نصوص وصفة هي شكل خصوصي للغة التعليمية التي تشكل تحديات فريدة من نوعها للتفاهم التلقائي.أحد التحديات هو أن خطوة الطهي في وصفة واحدة يمكن تفسيرها في وصفة أخرى بكلمات مختلفة، على مستوى مختلف من التجريد، أم لا على الإطلاق.تعلق العمل السابق المراسلات بين إرشادات الوصفة على مستوى الجملة، وغالبا ما تعلق المراسلات المهمة بين خطوات الطبخ عبر الوصفات.نقدم رواية وصفة إنجليزية بالكامل، ARA (إجراءات الوصفة المحاذاة)، والتي تعلق المراسلات بين الإجراءات الفردية عبر وصفات مماثلة بهدف التقاط المعلومات الضمنية لفهم وصفة دقيقة.نحن نمثل هذه المعلومات في شكل رسوم بيانية وصفة، ونحن نربع نموذج عصبي للتنبؤ بالمراسلات على ARA.نجد أن المكاسب الكبيرة في الدقة يمكن الحصول عليها عن طريق أخذ معلومات هيكلية محظورة دقيقة عن الوصفات في الاعتبار.
Recipe texts are an idiosyncratic form of instructional language that pose unique challenges for automatic understanding. One challenge is that a cooking step in one recipe can be explained in another recipe in different words, at a different level of abstraction, or not at all. Previous work has annotated correspondences between recipe instructions at the sentence level, often glossing over important correspondences between cooking steps across recipes. We present a novel and fully-parsed English recipe corpus, ARA (Aligned Recipe Actions), which annotates correspondences between individual actions across similar recipes with the goal of capturing information implicit for accurate recipe understanding. We represent this information in the form of recipe graphs, and we train a neural model for predicting correspondences on ARA. We find that substantial gains in accuracy can be obtained by taking fine-grained structural information about the recipes into account.
References used
https://aclanthology.org/
In order to interpret the communicative intents of an utterance, it needs to be grounded in something that is outside of language; that is, grounded in world modalities. In this paper, we argue that dialogue clarification mechanisms make explicit the
Text generation from semantic graphs is traditionally performed with deterministic methods, which generate a unique description given an input graph. However, the generation problem admits a range of acceptable textual outputs, exhibiting lexical, sy
Knowledge graph entity typing aims to infer entities' missing types in knowledge graphs which is an important but under-explored issue. This paper proposes a novel method for this task by utilizing entities' contextual information. Specifically, we d
Although paths of user interests shift in knowledge graphs (KGs) can benefit conversational recommender systems (CRS), explicit reasoning on KGs has not been well considered in CRS, due to the complex of high-order and incomplete paths. We propose CR
With the recent surge in social applications relying on knowledge graphs, the need for techniques to ensure fairness in KG based methods is becoming increasingly evident. Previous works have demonstrated that KGs are prone to various social biases, a