Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userDiversity as a By-Product: Goal-oriented Language Generation Leads to Linguistic Variation
التنوع كمنتج ثانوي: توليد اللغة الموجهة نحو الأهداف يؤدي إلى التباين اللغوي
383
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
إن القدرة على التباين في استخدام اللغة ضروري للمتحدثين لتحقيق أهدافهم المحادثة، على سبيل المثال عند الإشارة إلى الكائنات في البيئات المرئية.نقول أن التنوع لا ينبغي أن يكون على غرار كهدف مستقل في الحوار، ولكن يجب أن يكون نتيجة لذلك أو منتج ثاني لتوليد اللغة الموجهة نحو الأهداف.تم التحقيق في خطوط عمل مختلفة في توليد اللغة العصبية طرق فك تشفيرها لتوليد المزيد من الكلمات المتنوعة، أو زيادة المعلوماتية من خلال التفكير العملي.نربط تلك خطوط العمل وتحليل كيفية تأثير المنطق العملي أثناء فك التشفير على تنوع التسميات التوضيحية الناتجة عنها.نجد أن تعزيز التنوع نفسه لا يؤدي إلى تسهيلات مفيدة بشكل أكثر عمليا، لكن المنطق العملي يزيد من التنوع المعجمي.أخيرا، نناقش ما إذا كان الاستفادة من المعلوماتية بطرق غير معقولة بمرحلة ما بين اللغوي.
The ability for variation in language use is necessary for speakers to achieve their conversational goals, for instance when referring to objects in visual environments. We argue that diversity should not be modelled as an independent objective in dialogue, but should rather be a result or by-product of goal-oriented language generation. Different lines of work in neural language generation investigated decoding methods for generating more diverse utterances, or increasing the informativity through pragmatic reasoning. We connect those lines of work and analyze how pragmatic reasoning during decoding affects the diversity of generated image captions. We find that boosting diversity itself does not result in more pragmatically informative captions, but pragmatic reasoning does increase lexical diversity. Finally, we discuss whether the gain in informativity is achieved in linguistically plausible ways.
References used
https://aclanthology.org/
rate research
Read More
The knowledge of scripts, common chains of events in stereotypical scenarios, is a valuable asset for task-oriented natural language understanding systems. We propose the Goal-Oriented Script Construction task, where a model produces a sequence of st
eps to accomplish a given goal. We pilot our task on the first multilingual script learning dataset supporting 18 languages collected from wikiHow, a website containing half a million how-to articles. For baselines, we consider both a generation-based approach using a language model and a retrieval-based approach by first retrieving the relevant steps from a large candidate pool and then ordering them. We show that our task is practical, feasible but challenging for state-of-the-art Transformer models, and that our methods can be readily deployed for various other datasets and domains with decent zero-shot performance.
In goal-oriented dialogue systems, users provide information through slot values to achieve specific goals. Practically, some combinations of slot values can be invalid according to external knowledge. For example, a combination of cheese pizza'' (a
menu item) and oreo cookies'' (a topping) from an input utterance Can I order a cheese pizza with oreo cookies on top?'' exemplifies such invalid combinations according to the menu of a restaurant business. Traditional dialogue systems allow execution of validation rules as a post-processing step after slots have been filled which can lead to error accumulation. In this paper, we formalize knowledge-driven slot constraints and present a new task of constraint violation detection accompanied with benchmarking data. Then, we propose methods to integrate the external knowledge into the system and model constraint violation detection as an end-to-end classification task and compare it to the traditional rule-based pipeline approach. Experiments on two domains of the MultiDoGO dataset reveal challenges of constraint violation detection and sets the stage for future work and improvements.
With the increasing use of machine-learning driven algorithmic judgements, it is critical to develop models that are robust to evolving or manipulated inputs. We propose an extensive analysis of model robustness against linguistic variation in the se
tting of deceptive news detection, an important task in the context of misinformation spread online. We consider two prediction tasks and compare three state-of-the-art embeddings to highlight consistent trends in model performance, high confidence misclassifications, and high impact failures. By measuring the effectiveness of adversarial defense strategies and evaluating model susceptibility to adversarial attacks using character- and word-perturbed text, we find that character or mixed ensemble models are the most effective defenses and that character perturbation-based attack tactics are more successful.
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.
For each goal-oriented dialog task of interest, large amounts of data need to be collected for end-to-end learning of a neural dialog system. Collecting that data is a costly and time-consuming process. Instead, we show that we can use only a small a
mount of data, supplemented with data from a related dialog task. Naively learning from related data fails to improve performance as the related data can be inconsistent with the target task. We describe a meta-learning based method that selectively learns from the related dialog task data. Our approach leads to significant accuracy improvements in an example dialog task.
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
