Milad Shokouhi
Milad Shokouhi has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
Ahmed Hassan Awadallah
Microsoft Research
2 shared publications- Mengnan Du
New Jersey Institute of Technology, USA
2 shared publications Subhabrata Mukherjee
Microsoft Research
2 shared publications- Xia Hu
Rice University, Houston, TX, USA
2 shared publications - Yu Cheng
The Chinese University of Hong Kong, Hong Kong, China
2 shared publications - Budhaditya Deb
Microsoft New England R&D Center
1 shared publication
Latest Publications
- Open Access
Robustness Challenges in Model Distillation and Pruning for Natural Language Understanding
Recent work has focused on compressing pre-trained language models (PLMs) like BERT where the major focus has been to improve the in-distribution performance for downstream tasks. However, very few of these studies have analyzed the impact of compression on the generalizability and robustness of compressed models for out-of-distribution (OOD) data. Towards this end, we study two popular model compression techniques including knowledge distillation and pruning and show that the compressed models are significantly less robust than their PLM counterparts on OOD test sets although they obtain similar performance on in-distribution development sets for a task. Further analysis indicates that the compressed models overfit on the shortcut samples and generalize poorly on the hard ones. We further leverage this observation to develop a regularization strategy for robust model compression based on sample uncertainty. Experimental results on several natural language understanding tasks demonstrate that our bias mitigation framework improves the OOD generalization of the compressed models, while not sacrificing the in-distribution task performance.
Open AccessRobustness Challenges in Model Distillation and Pruning for Natural Language Understanding
Recent work has focused on compressing pre-trained language models (PLMs) like BERT where the major focus has been to improve the in-distribution performance for downstream tasks. However, very few of these studies have analyzed the impact of compression on the generalizability and robustness of compressed models for out-of-distribution (OOD) data. Towards this end, we study two popular model compression techniques including knowledge distillation and pruning and show that the compressed models are significantly less robust than their PLM counterparts on OOD test sets although they obtain similar performance on in-distribution development sets for a task. Further analysis indicates that the compressed models overfit on the shortcut samples and generalize poorly on the hard ones. We further leverage this observation to develop a regularization strategy for robust model compression based on sample uncertainty. Experimental results on several natural language understanding tasks demonstrate that our bias mitigation framework improves the OOD generalization of the compressed models, while not sacrificing the in-distribution task performance.
- Open Access
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 1766-1778
Robustness Challenges in Model Distillation and Pruning for Natural Language Understanding
Mengnan Du, Subhabrata Mukherjee, Yu Cheng, Milad Shokouhi, Xia Hu, Ahmed Hassan Awadallah. Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics. 2023.
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 1766-1778
Open AccessRobustness Challenges in Model Distillation and Pruning for Natural Language Understanding
Mengnan Du, Subhabrata Mukherjee, Yu Cheng, Milad Shokouhi, Xia Hu, Ahmed Hassan Awadallah. Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics. 2023.
- Open Access
UserIdentifier: Implicit User Representations for Simple and Effective Personalized Sentiment Analysis
Global models are trained to be as generalizable as possible, with user invariance considered desirable since the models are shared across multitudes of users. As such, these models are often unable to produce personalized responses for individual users, based on their data. Contrary to widely-used personalization techniques based on few-shot learning, we propose UserIdentifier, a novel scheme for training a single shared model for all users. Our approach produces personalized responses by adding fixed, non-trainable user identifiers to the input data. We empirically demonstrate that this proposed method outperforms the prefix-tuning based state-of-the-art approach by up to 13%, on a suite of sentiment analysis datasets. We also show that, unlike prior work, this method needs neither any additional model parameters nor any extra rounds of few-shot fine-tuning.
Open AccessUserIdentifier: Implicit User Representations for Simple and Effective Personalized Sentiment Analysis
Global models are trained to be as generalizable as possible, with user invariance considered desirable since the models are shared across multitudes of users. As such, these models are often unable to produce personalized responses for individual users, based on their data. Contrary to widely-used personalization techniques based on few-shot learning, we propose UserIdentifier, a novel scheme for training a single shared model for all users. Our approach produces personalized responses by adding fixed, non-trainable user identifiers to the input data. We empirically demonstrate that this proposed method outperforms the prefix-tuning based state-of-the-art approach by up to 13%, on a suite of sentiment analysis datasets. We also show that, unlike prior work, this method needs neither any additional model parameters nor any extra rounds of few-shot fine-tuning.
- Open Access
Characterizing Reading Time on Enterprise Emails
Email is an integral part of people's work and life, enabling them to perform activities such as communicating, searching, managing tasks and storing information. Modern email clients take a step forward and help improve users' productivity by automatically creating reminders, tasks or responses. The act of reading is arguably the only activity that is in common in most -- if not all -- of the interactions that users have with their emails. In this paper, we characterize how users read their enterprise emails, and reveal the various contextual factors that impact reading time. Our approach starts with a reading time analysis based on the reading events from a major email platform, followed by a user study to provide explanations for some discoveries. We identify multiple temporal and user contextual factors that are correlated with reading time. For instance, email reading time is correlated with user devices: on desktop reading time increases through the morning and peaks at noon but on mobile it increases through the evening till midnight. The reading time is also negatively correlated with the screen size. We have established the connection between user status and reading time: users spend more time reading emails when they have fewer meetings and busy hours during the day. In addition, we find that users also reread emails across devices. Among the cross-device reading events, 76% of reread emails are first visited on mobile and then on desktop. Overall, our study is the first to characterize enterprise email reading time on a very large scale. The findings provide insights to develop better metrics and user models for understanding and improving email interactions.
Open AccessCharacterizing Reading Time on Enterprise Emails
Email is an integral part of people's work and life, enabling them to perform activities such as communicating, searching, managing tasks and storing information. Modern email clients take a step forward and help improve users' productivity by automatically creating reminders, tasks or responses. The act of reading is arguably the only activity that is in common in most -- if not all -- of the interactions that users have with their emails. In this paper, we characterize how users read their enterprise emails, and reveal the various contextual factors that impact reading time. Our approach starts with a reading time analysis based on the reading events from a major email platform, followed by a user study to provide explanations for some discoveries. We identify multiple temporal and user contextual factors that are correlated with reading time. For instance, email reading time is correlated with user devices: on desktop reading time increases through the morning and peaks at noon but on mobile it increases through the evening till midnight. The reading time is also negatively correlated with the screen size. We have established the connection between user status and reading time: users spend more time reading emails when they have fewer meetings and busy hours during the day. In addition, we find that users also reread emails across devices. Among the cross-device reading events, 76% of reread emails are first visited on mobile and then on desktop. Overall, our study is the first to characterize enterprise email reading time on a very large scale. The findings provide insights to develop better metrics and user models for understanding and improving email interactions.
- Open Access
Diversifying Reply Suggestions using a Matching-Conditional Variational Autoencoder
We consider the problem of diversifying automated reply suggestions for a commercial instant-messaging (IM) system (Skype). Our conversation model is a standard matching based information retrieval architecture, which consists of two parallel encoders to project messages and replies into a common feature representation. During inference, we select replies from a fixed response set using nearest neighbors in the feature space. To diversify responses, we formulate the model as a generative latent variable model with Conditional Variational Auto-Encoder (M-CVAE). We propose a constrained-sampling approach to make the variational inference in M-CVAE efficient for our production system. In offline experiments, M-CVAE consistently increased diversity by ~30-40% without significant impact on relevance. This translated to a 5% gain in click-rate in our online production system.
Open AccessDiversifying Reply Suggestions using a Matching-Conditional Variational Autoencoder
We consider the problem of diversifying automated reply suggestions for a commercial instant-messaging (IM) system (Skype). Our conversation model is a standard matching based information retrieval architecture, which consists of two parallel encoders to project messages and replies into a common feature representation. During inference, we select replies from a fixed response set using nearest neighbors in the feature space. To diversify responses, we formulate the model as a generative latent variable model with Conditional Variational Auto-Encoder (M-CVAE). We propose a constrained-sampling approach to make the variational inference in M-CVAE efficient for our production system. In offline experiments, M-CVAE consistently increased diversity by ~30-40% without significant impact on relevance. This translated to a 5% gain in click-rate in our online production system.
- Open Access
- 1 January 2013
- Published by BCS Learning & Development Ltd in Electronic Workshops in Computing
Keynote: PhD Recipes
Doing research is a bit like cooking.
- 1 January 2013
- Published by BCS Learning & Development Ltd in Electronic Workshops in Computing
Open AccessKeynote: PhD Recipes
Doing research is a bit like cooking.
- 7 March 2011
- Published by Emerald Publishing in Foundations and Trends® in Information Retrieval
- Vol. 5 (1) , 1-102
Federated Search
Federated search (federated information retrieval or distributed information retrieval) is a technique for searching multiple text collections simultaneously. Queries are submitted to a subset of collections that are most likely to return relevant answers. The results returned by selected collections are integrated and merged into a single list. Federated search is preferred over centralized search alternatives in many environments. For example, commercial search engines such as Google cannot easily index uncrawlable hidden web collections while federated search systems can search the contents of hidden web collections without crawling. In enterprise environments, where each organization maintains an independent search engine, federated search techniques can provide parallel search over multiple collections. There are three major challenges in federated search. For each query, a subset of collections that are most likely to return relevant documents are selected. This creates the collection selection problem. To be able to select suitable collections, federated search systems need to acquire some knowledge about the contents of each collection, creating the collection representation problem. The results returned from the selected collections are merged before the final presentation to the user. This final step is the result merging problem. The goal of this work, is to provide a comprehensive summary of the previous research on the federated search challenges described above.
- 7 March 2011
- Published by Emerald Publishing in Foundations and Trends® in Information Retrieval
- Vol. 5 (1) , 1-102
Federated Search
Federated search (federated information retrieval or distributed information retrieval) is a technique for searching multiple text collections simultaneously. Queries are submitted to a subset of collections that are most likely to return relevant answers. The results returned by selected collections are integrated and merged into a single list. Federated search is preferred over centralized search alternatives in many environments. For example, commercial search engines such as Google cannot easily index uncrawlable hidden web collections while federated search systems can search the contents of hidden web collections without crawling. In enterprise environments, where each organization maintains an independent search engine, federated search techniques can provide parallel search over multiple collections. There are three major challenges in federated search. For each query, a subset of collections that are most likely to return relevant documents are selected. This creates the collection selection problem. To be able to select suitable collections, federated search systems need to acquire some knowledge about the contents of each collection, creating the collection representation problem. The results returned from the selected collections are merged before the final presentation to the user. This final step is the result merging problem. The goal of this work, is to provide a comprehensive summary of the previous research on the federated search challenges described above.
- 27 August 2010
- Published by Springer Nature in Information Retrieval Journal
- Vol. 14 (1) , 1-4
Introduction to special issue on the second international conference on the theory of information retrieval
- 27 August 2010
- Published by Springer Nature in Information Retrieval Journal
- Vol. 14 (1) , 1-4
Introduction to special issue on the second international conference on the theory of information retrieval