Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userTowards Hybrid Human-Machine Workflow for Natural Language Generation
نحو سير عمل الجهاز البشري الهجين لتوليد اللغة الطبيعية
273
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
في السنوات الأخيرة، اكتسب التعهيد الجماعي الكثير من الاهتمام من الباحثين لإنشاء بيانات لأدوات جيل اللغة الطبيعية (NLG) أو تقييمها. ومع ذلك، تم استجواب جودة بيانات الجماعة الجماعية مرارا وتكرارا بسبب تعقيد مهارات NLG ومهارات العمال في الحشد. علاوة على ذلك، يمكن أن يكون التعهيد الجماعي أيضا مكلفا وغالبا ما لا يكون ممكنا لتوليد البيانات أو التقييم على نطاق واسع. للتغلب على هذه التحديات والاستفادة من نقاط القوة التكميلية للبشر والأدوات الآلية، نقترح سير عمل هجين - آلة الإنسان المصممة بشكل صريح لمهام NLG مع آليات مراقبة الجودة في الوقت الفعلي تحت قيود الميزانية. هذه المنهجية الهجينة هي أداة قوية لتحقيق بيانات عالية الجودة مع الحفاظ على الكفاءة. من خلال الجمع بين الذكاء البشري والآلات، تقرر سير العمل المقترح ديناميكيا في الخطوة التالية بناء على البيانات من الخطوات السابقة والمعطلات. هدفنا هو تقديم ليس فقط الأسس النظرية لسير العمل الهجين ولكن أيضا لتوفير تنفيذها كمصدر مفتوح في العمل في المستقبل.
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 complexity 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.
References used
https://aclanthology.org/
rate research
Read More
We ask subjects whether they perceive as human-produced a bunch of texts, some of which are actually human-written, while others are automatically generated. We use this data to fine-tune a GPT-2 model to push it to generate more human-like texts, an
d observe that this fine-tuned model produces texts that are indeed perceived more human-like than the original model. Contextually, we show that our automatic evaluation strategy well correlates with human judgements. We also run a linguistic analysis to unveil the characteristics of human- vs machine-perceived language.
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.
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 this paper, we propose a definition and taxonomy of various types of non-standard textual content -- generally referred to as noise'' -- in Natural Language Processing (NLP). While data pre-processing is undoubtedly important in NLP, especially wh
en dealing with user-generated content, a broader understanding of different sources of noise and how to deal with them is an aspect that has been largely neglected. We provide a comprehensive list of potential sources of noise, categorise and describe them, and show the impact of a subset of standard pre-processing strategies on different tasks. Our main goal is to raise awareness of non-standard content -- which should not always be considered as noise'' -- and of the need for careful, task-dependent pre-processing. This is an alternative to blanket, all-encompassing solutions generally applied by researchers through standard'' pre-processing pipelines. The intention is for this categorisation to serve as a point of reference to support NLP researchers in devising strategies to clean, normalise or embrace non-standard content.
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.
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
