University of Washington（华盛顿大学）；Microsoft Research（微软研究院）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）
We propose the task of outline-conditioned story generation: given an outline as a set of phrases that describe key characters and events to appear in a story, the task is to generate a coherent narrative that is consistent with the provided outline. This task is challenging as the input only provides a rough sketch of the plot, and thus, models need to generate a story by interweaving the key points provided in the outline. This requires the model to keep track of the dynamic states of the latent plot, conditioning on the input outline while generating the full story. We present PlotMachines,…
University of Southern California（南加州大学）；Tokyo University（东京大学）；University of California, Los Angeles（加州大学洛杉矶分校）
Stories or narratives are comprised of a sequence of events. To compose interesting stories, professional writers often leverage a creative writing technique called flashback that inserts past events into current storylines as we commonly observe in novels and plays. However, it is challenging for machines to generate flashback as it requires a solid understanding of event temporal order (e.g. "feeling hungry" before "eat," not vice versa), and the creativity to arrange storylines so that earlier events do not always appear first in narrative order. Two major issues in existing systems that ex…
"Once Upon a Time..." Literary Narrative Connectedness Progresses with Grade Level: Potential Impact on Reading Fluency and Literacy Skills
Mobile Brain（移动脑机构）；Bioinformatics Multidisciplinary Environment (BioME), Federal University of Rio Grande do Norte (UFRN)（巴西北里奥格兰德联邦大学生物信息学多学科环境）；Árvore（阿沃雷机构）；Institute of Psychiatry (IPUB), Federal University of Rio de Janeiro (UFRJ)（里约热内卢联邦大学精神病学研究所）
Affective and Dynamic Beam Search for Story Generation
University of Southern California（南加州大学）；Columbia University（哥伦比亚大学）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）；University of California, Davis（加州大学戴维斯分校）；University of North Carolina（北卡罗来纳大学）
Named entity recognition (NER) is an important task in narration extraction. Narration, as a system of stories, provides insights into how events and characters in the stories develop over time. This paper proposes an architecture for NER on a corpus about social purpose organizations. This is the first NER task specifically targeted at social service entities. We show how this approach can be used for the sequencing of services and impacted clients with information extracted from unstructured text. The methodology outlines steps for extracting ontological representation of entities such as ne…
Reframe Your Life Story: Interactive Narrative Therapist and Innovative Moment Assessment with Large Language Models
Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence（北京交通大数据挖掘与具身智能重点实验室）；Beijing Jiaotong University（北京交通大学）；CoAI Group（CoAI集团）；DCST（国防科技大学）；IAI（人工智能院）；BNRIST（北航机器人与智能技术研究院）；Tsinghua University（清华大学）；Tencent Jarvis Lab（腾讯Jarvis实验室）；Singapore University of Technology and Design（新加坡科技与设计大学）；Central South University（中南大学）；Lingxin AI（灵犀AI）
Generating code-switched text is a problem of growing interest, especially given the scarcity of corpora containing large volumes of real code-switched text. In this work, we adapt a state-of-the-art neural machine translation model to generate Hindi-English code-switched sentences starting from monolingual Hindi sentences. We outline a carefully designed curriculum of pretraining steps, including the use of synthetic code-switched text, that enable the model to generate high-quality code-switched text. Using text generated from our model as data augmentation, we show significant reductions in…
Large pre-trained language models (LMs) have demonstrated impressive capabilities in generating long, fluent text; however, there is little to no analysis on their ability to maintain entity coherence and consistency. In this work, we focus on the end task of narrative generation and systematically analyse the long-range entity coherence and consistency in generated stories. First, we propose a set of automatic metrics for measuring model performance in terms of entity usage. Given these metrics, we quantify the limitations of current LMs. Next, we propose augmenting a pre-trained LM with a dy…
Institute for Natural Language Processing (IMS), University of Stuttgart（斯图加特大学自然语言处理研究所（IMS））
This paper presents our latest effort on improving Code-switching language models that suffer from data scarcity. We investigate methods to augment Code-switching training text data by artificially generating them. Concretely, we propose a cycle-consistent adversarial networks based framework to transfer monolingual text into Code-switching text, considering Code-switching as a speaking style. Our experimental results on the SEAME corpus show that utilising artificially generated Code-switching text data improves consistently the language model as well as the automatic speech recognition perfo…
Large pre-trained language models are capable of generating varied and fluent texts. Starting from the prompt, these models generate a narrative that can develop unpredictably. The existing methods of controllable text generation, which guide the narrative in the text in the user-specified direction, require creating a training corpus and an additional time-consuming training procedure. The paper proposes and investigates Collocation2Text, a plug-and-play method for automatic controllable text generation in Russian, which does not require fine-tuning. The method is based on two interacting mod…
Fondazione Bruno Kessler（布鲁诺·凯斯勒基金会）；University of Trento（特伦托大学）；University of Stuttgart（斯图加特大学）
In this work, we present an extensive study on the use of pre-trained language models for the task of automatic Counter Narrative (CN) generation to fight online hate speech in English. We first present a comparative study to determine whether there is a particular Language Model (or class of LMs) and a particular decoding mechanism that are the most appropriate to generate CNs. Findings show that autoregressive models combined with stochastic decodings are the most promising. We then investigate how an LM performs in generating a CN with regard to an unseen target of hate. We find out that a …
