Conference Paper

Deep Learning for Customs Classification of Goods Based on Their Textual Descriptions Analysis

Authors:
To read the full-text of this research, you can request a copy directly from the authors.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the authors.

Article
Full-text available
Customs classification is an essential international procedure to import cross-border goods traded by various companies and individuals. Proper classification of such goods with high efficiency in light of the rapidly increasing amount of international trade is still challenging. The current abundant e-commence data and advanced machine learning techniques provide an opportunity for cross-border e-commerce sellers to classify goods efficiently. Thus, in this paper, we propose a text-image adaptive convolutional neural network to effectively utilize website information and facilitate the customs classification process. The proposed model includes two independent submodels: one for text and the other for image. The submodels are fused by a novel method, which can adjust the value of parameters according to the model training result. Finally, we conduct a case study and comparison experiments based on a group of customs tariff codes and a data set from an e-commerce website. Experiment results indicate the effectiveness of text and image combination in performance improvement, the outperformance of the adaptive fusion method, as well as the potential of this approach when applied to customs classification.
Article
Full-text available
In this work, we apply word embeddings and neural networks with Long Short-Term Memory (LSTM) to text classification problems, where the classification criteria are decided by the context of the application. We examine two applications in particular. The first is that of Actionability, where we build models to classify social media messages from customers of service providers as Actionable or Non-Actionable. We build models for over 30 different languages for actionability, and most of the models achieve accuracy around 85%, with some reaching over 90% accuracy. We also show that using LSTM neural networks with word embeddings vastly outperform traditional techniques. Second, we explore classification of messages with respect to political leaning, where social media messages are classified as Democratic or Republican. The model is able to classify messages with a high accuracy of 87.57%. As part of our experiments, we vary different hyperparameters of the neural networks, and report the effect of such variation on the accuracy. These actionability models have been deployed to production and help company agents provide customer support by prioritizing which messages to respond to. The model for political leaning has been opened and made available for wider use.
Conference Paper
Full-text available
Artificial neural networks have become state-of-the-art in the task of language modelling on a small corpora. While feed-forward networks are able to take into account only a fixed context length to predict the next word, recurrent neural networks (RNN) can take advantage of all previous words. Due the difficulties in training of RNN, the way could be in using Long Short Term Memory (LSTM) neural network architecture. In this work, we show an application of LSTM network with extensions on a language modelling task with Czech spontaneous phone calls. Experiments show considerable improvements in perplexity and WER on recognition system over n-gram baseline.
Article
Full-text available
The Harmonized System of tariff nomenclature created by the Brussels-based World Customs Organization is widely applied to standardize traded products with Code, Description, Unit of Quantity, and Duty for Classification, to cope with the rapidly increasing international merchandise trade. As part of the function desired by trading system for Singapore Customs, an autocategorization system is expected to accurately classify products into HS codes based on the text description of the goods declaration so to increase the overall usability of the trading system. Background Nets approach has been adopted as the key technique for the development of classification engine in the system. Experimental results indicate the potential of this approach in text categorization with ill-defined vocabularies and complex semantics.
Conference Paper
Full-text available
This article offers an empirical exploration on the use of character-level convolutional networks (ConvNets) for text classification. We constructed several large-scale datasets to show that character-level convolutional networks could achieve state-of-the-art or competitive results. Comparisons are offered against traditional models such as bag of words, n-grams and their TFIDF variants, and deep learning models such as word-based ConvNets and recurrent neural networks.
Article
Now a day's managing a vast amount of documents in digital forms is very important in text mining applications. Text categorization is a task of automatically sorting a set of documents into categories from a predefined set. A major characteristic or difficulty of text categorization is high dimensionality of feature space. The reduction of dimensionality by selecting new attributes which is subset of old attributes is known as feature selection. Feature-selection methods are discussed in this paper for reducing the dimensionality of the dataset by removing features that are considered irrelevant for the classification. In this paper we discuss several approaches of text categorization, feature selection methods and applications of text categorization.
Article
We report on a series of experiments with convolutional neural networks (CNN) trained on top of pre-trained word vectors for sentence-level classification tasks. We first show that a simple CNN with little hyperparameter tuning and static vectors achieves excellent results on multiple benchmarks. Learning task-specific vectors through fine-tuning offers further gains in performance. We additionally propose a simple modification to the architecture to allow for the use of both task-specific and static word vectors. The CNN models discussed herein improve upon the state-of-the-art on 4 out of 7 tasks, which include sentiment analysis and question classification.
Metod avtomatich-eskoi klassifikacii korotkih tekstovih soobshenii
  • A Dral
  • I V Sochenkov
  • E Mbaikodgi
Applying Machine Learning to Product Categorization
  • Sushant Shankar
  • Irving Lin
Sushant Shankar and Irving Lin. Applying Machine Learning to Product Categorization. Department of Computer Science, Stanford University
Metod avtomaticheskoi klassifikacii korotkih tekstovih soobshenii" // Informacionnie tehnologii i vichislitelnie sistemi
  • A A Dral
  • I V Sochenkov
  • E Mbaikodgi
Dral A.A, Sochenkov I. V., Mbaikodgi E., "Metod avtomaticheskoi klassifikacii korotkih tekstovih soobshenii" // Informacionnie tehnologii i vichislitelnie sistemi. -2012. -C. 93-102
Metod avtomatich-eskoi klassifikacii korotkih tekstovih soobshenii
  • dral