Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userStyle Control for Schema-Guided Natural Language Generation
التحكم في النمط لتوليد اللغة الطبيعية الموجهة المخطط
489
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تركز توليد اللغة الطبيعية (NLG) لأنظمة الحوار الموجهة نحو المهام على توصيل محتوى معين بدقة، بطلاقة، وتطافق. في حين أن هذه السمات أمر حاسم للحوار الناجح، فمن المستحسن أيضا تحقيق أهداف أسلوبية محددة في وقت واحد، مثل طول الاستجابة، وجهة النظر، وصفي، والشعور، والشكل، والشكل، والتعاطف. في هذا العمل، نركز على التحكم الأسلطي والتقييم ل NLG الموجهة للمخطط، مع أهداف مشتركة لتحقيق السيطرة الدلالية واللحلية. نقوم بتجربة تفصيلية مع مختلف طرق الجيل التي تسيطر عليها نماذج اللغة المحددة مسبقا: على وجه التحديد، والتدريب الشرطي، والضبط الجميل الموجه، والكشف الموجهة. نناقش مزاياها والقيود الخاصة بهم، وتقييمها بمجموعة واسعة من مقاييس التقييم التلقائي والبشري. تظهر نتائجنا أنه في حين أن الدقة عالية النمط والصحة الدلالية أسهل في تحقيق المزيد من الأساليب المعرفة من المعالم مع التدريب الشرطي، فإن التحكم الأسطوري يمكن تحقيقه أيضا على أنماط معقدة أكثر دلالة تستخدم أساليب فك التشفير الموجودة على أساس التمييز. تشير النتائج أيضا إلى أن الطرق التي تعتبر أكثر قابلية للتطوير (مع ضبط المعلمات أقل فرط) وأن توليد سياق Disent Nastange والاختلافات الأسلوبية أكثر فعالية في تحقيق صحة دلالية ودقة أسلوب.
Natural Language Generation (NLG) for task-oriented dialogue systems focuses on communicating specific content accurately, fluently, and coherently. While these attributes are crucial for a successful dialogue, it is also desirable to simultaneously accomplish specific stylistic goals, such as response length, point-of-view, descriptiveness, sentiment, formality, and empathy. In this work, we focus on stylistic control and evaluation for schema-guided NLG, with joint goals of achieving both semantic and stylistic control. We experiment in detail with various controlled generation methods for large pretrained language models: specifically, conditional training, guided fine-tuning, and guided decoding. We discuss their advantages and limitations, and evaluate them with a broad range of automatic and human evaluation metrics. Our results show that while high style accuracy and semantic correctness are easier to achieve for more lexically-defined styles with conditional training, stylistic control is also achievable for more semantically complex styles using discriminator-based guided decoding methods. The results also suggest that methods that are more scalable (with less hyper-parameters tuning) and that disentangle context generation and stylistic variations are more effective at achieving semantic correctness and style accuracy.
References used
https://aclanthology.org/
rate research
Read More
This paper presents an automatic method to evaluate the naturalness of natural language generation in dialogue systems. While this task was previously rendered through expensive and time-consuming human labor, we present this novel task of automatic
naturalness evaluation of generated language. By fine-tuning the BERT model, our proposed naturalness evaluation method shows robust results and outperforms the baselines: support vector machines, bi-directional LSTMs, and BLEURT. In addition, the training speed and evaluation performance of naturalness model are improved by transfer learning from quality and informativeness linguistic knowledge.
In recent years, crowdsourcing has gained much attention from researchers to generate data for the Natural Language Generation (NLG) tools or to evaluate them. However, the quality of crowdsourced data has been questioned repeatedly because of the co
mplexity of NLG tasks and crowd workers' unknown skills. Moreover, crowdsourcing can also be costly and often not feasible for large-scale data generation or evaluation. To overcome these challenges and leverage the complementary strengths of humans and machine tools, we propose a hybrid human-machine workflow designed explicitly for NLG tasks with real-time quality control mechanisms under budget constraints. This hybrid methodology is a powerful tool for achieving high-quality data while preserving efficiency. By combining human and machine intelligence, the proposed workflow decides dynamically on the next step based on the data from previous steps and given constraints. Our goal is to provide not only the theoretical foundations of the hybrid workflow but also to provide its implementation as open-source in future work.
Natural language generation (NLG) tasks on pro-drop languages are known to suffer from zero pronoun (ZP) problems, and the problems remain challenging due to the scarcity of ZP-annotated NLG corpora. In this case, we propose a highly adaptive two-sta
ge approach to couple context modeling with ZP recovering to mitigate the ZP problem in NLG tasks. Notably, we frame the recovery process in a task-supervised fashion where the ZP representation recovering capability is learned during the NLG task learning process, thus our method does not require NLG corpora annotated with ZPs. For system enhancement, we learn an adversarial bot to adjust our model outputs to alleviate the error propagation caused by mis-recovered ZPs. Experiments on three document-level NLG tasks, i.e., machine translation, question answering, and summarization, show that our approach can improve the performance to a great extent, and the improvement on pronoun translation is very impressive.
Developing mechanisms that flexibly adapt dialog systems to unseen tasks and domains is a major challenge in dialog research. Neural models implicitly memorize task-specific dialog policies from the training data. We posit that this implicit memoriza
tion has precluded zero-shot transfer learning. To this end, we leverage the schema-guided paradigm, wherein the task-specific dialog policy is explicitly provided to the model. We introduce the Schema Attention Model (SAM) and improved schema representations for the STAR corpus. SAM obtains significant improvement in zero-shot settings, with a +22 F1 score improvement over prior work. These results validate the feasibility of zero-shot generalizability in dialog. Ablation experiments are also presented to demonstrate the efficacy of SAM.
Knowledge-enriched text generation poses unique challenges in modeling and learning, driving active research in several core directions, ranging from integrated modeling of neural representations and symbolic information in the sequential/hierarchica
l/graphical structures, learning without direct supervisions due to the cost of structured annotation, efficient optimization and inference with massive and global constraints, to language grounding on multiple modalities, and generative reasoning with implicit commonsense knowledge and background knowledge. In this tutorial we will present a roadmap to line up the state-of-the-art methods to tackle these challenges on this cutting-edge problem. We will dive deep into various technical components: how to represent knowledge, how to feed knowledge into a generation model, how to evaluate generation results, and what are the remaining challenges?
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
