Sensory Descriptor Analysis of Whisky Lexicons through the Use of Deep Learning (original) (raw)

Generating flavors using Scientific Machine Learning

The flavor is an essential component in developing numerous products in the market. The increasing consumption of processed and fast food and healthy packages has upraised the investment in new flavoring agents and, consequently, molecules with flavoring properties. In this context, this work brings a Scientific Machine Learning approach to address this product engineering need. Scientific Machine Learning in computational chemistry has opened paths in predicting a compound's properties without requiring synthesis. This work proposes a novel framework of deep generative models within this context to design new flavor molecules.

A New Annotation Scheme for the Semantics of Taste

2024

FrameNet serves as a comprehensive lexical database intended to represent contemporary language usage. However, it faces challenges in accurately representing specialized domains. Among these domains, FrameNet presents difficulties in capturing the specific semantics of human senses. Senses such as smell and taste are in fact included in more general frames or inadequately represented. Building on a previous resource proposing a new framework for olfactory events, we propose a similar annotation scheme for gustatory references in English, enlightening the potential of frames to effectively capture sensory semantics. Having a comprehensive framework to deal with the annotation of this kind of references in textual data is especially important to develop systems for the automatic extraction of sensory information. Moreover, our approach incorporates words from specific historical periods, thereby enriching the framework's utility for studying language in a diachronic perspective. In this paper, we introduce the annotation guidelines for taste and a preliminary annotation of culinary documents done using this approach.

A descriptive algorithm for a wine tasting lexicon corpus

Scire: representación y organización del conocimiento, 2009

Se pretende mostrar los avances en las pruebas de validez de un procedimiento de identificación computacional de los componentes que constituyen el significado de las expresiones en el restringido subdominio de las notas de cata de los vinos. El procedimiento consiste en un algoritmo de enlace que incluye un conjunto de componentes etiquetados. Dichos componentes van desde los no lingüísticos, con etiquetas para la “entrada perceptiva” y el “conocimiento del mundo”, hasta los propiamente lingüísticos, tales como analizadores y definiciones de diccionario. Se utiliza la metodología Clashing Identification Procedure (CIP), que permite la reducción progresiva del corpus a un tamaño manejable. El interés de diseñar un sistema de etiquetado semántico reside en su contribución a la identificación de las expresiones metafóricas y sinestésicas que se usan frecuentemente en las notas de cata, y también a las tareas de desambiguación. En definitiva, se trata de mostrar cómo deducir computacio...

A survey on computational taste predictors

European Food Research and Technology

Taste is a sensory modality crucial for nutrition and survival, since it allows the discrimination between healthy foods and toxic substances thanks to five tastes, i.e., sweet, bitter, umami, salty, and sour, associated with distinct nutritional or physiological needs. Today, taste prediction plays a key role in several fields, e.g., medical, industrial, or pharmaceutical, but the complexity of the taste perception process, its multidisciplinary nature, and the high number of potentially relevant players and features at the basis of the taste sensation make taste prediction a very complex task. In this context, the emerging capabilities of machine learning have provided fruitful insights in this field of research, allowing to consider and integrate a very large number of variables and identifying hidden correlations underlying the perception of a particular taste. This review aims at summarizing the latest advances in taste prediction, analyzing available food-related databases and...

The phraseology of wine and olive oil tasting notes. A corpus based semantic analysis

Terminology, 2022

Specialized genres are bound to the communicative context of their discourse community. However, certain genres extend beyond one specific domain, remaining unchanged at different linguistic levels across domains. That seems to be the case of wine and olive oil tasting notes since both analyze and evaluate sensory descriptions. The present study aims at describing and comparing lexical chunks of wine and olive oil tasting notes at a semantic level to show if there is variation in the same genre across domains; we will not only describe, classify and compare lexical chunks, but also identify the way this knowledge is structured and construed in the same genre in both domains. We will test our methodology in a corpus of English tasting notes from both genres written by three different writer profiles: professionals, amateurs and wineries/mills. Our results will be useful for scholars as well as technical writers when writing tasting notes.

HAN TO PREDICT CUISINE FROM RECIPES INGREDIENTS

International Research Journal of Modernization in Engineering Technology and Science, 2022

Cuisine is an important aspect of a recipe, as it influences the flavors and techniques used in the preparation of a dish. Predicting cuisine from recipe ingredients is a problem that involves classifying a recipe into one of many possible cuisines based on the ingredients it contains. This is a challenging task because there are many different cuisines in the world, each with its own unique set of ingredients and flavors. To accurately predict the cuisine of a recipe, a model must be able to learn the characteristics of each cuisine and use them to identify the correct cuisine based on the ingredients of the recipe. In this study, we implement different deep learning techniques, such as fastText, TextCNN, TextRNN, TextBiRNN, TextAttBiRNN, and HAN, to the task of accurately predicting cuisine from ingredients. Our results showed that all of the techniques gave a good performance, but HAN achieved the highest accuracy, at 87%.

Cooking Up a Neural-based Model for Recipe Classification

2020

In this paper, we propose a neural-based model to address the first task of the DEFT 2013 shared task, with the main challenge of a highly imbalanced dataset, using state-of-the-art embedding approaches and deep architectures. We report on our experiments on the use of linguistic features, extracted by Charton et. al. (2014), in different neural models utilizing pretrained embeddings. Our results show that all of the models that use linguistic features outperform their counterpart models that only use pretrained embeddings. The best performing model uses pretrained CamemBERT embeddings as input and CNN as the hidden layer, and uses additional linguistic features. Adding the linguistic features to this model improves its performance by 4.5% and 11.4% in terms of micro and macro F1 scores, respectively, leading to state-of-the-art results and an improved classification of the rare classes.