Search

Your search keyword '"Haffari, Gholamreza"' showing total 414 results
Start Over Author "Haffari, Gholamreza"
414 results on '"Haffari, Gholamreza"'

154. Turning Flowchart into Dialog: Plan-based Data Augmentation for Low-Resource Flowchart-grounded Troubleshooting Dialogs

Author

Zhan, Haolan, Maruf, Sameen, Qu, Lizhen, Wang, Yufei, Zukerman, Ingrid, and Haffari, Gholamreza

Subjects
FOS: Computer and information sciences, Computer Science - Computation and Language, Computation and Language (cs.CL)
Abstract

Flowchart-grounded troubleshooting dialogue (FTD) systems, which follow the instructions of a flowchart to diagnose users' problems in specific domains (eg., vehicle, laptop), have been gaining research interest in recent years. However, collecting sufficient dialogues that are naturally grounded on flowcharts is costly, thus FTD systems are impeded by scarce training data. To mitigate the data sparsity issue, we propose a plan-based data augmentation (PlanDA) approach that generates diverse synthetic dialog data at scale by transforming concise flowchart into dialogues. Specifically, its generative model employs a variational-base framework with a hierarchical planning strategy that includes global and local latent planning variables. Experiments on the FloDial dataset show that synthetic dialogue produced by PlanDA improves the performance of downstream tasks, including flowchart path retrieval and response generation, in particular on the Out-of-Flowchart settings. In addition, further analysis demonstrate the quality of synthetic data generated by PlanDA in paths that are covered by current sample dialogues and paths that are not covered.

Published
2023
Full Text
View/download PDF

155. HIT’nDRIVE: Multi-driver Gene Prioritization Based on Hitting Time

Author

Shrestha, Raunak, Hodzic, Ermin, Yeung, Jake, Wang, Kendric, Sauerwald, Thomas, Dao, Phuong, Anderson, Shawn, Beltran, Himisha, Rubin, Mark A., Collins, Colin C., Haffari, Gholamreza, Sahinalp, S. Cenk, Hutchison, David, editor, Kanade, Takeo, editor, Kittler, Josef, editor, Kleinberg, Jon M., editor, Mattern, Friedemann, editor, Mitchell, John C., editor, Naor, Moni, editor, Nierstrasz, Oscar, editor, Pandu Rangan, C., editor, Steffen, Bernhard, editor, Sudan, Madhu, editor, Terzopoulos, Demetri, editor, Tygar, Doug, editor, Vardi, Moshe Y., editor, Weikum, Gerhard, editor, Istrail, Sorin, editor, Pevzner, Pavel, editor, Waterman, Michael S., editor, and Sharan, Roded, editor

Published
2014
Full Text
View/download PDF

156. Generate, Annotate, and Learn: NLP with Synthetic Text

Author

He, Xuanli, Nassar, Islam, Kiros, Jamie, Haffari, Gholamreza, and Norouzi, Mohammad

Subjects
FOS: Computer and information sciences, Human-Computer Interaction, Computer Science - Machine Learning, Linguistics and Language, ComputingMethodologies_PATTERNRECOGNITION, Artificial Intelligence, Communication, Machine Learning (cs.LG), Computer Science Applications
Abstract

This paper studies the use of language models as a source of synthetic unlabeled text for NLP. We formulate a general framework called ``generate, annotate, and learn (GAL)'' to take advantage of synthetic text within knowledge distillation, self-training, and few-shot learning applications. To generate high-quality task-specific text, we either fine-tune LMs on inputs from the task of interest, or prompt large LMs with few examples. We use the best available classifier to annotate synthetic text with soft pseudo labels for knowledge distillation and self-training, and use LMs to obtain hard labels for few-shot learning. We train new supervised models on the combination of labeled and pseudo-labeled data, which results in significant gains across several applications. We investigate key components of GAL and present theoretical and empirical arguments against the use of class-conditional LMs to generate synthetic labeled text instead of unlabeled text. GAL achieves new state-of-the-art knowledge distillation results for 6-layer transformers on the GLUE leaderboard., Comment: accepted to TACL2022

Published
2022

163. Voicify Your UI

Author

Vu, Minh Duc, primary, Wang, Han, additional, Li, Zhuang, additional, Haffari, Gholamreza, additional, Xing, Zhenchang, additional, and Chen, Chunyang, additional

Published
2022
Full Text
View/download PDF

168. Towards relation extraction from speech

Author

Wu, Tongtong, primary, Wang, Guitao, additional, Zhao, Jinming, additional, Liu, Zhaoran, additional, Qi, Guilin, additional, Li, Yuan-Fang, additional, and Haffari, Gholamreza, additional

Published
2022
Full Text
View/download PDF

177. Scoring relevancy of features based on combinatorial analysis of Lasso with application to lymphoma diagnosis

Author

Zare Habil, Haffari Gholamreza, Gupta Arvind, and Brinkman Ryan R

Subjects
Biotechnology, TP248.13-248.65, Genetics, QH426-470
Abstract

Abstract One challenge in applying bioinformatic tools to clinical or biological data is high number of features that might be provided to the learning algorithm without any prior knowledge on which ones should be used. In such applications, the number of features can drastically exceed the number of training instances which is often limited by the number of available samples for the study. The Lasso is one of many regularization methods that have been developed to prevent overfitting and improve prediction performance in high-dimensional settings. In this paper, we propose a novel algorithm for feature selection based on the Lasso and our hypothesis is that defining a scoring scheme that measures the "quality" of each feature can provide a more robust feature selection method. Our approach is to generate several samples from the training data by bootstrapping, determine the best relevance-ordering of the features for each sample, and finally combine these relevance-orderings to select highly relevant features. In addition to the theoretical analysis of our feature scoring scheme, we provided empirical evaluations on six real datasets from different fields to confirm the superiority of our method in exploratory data analysis and prediction performance. For example, we applied FeaLect, our feature scoring algorithm, to a lymphoma dataset, and according to a human expert, our method led to selecting more meaningful features than those commonly used in the clinics. This case study built a basis for discovering interesting new criteria for lymphoma diagnosis. Furthermore, to facilitate the use of our algorithm in other applications, the source code that implements our algorithm was released as FeaLect, a documented R package in CRAN.

Published
2013
Full Text
View/download PDF

183. Cognition-aware Cognate Detection

Author

Kanojia, Diptesh, primary, Sharma, Prashant, additional, Ghodekar, Sayali, additional, Bhattacharyya, Pushpak, additional, Haffari, Gholamreza, additional, and Kulkarni, Malhar, additional

Published
2021
Full Text
View/download PDF

194. PREvaIL, an integrative approach for inferring catalytic residues using sequence, structural, and network features in a machine-learning framework

Author

Song, Jiangning, Li, Fuyi, Takemoto, Kazuhiro, Haffari, Gholamreza, Akutsu, Tatsuya, Chou, Kuo-Chen, and Webb, Geoffrey I.

Subjects
Sequence–structure–function relationship, Bioinformatics, Pattern recognition, Machine learning, Sequence analysis, Functional annotation, Enzyme catalytic residues
Abstract

Determining the catalytic residues in an enzyme is critical to our understanding the relationship between protein sequence, structure, function, and enhancing our ability to design novel enzymes and their inhibitors. Although many enzymes have been sequenced, and their primary and tertiary structures determined, experimental methods for enzyme functional characterization lag behind. Because experimental methods used for identifying catalytic residues are resource- and labor-intensive, computational approaches have considerable value and are highly desirable for their ability to complement experimental studies in identifying catalytic residues and helping to bridge the sequence–structure–function gap. In this study, we describe a new computational method called PREvaIL for predicting enzyme catalytic residues. This method was developed by leveraging a comprehensive set of informative features extracted from multiple levels, including sequence, structure, and residue-contact network, in a random forest machine-learning framework. Extensive benchmarking experiments on eight different datasets based on 10-fold cross-validation and independent tests, as well as side-by-side performance comparisons with seven modern sequence- and structure-based methods, showed that PREvaIL achieved competitive predictive performance, with an area under the receiver operating characteristic curve and area under the precision-recall curve ranging from 0.896 to 0.973 and from 0.294 to 0.523, respectively. We demonstrated that this method was able to capture useful signals arising from different levels, leveraging such differential but useful types of features and allowing us to significantly improve the performance of catalytic residue prediction. We believe that this new method can be utilized as a valuable tool for both understanding the complex sequence–structure–function relationships of proteins and facilitating the characterization of novel enzymes lacking functional annotations.

Published
2018

195. Caption Alignment for Low Resource Audio-Visual Data

Author

Konda, Vighnesh Reddy, primary, Warialani, Mayur, additional, Achari, Rakesh Prasanth, additional, Bhatnagar, Varad, additional, Akula, Jayaprakash, additional, Jyothi, Preethi, additional, Ramakrishnan, Ganesh, additional, Haffari, Gholamreza, additional, and Singh, Pankaj, additional

Published
2020
Full Text
View/download PDF

196. A Survey on Document-level Neural Machine Translation: Methods and Evaluation.

Author

MARUF, SAMEEN, SALEH, FAHIMEH, and HAFFARI, GHOLAMREZA

Subjects
NATURAL language processing, MACHINE translating, EVALUATION methodology, TRANSLATORS, TRANSLATIONS
Abstract

Machine translation (MT) is an important task in natural language processing (NLP), as it automates the translation process and reduces the reliance on human translators. With the resurgence of neural networks, the translation quality surpasses that of the translations obtained using statistical techniques for most languagepairs. Up until a few years ago, almost all of the neural translation models translated sentences independently, without incorporating the wider document-context and inter-dependencies among the sentences. The aim of this survey article is to highlight the major works that have been undertaken in the space of document-level machine translation after the neural revolution, so researchers can recognize the current state and future directions of this field. We provide an organization of the literature based on novelties in modelling and architectures as well as training and decoding strategies. In addition, we cover evaluation strategies that have been introduced to account for the improvements in document MT, including automatic metrics and discourse-targeted test sets. We conclude by presenting possible avenues for future exploration in this research field. [ABSTRACT FROM AUTHOR]

Published
2022
Full Text
View/download PDF

197. The genomic and transcriptomic architecture of 2,000 breast tumours reveals novel subgroups

Author

Curtis, Christina, Shah, Sohrab P., Chin, Suet-Feung, Turashvili, Gulisa, Rueda, Oscar M., Dunning, Mark J., Speed, Doug, Lynch, Andy G., Samarajiwa, Shamith, Yuan, Yinyin, Gräf, Stefan, Ha, Gavin, Haffari, Gholamreza, Bashashati, Ali, Russell, Roslin, McKinney, Steven, Aparicio, Samuel, Brenton, James D., Ellis, Ian, Huntsman, David, Pinder, Sarah, Purushotham, Arnie, Murphy, Leigh, Caldas, Carlos, Bardwell, Helen, Ding, Zhihao, Jones, Linda, Liu, Bin, Papatheodorou, Irene, Sammut, Stephen J., Wishart, Gordon, Chia, Steven, Gelmon, Karen, Speers, Caroline, Watson, Peter, Blamey, Roger, Green, Andrew, Macmillan, Douglas, Rakha, Emad, Gillett, Cheryl, Grigoriadis, Anita, de Rinaldis, Emanuele, Tutt, Andy, Parisien, Michelle, Troup, Sandra, Chan, Derek, Fielding, Claire, Maia, Ana-Teresa, McGuire, Sarah, Osborne, Michelle, Sayalero, Sara M., Spiteri, Inmaculada, Hadfield, James, Bell, Lynda, Chow, Katie, Gale, Nadia, Kovalik, Maria, Ng, Ying, Prentice, Leah, Tavaré, Simon, Markowetz, Florian, Langerød, Anita, Provenzano, Elena, and Børresen-Dale, Anne-Lise

Published
2012
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results