Mohammad Sohrab | Toyota Technological Institute at Nagoya (original) (raw)

Uploads

Papers by Mohammad Sohrab

Research paper thumbnail of A Foundation of Class-Indexing and Class-Semantic-Indexing based Term Weighting Approaches for Automatic Text Classification

Research paper thumbnail of Chemical and Antioxidant Studies of Citrus macroptera

Bangladesh Journal of …, 2009

Key words : Citrus macroptera, Rutaceae, Lupeol, Stigmasterol, Antioxidant. ... Citrus macroptera... more Key words : Citrus macroptera, Rutaceae, Lupeol, Stigmasterol, Antioxidant. ... Citrus macroptera (Bengali name-Shatkara; English name - Wild orange; Family-Rutaceae) is a tree which grows in Indochina, Myanmar, Thailand, Indonesia, Malayasia and Papua New Guinea ...

Research paper thumbnail of Combined Term Weighting Scheme using FFNN,GA, MR, Sum, & Average for Text Classification

This work presents empirical studies on building a combinational process from different term weig... more This work presents empirical studies on building a combinational process from different term weighting approaches to address a new Combined-Term-Weighting-Scheme (CTWS) in information access system, especially on automatic text classification (ATC). The CTWS including, TFCC, TFMI, TFOR, TFPB, TFRF, TFIDF, TFICF, TFICSδF, TFIDFICF, and TFIDFICSδF are used to generate the CTWS approach. Moreover, we introduce five different models to create global weight from a certain weighting scheme to assist the proposed approach. In this study, besides summation and average approaches, well-known mathematical regression (MR), genetic algorithm (GA), and Feed Forward Neural Network (FFNN) are incorporated for creating global weights from a certain weighting scheme. Experiment results show that the proposed combined term weighting schemes including, CTWS-Sum, CTWS-Avg., CTWS-FFNN, CTWS-GA, and CTWS-MR are very effective on the Reuter-21578, 20Newsgroups, and RCV1-v2/LYRL2004 datasets over the Centr...

Research paper thumbnail of EDGE2VEC: Edge Representations for Large-Scale Scalable Hierarchical Learning

Computación y Sistemas

In present front-line of Big Data, prediction tasks over the nodes and edges in complex deep arch... more In present front-line of Big Data, prediction tasks over the nodes and edges in complex deep architecture needs a careful representation of features by assigning hundreds of thousands, or even millions of labels and samples for information access system, especially for hierarchical extreme multi-label classification. We introduce edge2vec, an edge representations framework for learning discrete and continuous features of edges in deep architecture. In edge2vec, we learn a mapping of edges associated with nodes where random samples are augmented by statistical and semantic representations of words and documents. We argue that infusing semantic representations of features for edges by exploiting word2vec and para2vec is the key to learning richer representations for exploring target nodes or labels in the hierarchy. Moreover, we design and implement a balanced stochastic dual coordinate ascent (DCA)-based support vector machine for speeding up training. We introduce a global decision-based top-down walks instead of random walks to predict the most likelihood labels in the deep architecture. We judge the efficiency of edge2vec over the existing state-of-the-art techniques on extreme multi-label hierarchical as well as flat classification tasks. The empirical results show that edge2vec is very promising and computationally very efficient in fast learning and predicting tasks. In deep learning workbench, edge2vec represents a new direction for statistical and semantic representations of features in task-independent networks.

Research paper thumbnail of BENNERD: A Neural Named Entity Linking System for COVID-19

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations

Research paper thumbnail of mgsohrab at WNUT 2020 Shared Task-1: Neural Exhaustive Approach for Entity and Relation Recognition Over Wet Lab Protocols

Proceedings of the Sixth Workshop on Noisy User-generated Text (W-NUT 2020)

Research paper thumbnail of Customer gender prediction system on hierarchical E-commerce data

Beni-Suef University Journal of Basic and Applied Sciences

Background: E-commerce services provide online shopping sites and mobile applications for small a... more Background: E-commerce services provide online shopping sites and mobile applications for small and medium sellers. To provide more efficient buying and selling experiences, a machine learning system can be applied to predict the optimal organization and display of products that maximize the chance of bringing useful information to user that facilitate the online purchases. Therefore, it is important to understand the relevant products for a gender to facilitate the online purchases. In this work, we present a statistical machine learning (ML)-based gender prediction system to predict the gender "male" or "female" from transactional E-commerce data. We introduce different sets of learning algorithms including unique IDs decomposition, context window-based history generation, and extract identical hierarchy from training set to address the gender prediction classification system from online transnational data.

Research paper thumbnail of A Neural Pipeline Approach for the PharmaCoNER Shared Task using Contextual Exhaustive Models

Proceedings of The 5th Workshop on BioNLP Open Shared Tasks

We present a neural pipeline approach that performs named entity recognition (NER) and concept in... more We present a neural pipeline approach that performs named entity recognition (NER) and concept indexing (CI), which links them to concept unique identifiers (CUIs) in a knowledge base, for the PharmaCoNER shared task on pharmaceutical drugs and chemical entities. We proposed a neural NER model that captures the surrounding semantic information of a given sequence by capturing the forwardand backward-context of bidirectional LSTM (Bi-LSTM) output of a target span using contextual span representation-based exhaustive approach. The NER model enumerates all possible spans as potential entity mentions and classify them into entity types or no entity with deep neural networks. For representing span, we compare several different neural network architectures and their ensembling for the NER model. We then perform dictionary matching for CI and, if there is no matching, we further compute similarity scores between a mention and CUIs using entity embeddings to assign the CUI with the highest score to the mention. We evaluate our approach on the two sub-tasks in the shared task. Among the five submitted runs, the best run for each sub-task achieved the F-score of 86.76% on Sub-task 1 (NER) and the F-score of 79.97% (strict) on Sub-task 2 (CI).

Research paper thumbnail of Deep Exhaustive Model for Nested Named Entity Recognition

Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

We propose a simple deep neural model for nested named entity recognition (NER). Most NER models ... more We propose a simple deep neural model for nested named entity recognition (NER). Most NER models focused on flat entities and ignored nested entities, which failed to fully capture underlying semantic information in texts.

Research paper thumbnail of EDGE2VEC: Edge Representations for Large-Scale Scalable Hierarchical Learning

Computación y Sistemas

In present front-line of Big Data, prediction tasks over the nodes and edges in complex deep arch... more In present front-line of Big Data, prediction tasks over the nodes and edges in complex deep architecture needs a careful representation of features by assigning hundreds of thousands, or even millions of labels and samples for information access system, especially for hierarchical extreme multi-label classification. We introduce edge2vec, an edge representations framework for learning discrete and continuous features of edges in deep architecture. In edge2vec, we learn a mapping of edges associated with nodes where random samples are augmented by statistical and semantic representations of words and documents. We argue that infusing semantic representations of features for edges by exploiting word2vec and para2vec is the key to learning richer representations for exploring target nodes or labels in the hierarchy. Moreover, we design and implement a balanced stochastic dual coordinate ascent (DCA)-based support vector machine for speeding up training. We introduce a global decision-based top-down walks instead of random walks to predict the most likelihood labels in the deep architecture. We judge the efficiency of edge2vec over the existing state-of-the-art techniques on extreme multi-label hierarchical as well as flat classification tasks. The empirical results show that edge2vec is very promising and computationally very efficient in fast learning and predicting tasks. In deep learning workbench, edge2vec represents a new direction for statistical and semantic representations of features in task-independent networks.

Research paper thumbnail of Class-indexing-based term weighting for automatic text classification

Information Sciences, 2013

ABSTRACT Most of the previous studies related on different term weighting emphasize on the docume... more ABSTRACT Most of the previous studies related on different term weighting emphasize on the document-indexing-based and four fundamental information elements-based approaches to address automatic text classification (ATC). In this study, we introduce class-indexing-based term-weighting approaches and judge their effects in high-dimensional and comparatively low-dimensional vector space over the TF.IDF and five other different term weighting approaches that are considered as the baseline approaches. First, we implement a class-indexing-based TF.IDF.ICF observational term weighting approach in which the inverse class frequency (ICF) is incorporated. In the experiment, we investigate the effects of TF.IDF.ICF over the Reuters-21578, 20 Newsgroups, and RCV1-v2 datasets as benchmark collections, which provide positive discrimination on rare terms in the vector space and biased against frequent terms in the text classification (TC) task. Therefore, we revised the ICF function and implemented a new inverse class space density frequency (ICSδF), and generated the TF.IDF.ICSδF method that provides a positive discrimination on infrequent and frequent terms. We present detailed evaluation of each category for the three datasets with term weighting approaches. The experimental results show that the proposed class-indexing-based TF.IDF.ICSδF term weighting approach is promising over the compared well-known baseline term weighting approaches.

Research paper thumbnail of Class-indexing-based term weighting for automatic text classification

Information Sciences, 2013

ABSTRACT Most of the previous studies related on different term weighting emphasize on the docume... more ABSTRACT Most of the previous studies related on different term weighting emphasize on the document-indexing-based and four fundamental information elements-based approaches to address automatic text classification (ATC). In this study, we introduce class-indexing-based term-weighting approaches and judge their effects in high-dimensional and comparatively low-dimensional vector space over the TF.IDF and five other different term weighting approaches that are considered as the baseline approaches. First, we implement a class-indexing-based TF.IDF.ICF observational term weighting approach in which the inverse class frequency (ICF) is incorporated. In the experiment, we investigate the effects of TF.IDF.ICF over the Reuters-21578, 20 Newsgroups, and RCV1-v2 datasets as benchmark collections, which provide positive discrimination on rare terms in the vector space and biased against frequent terms in the text classification (TC) task. Therefore, we revised the ICF function and implemented a new inverse class space density frequency (ICSδF), and generated the TF.IDF.ICSδF method that provides a positive discrimination on infrequent and frequent terms. We present detailed evaluation of each category for the three datasets with term weighting approaches. The experimental results show that the proposed class-indexing-based TF.IDF.ICSδF term weighting approach is promising over the compared well-known baseline term weighting approaches.

Research paper thumbnail of Centroid-Means-Embedding: An Approach to Infusing Word Embeddings into Features for Text Classification

Lecture Notes in Computer Science, 2015

Research paper thumbnail of A Foundation of Class-Indexing and Class-Semantic-Indexing based Term Weighting Approaches for Automatic Text Classification

Research paper thumbnail of Chemical and Antioxidant Studies of Citrus macroptera

Bangladesh Journal of …, 2009

Key words : Citrus macroptera, Rutaceae, Lupeol, Stigmasterol, Antioxidant. ... Citrus macroptera... more Key words : Citrus macroptera, Rutaceae, Lupeol, Stigmasterol, Antioxidant. ... Citrus macroptera (Bengali name-Shatkara; English name - Wild orange; Family-Rutaceae) is a tree which grows in Indochina, Myanmar, Thailand, Indonesia, Malayasia and Papua New Guinea ...

Research paper thumbnail of Combined Term Weighting Scheme using FFNN,GA, MR, Sum, & Average for Text Classification

This work presents empirical studies on building a combinational process from different term weig... more This work presents empirical studies on building a combinational process from different term weighting approaches to address a new Combined-Term-Weighting-Scheme (CTWS) in information access system, especially on automatic text classification (ATC). The CTWS including, TFCC, TFMI, TFOR, TFPB, TFRF, TFIDF, TFICF, TFICSδF, TFIDFICF, and TFIDFICSδF are used to generate the CTWS approach. Moreover, we introduce five different models to create global weight from a certain weighting scheme to assist the proposed approach. In this study, besides summation and average approaches, well-known mathematical regression (MR), genetic algorithm (GA), and Feed Forward Neural Network (FFNN) are incorporated for creating global weights from a certain weighting scheme. Experiment results show that the proposed combined term weighting schemes including, CTWS-Sum, CTWS-Avg., CTWS-FFNN, CTWS-GA, and CTWS-MR are very effective on the Reuter-21578, 20Newsgroups, and RCV1-v2/LYRL2004 datasets over the Centr...

Research paper thumbnail of EDGE2VEC: Edge Representations for Large-Scale Scalable Hierarchical Learning

Computación y Sistemas

In present front-line of Big Data, prediction tasks over the nodes and edges in complex deep arch... more In present front-line of Big Data, prediction tasks over the nodes and edges in complex deep architecture needs a careful representation of features by assigning hundreds of thousands, or even millions of labels and samples for information access system, especially for hierarchical extreme multi-label classification. We introduce edge2vec, an edge representations framework for learning discrete and continuous features of edges in deep architecture. In edge2vec, we learn a mapping of edges associated with nodes where random samples are augmented by statistical and semantic representations of words and documents. We argue that infusing semantic representations of features for edges by exploiting word2vec and para2vec is the key to learning richer representations for exploring target nodes or labels in the hierarchy. Moreover, we design and implement a balanced stochastic dual coordinate ascent (DCA)-based support vector machine for speeding up training. We introduce a global decision-based top-down walks instead of random walks to predict the most likelihood labels in the deep architecture. We judge the efficiency of edge2vec over the existing state-of-the-art techniques on extreme multi-label hierarchical as well as flat classification tasks. The empirical results show that edge2vec is very promising and computationally very efficient in fast learning and predicting tasks. In deep learning workbench, edge2vec represents a new direction for statistical and semantic representations of features in task-independent networks.

Research paper thumbnail of BENNERD: A Neural Named Entity Linking System for COVID-19

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations

Research paper thumbnail of mgsohrab at WNUT 2020 Shared Task-1: Neural Exhaustive Approach for Entity and Relation Recognition Over Wet Lab Protocols

Proceedings of the Sixth Workshop on Noisy User-generated Text (W-NUT 2020)

Research paper thumbnail of Customer gender prediction system on hierarchical E-commerce data

Beni-Suef University Journal of Basic and Applied Sciences

Background: E-commerce services provide online shopping sites and mobile applications for small a... more Background: E-commerce services provide online shopping sites and mobile applications for small and medium sellers. To provide more efficient buying and selling experiences, a machine learning system can be applied to predict the optimal organization and display of products that maximize the chance of bringing useful information to user that facilitate the online purchases. Therefore, it is important to understand the relevant products for a gender to facilitate the online purchases. In this work, we present a statistical machine learning (ML)-based gender prediction system to predict the gender "male" or "female" from transactional E-commerce data. We introduce different sets of learning algorithms including unique IDs decomposition, context window-based history generation, and extract identical hierarchy from training set to address the gender prediction classification system from online transnational data.

Research paper thumbnail of A Neural Pipeline Approach for the PharmaCoNER Shared Task using Contextual Exhaustive Models

Proceedings of The 5th Workshop on BioNLP Open Shared Tasks

We present a neural pipeline approach that performs named entity recognition (NER) and concept in... more We present a neural pipeline approach that performs named entity recognition (NER) and concept indexing (CI), which links them to concept unique identifiers (CUIs) in a knowledge base, for the PharmaCoNER shared task on pharmaceutical drugs and chemical entities. We proposed a neural NER model that captures the surrounding semantic information of a given sequence by capturing the forwardand backward-context of bidirectional LSTM (Bi-LSTM) output of a target span using contextual span representation-based exhaustive approach. The NER model enumerates all possible spans as potential entity mentions and classify them into entity types or no entity with deep neural networks. For representing span, we compare several different neural network architectures and their ensembling for the NER model. We then perform dictionary matching for CI and, if there is no matching, we further compute similarity scores between a mention and CUIs using entity embeddings to assign the CUI with the highest score to the mention. We evaluate our approach on the two sub-tasks in the shared task. Among the five submitted runs, the best run for each sub-task achieved the F-score of 86.76% on Sub-task 1 (NER) and the F-score of 79.97% (strict) on Sub-task 2 (CI).

Research paper thumbnail of Deep Exhaustive Model for Nested Named Entity Recognition

Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

We propose a simple deep neural model for nested named entity recognition (NER). Most NER models ... more We propose a simple deep neural model for nested named entity recognition (NER). Most NER models focused on flat entities and ignored nested entities, which failed to fully capture underlying semantic information in texts.

Research paper thumbnail of EDGE2VEC: Edge Representations for Large-Scale Scalable Hierarchical Learning

Computación y Sistemas

In present front-line of Big Data, prediction tasks over the nodes and edges in complex deep arch... more In present front-line of Big Data, prediction tasks over the nodes and edges in complex deep architecture needs a careful representation of features by assigning hundreds of thousands, or even millions of labels and samples for information access system, especially for hierarchical extreme multi-label classification. We introduce edge2vec, an edge representations framework for learning discrete and continuous features of edges in deep architecture. In edge2vec, we learn a mapping of edges associated with nodes where random samples are augmented by statistical and semantic representations of words and documents. We argue that infusing semantic representations of features for edges by exploiting word2vec and para2vec is the key to learning richer representations for exploring target nodes or labels in the hierarchy. Moreover, we design and implement a balanced stochastic dual coordinate ascent (DCA)-based support vector machine for speeding up training. We introduce a global decision-based top-down walks instead of random walks to predict the most likelihood labels in the deep architecture. We judge the efficiency of edge2vec over the existing state-of-the-art techniques on extreme multi-label hierarchical as well as flat classification tasks. The empirical results show that edge2vec is very promising and computationally very efficient in fast learning and predicting tasks. In deep learning workbench, edge2vec represents a new direction for statistical and semantic representations of features in task-independent networks.

Research paper thumbnail of Class-indexing-based term weighting for automatic text classification

Information Sciences, 2013

ABSTRACT Most of the previous studies related on different term weighting emphasize on the docume... more ABSTRACT Most of the previous studies related on different term weighting emphasize on the document-indexing-based and four fundamental information elements-based approaches to address automatic text classification (ATC). In this study, we introduce class-indexing-based term-weighting approaches and judge their effects in high-dimensional and comparatively low-dimensional vector space over the TF.IDF and five other different term weighting approaches that are considered as the baseline approaches. First, we implement a class-indexing-based TF.IDF.ICF observational term weighting approach in which the inverse class frequency (ICF) is incorporated. In the experiment, we investigate the effects of TF.IDF.ICF over the Reuters-21578, 20 Newsgroups, and RCV1-v2 datasets as benchmark collections, which provide positive discrimination on rare terms in the vector space and biased against frequent terms in the text classification (TC) task. Therefore, we revised the ICF function and implemented a new inverse class space density frequency (ICSδF), and generated the TF.IDF.ICSδF method that provides a positive discrimination on infrequent and frequent terms. We present detailed evaluation of each category for the three datasets with term weighting approaches. The experimental results show that the proposed class-indexing-based TF.IDF.ICSδF term weighting approach is promising over the compared well-known baseline term weighting approaches.

Research paper thumbnail of Class-indexing-based term weighting for automatic text classification

Information Sciences, 2013

ABSTRACT Most of the previous studies related on different term weighting emphasize on the docume... more ABSTRACT Most of the previous studies related on different term weighting emphasize on the document-indexing-based and four fundamental information elements-based approaches to address automatic text classification (ATC). In this study, we introduce class-indexing-based term-weighting approaches and judge their effects in high-dimensional and comparatively low-dimensional vector space over the TF.IDF and five other different term weighting approaches that are considered as the baseline approaches. First, we implement a class-indexing-based TF.IDF.ICF observational term weighting approach in which the inverse class frequency (ICF) is incorporated. In the experiment, we investigate the effects of TF.IDF.ICF over the Reuters-21578, 20 Newsgroups, and RCV1-v2 datasets as benchmark collections, which provide positive discrimination on rare terms in the vector space and biased against frequent terms in the text classification (TC) task. Therefore, we revised the ICF function and implemented a new inverse class space density frequency (ICSδF), and generated the TF.IDF.ICSδF method that provides a positive discrimination on infrequent and frequent terms. We present detailed evaluation of each category for the three datasets with term weighting approaches. The experimental results show that the proposed class-indexing-based TF.IDF.ICSδF term weighting approach is promising over the compared well-known baseline term weighting approaches.

Research paper thumbnail of Centroid-Means-Embedding: An Approach to Infusing Word Embeddings into Features for Text Classification

Lecture Notes in Computer Science, 2015