Natural Language Generation and Creative Writing A Systematic Review

Natural Language Understanding (NLU) and Natural Language Generation (NLG) are the general methods that support machine understanding of text content. They play a very important role in the text information processing system including recommendation and question and answer systems. There are many researches in the field of NLU such as Bag of words, N-Gram, and neural network language model. These models have achieved a good performance in NLU and NLG tasks. However, since they require lots of training data, it is difficult to obtain rich data in practical applications. Thus, pretraining becomes important. This paper proposes a semisupervised way to deal with math word problem (MWP) tasks using unsupervised pretraining and supervised tuning methods, which are based on the Unified pretrained Language Model (UniLM). The proposed model requires fewer training data than traditional models since it uses model parameters of tasks that have been learned before to initialize the model parameters of new tasks. In this way, old knowledge helps new models successfully perform new tasks from old experiences instead of from scratch. Moreover, in order to help the decoder make accurate predictions, we combine the advantages of AR and AE language models to support one-way, sequence-to-sequence, and two-way predictions. Experiments, carried out on MWP tasks with 20,000+ mathematical questions, show that the improved model outperforms the traditional models with a maximum accuracy of 79.57%. The impact of different experiment parameters is also studied in the paper and we found that a wrong arithmetic order leads to incorrect solution expression generation.

Natural language generation (NLG) spans a broad range of tasks, each of which serves for specific objectives and desires different properties of generated text. The complexity makes automatic evaluation of NLG particularly challenging. Previous work has typically focused on a single task and developed individual evaluation metrics based on specific intuitions. In this paper, we propose a unifying perspective based on the nature of information change in NLG tasks, including compression (e.g., summarization), transduction (e.g., text rewriting), and creation (e.g., dialog). Information alignment between input, context, and output text plays a common central role in characterizing the generation. With automatic alignment prediction models, we develop a family of interpretable metrics that are suitable for evaluating key aspects of different NLG tasks, often without need of gold reference data. Experiments show the uniformly designed metrics achieve stronger or comparable correlations with human judgement compared to state-of-the-art metrics in each of diverse tasks, including text summarization, style transfer, and knowledge-grounded dialog.

In natural language generation tasks, a neural language model is used for generating a sequence of words forming a sentence. The topmost weight matrix of the language model, known as the classification layer, can be viewed as a set of vectors, each representing a target word from the target dictionary. The target word vectors, along with the rest of the model parameters, are learned and updated during training. In this paper, we analyze the properties encoded in the target vectors and question the necessity of learning these vectors. We suggest to randomly draw the target vectors and set them as fixed so that no weights updates are being made during training. We show that by excluding the vectors from the optimization, the number of parameters drastically decreases with a marginal effect on the performance. We demonstrate the effectiveness of our method in image-captioning and machine-translation.

This paper addresses the problem of automatic generation of natural language descriptions for ontology-described artifacts. The original motivation for the work is the challenge of providing textual narratives of automatically generated scientific workflows (e.g., paragraphs that scientists can include in their publications). The paper presents two systems which generate descriptions of sets of atoms derived from a collection of ontologies. The first system, called nlgPhylogeny, demonstrates the feasibility of the task in the Phylotastic project, providing evolutionary biologists with narrative for automatically generated analysis workflows. nlgPhylogeny utilizes the fact that the Grammatical Framework (GF) is suitable for the natural language generation (NLG) task; the paper shows how elements of the ontologies in Phylotastic, such as web services and information artifacts, can be encoded in GF for the NLG task. The second system, called \(\mathtt{\small nlgOntology}^{A}\), is a generalization of nlgPhylogeny. It eliminates the requirement that a GF needs to be defined and proposes the use of annotated ontologies for NLG. Given a set of annotated ontologies, \(\mathtt{\small nlgOntology}^{A}\) generates a GF suitable for the creation of natural language descriptions of sets of atoms derived from these ontologies. The paper describes the algorithms used in the development of nlgPhylogeny and \(\mathtt{\small nlgOntology}^{A}\) and discusses potential applications of these systems.

Transformer-based language models are able to generate fluent text and be efficiently adapted across various natural language generation tasks. However, language models that are pretrained on large unlabeled web text corpora have been shown to suffer from degenerating toxic content and social bias behaviors, consequently hindering their safe deployment. Various detoxification methods were proposed to mitigate the language model's toxicity; however, these methods struggled to detoxify language models when conditioned on prompts that contain specific social identities related to gender, race, or religion. In this study, we propose Reinforce-Detoxify; A reinforcement learning-based method for mitigating toxicity in language models. We address the challenge of safety in language models and propose a new reward model that is able to detect toxic content and mitigate unintended bias towards social identities in toxicity prediction. The experiments demonstrate that the Reinforce-Detoxify method for language model detoxification outperforms existing detoxification approaches in automatic evaluation metrics, indicating the ability of our approach in language model detoxification and less prone to unintended bias toward social identities in generated content.

Existing data-driven methods can well handle short text generation. However, when applied to the long-text generation scenarios such as story generation or advertising text generation in the commercial scenario, these methods may generate illogical and uncontrollable texts. To address these aforementioned issues, we propose a graph-based grouping planner~(GGP) following the idea of first-plan-then-generate. Specifically, given a collection of key phrases, GGP firstly encodes these phrases into a instance-level sequential representation and a corpus-level graph-based representation separately. With these two synergic representations, we then regroup these phrases into a fine-grained plan, based on which we generate the final long text. We conduct our experiments on three long text generation datasets and the experimental results reveal that GGP significantly outperforms baselines, which proves that GGP can control the long text generation with knowing how to say and in what order.

The task of natural language generation by computer requires a method for the selection of lexical items that refer to concepts. A generation system cannot assume that every concept will have an appropriate lexical entry associated with it. Similarly, a generation system must avoid redundant text and must strive for the most specific descriptions possible. This paper presents an algorithm for lexical selection that takes advantage of a conceptual network in which we represent the relationships between concepts (such as which concepts subsume each other and what differentiates concepts at different levels of generality). When the algorithm chooses a lexical realization for a concept, it first checks to see if the concept to be expressed is associated with a lexical entry. If so, that entry is used. If the concept does not have the appropriate lexical associations, the algorithm generates a phrase with a more general head term and restrictive modifiers. It does this by using the conceptual network to compute a semantically appropriate head term, and then modifying the request for generation by adding restrictions that differentiate the concept associated with the head term from the concept initially requested. Similarly, the conceptual network is used to eliminate redundant modifiers by computing the information contained in a lexical item that is chosen as a head term. Here the algorithm modifies the generation request to avoid restating the extra information. This algorithm is being implemented within Penman, a computerized system for the generation of English text from statements in a first-order predicate calculus language.

Despite the recent advancement in NLP research, cross-lingual transfer for natural language generation is relatively understudied. In this work, we transfer supervision from high resource language (HRL) to multiple low-resource languages (LRLs) for natural language generation (NLG). We consider four NLG tasks (text summarization, question generation, news headline generation, and distractor generation) and three syntactically diverse languages, i.e., English, Hindi, and Japanese. We propose an unsupervised cross-lingual language generation framework (called ZmBART) that does not use any parallel or pseudo-parallel/back-translated data. In this framework, we further pre-train mBART sequence-to-sequence denoising auto-encoder model with an auxiliary task using monolingual data of three languages. The objective function of the auxiliary task is close to the target tasks which enriches the multi-lingual latent representation of mBART and provides good initialization for target tasks. Then, this model is fine-tuned with task-specific supervised English data and directly evaluated with low-resource languages in the Zero-shot setting. To overcome catastrophic forgetting and spurious correlation issues, we applied freezing model component and data argumentation approaches respectively. This simple modeling approach gave us promising results.We experimented with few-shot training (with 1000 supervised data points) which boosted the model performance further. We performed several ablations and cross-lingual transferability analyses to demonstrate the robustness of ZmBART.

Evaluating Natural Language Generation (NLG) systems is a challenging task. Firstly, the metric should ensure that the generated hypothesis reflects the reference's semantics. Secondly, it should consider the grammatical quality of the generated sentence. Thirdly, it should be robust enough to handle various surface forms of the generated sentence. Thus, an effective evaluation metric has to be multifaceted. In this paper, we propose an automatic evaluation metric incorporating several core aspects of natural language understanding (language competence, syntactic and semantic variation). Our proposed metric, RoMe, is trained on language features such as semantic similarity combined with tree edit distance and grammatical acceptability, using a self-supervised neural network to assess the overall quality of the generated sentence. Moreover, we perform an extensive robustness analysis of the state-of-the-art methods and RoMe. Empirical results suggest that RoMe has a stronger correlation to human judgment over state-of-the-art metrics in evaluating system-generated sentences across several NLG tasks.

Information extraction (IE) aims to automatically identify and extract information about specific interests from raw texts. Despite the abundance of solutions based on fine-tuning pretrained language models, IE in the context of few-shot and zero-shot scenarios remains highly challenging due to the scarcity of training data. Large language models (LLMs), on the other hand, can generalize well to unseen tasks with few-shot demonstrations or even zero-shot instructions and have demonstrated impressive ability for a wide range of natural language understanding or generation tasks. Nevertheless, it is unclear, whether such effectiveness can be replicated in the task of IE, where the target tasks involve specialized schema and quite abstractive entity or relation concepts. In this paper, we first examine the validity of LLMs in executing IE tasks with an established prompting strategy and further propose multiple types of augmented prompting methods, including the structured fundamental prompt (SFP), the structured interactive reasoning prompt (SIRP), and the voting-enabled structured interactive reasoning prompt (VESIRP). The experimental results demonstrate that while directly promotes inferior performance, the proposed augmented prompt methods significantly improve the extraction accuracy, achieving comparable or even better performance (e.g., zero-shot FewNERD, FewNERD-INTRA) than state-of-the-art methods that require large-scale training samples. This study represents a systematic exploration of employing instruction-following LLM for the task of IE. It not only establishes a performance benchmark for this novel paradigm but, more importantly, validates a practical technical pathway through the proposed prompt enhancement method, offering a viable solution for efficient IE in low-resource settings.

With the rapid development of large language models (LLMs) in natural language processing and generation tasks, researchers are continuously validating their application potential in the field of medical artificial intelligence (AI). Generative Pre-trained Transformer 5 (GPT-5), Pathways Language Model 2 (PaLM-2), Large Language Model Meta AI 3 (Llama-3), Gemini-2.5, and various medical vertical models have demonstrated excellent performance in many medical and health-related tasks. However, LLMs still face key bottlenecks in real-world medical scenarios, including “illusions” slow knowledge updates, and a lack of interpretability. These problems severely restrict the safe deployment of large language models in high-risk medical scenarios and have become a major obstacle to the transition of medical artificial intelligence from research to clinical application. Retrieval-augmented generation (RAG) technology has therefore become an important solution for improving the credibility of medical LLMs. RAG significantly reduces the risk of information errors by retrieving authoritative medical knowledge before generation while maintaining knowledge updates without retraining. A review of research progress on RAG in the medical field is of great theoretical value and practical significance for promoting the design, evaluation, and standardized application of trustworthy medical AI. This review aims to systematically summarize the research progress of RAG in medical scenarios, including the technical frameworks, typical applications, and development trends of three types of methods—naive RAG, advanced RAG, and modular RAG—and further discuss their significance in medical reliability, health equity, and personalized medicine. The naive RAG architecture, through a standard “index-retrieval-generation” process, transforms external knowledge bases into a structured vector space that can be queried by an LLM, achieving positive results in electronic medical record (EMR) summary, preoperative assessment, and medical question answering (QA). However, naive RAG still has limitations in retrieval accuracy and cross-modal processing. To address these shortcomings, advanced RAG methods have been devised that significantly improve the model’s decision-making capabilities by improving retrieval strategies, enhancing inference chains, and introducing self-reflection mechanisms. Furthermore, modular RAG design offers composable, multi-module systems to support multi-source knowledge integration and complex task decomposition. In terms of application value, RAG’s contributions to the healthcare field are primarily reflected in these aspects. On the one hand, it significantly improves the reliability of medical AI by introducing traceable knowledge to reduce illusions. On the other hand, it helps promote healthcare equity by driving a shift toward a patient-centered healthcare model through localized knowledge bases and multilingual support. However, the deployment of RAG in medical scenarios still faces many challenges, such as data privacy risks. Future research should focus on improving self-supervised reflection capabilities and developing cross-modal knowledge fusion technologies. As research develops, RAG is expected to become a core foundational capability of future intelligent healthcare systems, further promoting the development of safe and efficient intelligent healthcare.

Sentiment analysis is a field of computational linguistics involving identification, extraction, and classification of opinions, sentiments, and emotions expressed in natural language. Sentiment classification algorithms aim to identify whether the author of a text has a positive or a negative opinion about a topic. One of the main indicators which help to detect the opinion are the words used in the texts. Needless to say, the sentiments expressed in the texts also depend on the syntactic structure and the discourse context. Supervised machine learning approaches to sentiment classification were shown to achieve good results. Classifying texts by emotions requires finer-grained analysis than sentiment classification. In this thesis, we explore the task of emotion and mood classification for blog postings. We propose a novel approach that uses the hierarchy of possible moods to achieve better results than a standard flat classification approach. We also show that using sentiment orientation features improves the performance of classification. We used the LiveJournal blog corpus as a dataset to train and evaluate our method. Another contribution of this work is extracting paraphrases for emotion terms based on the six basics emotions proposed by Ekman (happiness, anger, sadness, disgust, surprise, fear). Paraphrases are different ways to express the same information. Algorithms to extract and automatically identify paraphrases are of interest from both linguistic and practical points of view. Our paraphrase extraction method is based on a bootstrapping algorithms that starts with seed words. Unlike in previous work, our algorithm does not need a parallel corpus. In Natural Language Generation (NLG), paraphrasing is employed to create more varied and natural text. In our research, we extract paraphrases for emotions, with the goal of using them to automatically generate emotional texts (such as friendly or hostile texts) for conversations between intelligent agents and characters in educational games. Nowadays, online services are popular in many disciplines such as: e-learning, interactive games, educational games, stock market, chat rooms and so on. NLG methods can be used in order to generate more interesting and normal texts for such applications. Generating text with emotions is one of the contributions of our work. In the last part of this thesis, we give an overview of NLG from an applied system's points of view. We discuss when NLG techniques can be used; we explained the requirements analysis and specification of NLG systems. We also, describe the main NLG tasks of content determination, discourse planning, sentence aggregation, lexicalization, referring expression generation, and linguistic realisation. Moreover, we describe our Authoring Tool that we developed in order to allow writers without programming skills to automatically generate texts for educational games. We develop an NLG system that can generate text with different emotions. To do this, we introduce our pattern-based model for generation. We show our model starts with initial patterns, then constructs extended patterns from which we choose final'' patterns that are suitable for generating emotion sentences. A user can generate sentences to express the desired emotions by using our patterns. Alternatively, the user can use our Authoring Tool to generate sentences with emotions. Our acquired paraphrases will be employed by the tool in order to generate more varied outputs.

Large language models (LLMs), consisting of billions and trillions of parameters, have demonstrated exceptional ability in natural language understanding (NLU) and natural language generation (NLG) tasks. Increases in their numbers of parameters and model sizes have resulted in better performance and accuracy. However, models with such enormous numbers of parameters incur significant computational costs and resources, making them challenging to fine tune and adapt to a specific downstream task. Several parameter-efficient fine-tuning (PEFT) techniques have been proposed to address this issue. This study demonstrates the improvement obtained over the base LLaMA3-8B model using two prominent PEFT techniques: LoRA and QLoRA. We use the sequence classification task of sentiment analysis to conduct the experiments. Additionally, we analyze the effects of hyperparameter adjustments (r and α) on the model’s performance. We examine the tradeoff between efficiency and memory savings obtained using the quantized LoRA (QLoRA) technique. We also investigate and compare the performance changes of LoRA and QLoRA techniques obtained after adapting to attention layers (query, key, value, and project) to all the linear layers during fine tuning. We report the findings of our work along with limitations and future directions.

Storytelling is a pervasive part of our daily lives and culture. The task of creating stories for the purposes of entertaining, educating, and training has traditionally been the purview of humans. This sets up the conditions for a creative authoring bottleneck where the consumption of stories outpaces the production of stories by human professional creators. The automation of story creation may scale up the ability to produce and deliver novel, meaningful story artifacts. From this practical perspective, story generation systems replicate the creative abilities of humans and can thus be considered instances of computational creativity. Computational systems that are purported to be creative typically utilize one of three general approaches: exploration of a space of concepts, combination of concepts, and transformation of concepts. In this article we present an approach to story generation that utilize exploration, combination, and transformation. Our approach, implemented in the Vignette Based Partial Order Causal Link story planner, is an algorithm that searches through a space of possible story solutions, guided by combinations of existing story fragments called vignettes. The vignettes are made relevant to novel story generation contexts through an automated transformation pre-process. Through these processes, we show that story generation can incorporate multiple perspectives on computational creativity. Our approach is presented at both the theoretical and technical levels.

Statistical language models improve the performance of speech recognition systems by providing estimates of a priori probabilities of word sequences. The commonly used trigram language models obtain the conditional probability estimate of a word given the previous two words, from a large corpus of text. The text corpus is often a collection of several small diverse segments such as newspaper articles, or conversations on different topics. Knowledge of the current topic could be utilized to adapt the general trigram language models to match that topic closely. For example, an interpolation of the general language model with one built on the topic data could be used. The authors first discuss the adaptation of general trigram language models to a known topic using the minimum discrimination information (MDI) method. They then present results on the switchboard corpus which consists of telephone conversations on several topics.