Vishal Anand

Xiaofeng Zhu, Thomas Lin, Vishal Anand et al.

The core challenge in numerous real-world applications is to match an inquiry to the best document from a mutable and finite set of candidates. Existing industry solutions, especially latency-constrained services, often rely on similarity algorithms that sacrifice quality for speed. In this paper we introduce a generic semantic learning-to-rank framework, Self-training Semantic Cross-attention Ranking (sRank). This transformer-based framework uses linear pairwise loss with mutable training batch sizes and achieves quality gains and high efficiency, and has been applied effectively to show gains on two industry tasks at Microsoft over real-world large-scale data sets: Smart Reply (SR) and Ambient Clinical Intelligence (ACI). In Smart Reply, sRank assists live customers with technical support by selecting the best reply from predefined solutions based on consumer and support agent messages. It achieves 11.7% gain in offline top-one accuracy on the SR task over the previous system, and has enabled 38.7% time reduction in composing messages in telemetry recorded since its general release in January 2021. In the ACI task, sRank selects relevant historical physician templates that serve as guidance for a text summarization model to generate higher quality medical notes. It achieves 35.5% top-one accuracy gain, along with 46% relative ROUGE-L gain in generated medical notes.

Vishal Anand, Milad Alshomary, Kathleen McKeown

We present iBERT (interpretable-BERT), an encoder to produce inherently interpretable and controllable embeddings - designed to modularize and expose the discriminative cues present in language, such as stylistic and semantic structure. Each input token is represented as a sparse, non-negative mixture over k context-independent sense vectors, which can be pooled into sentence embeddings or used directly at the token level. This enables modular control over representation, before any decoding or downstream use. To demonstrate our model's interpretability, we evaluate it on a suite of style-focused tasks. On the STEL benchmark, it improves style representation effectiveness by ~8 points over SBERT-style baselines, while maintaining competitive performance on authorship verification. Because each embedding is a structured composition of interpretable senses, we highlight how specific style attributes - such as emoji use, formality, or misspelling can be assigned to specific sense vectors. While our experiments center on style, iBERT is not limited to stylistic modeling. Its structural modularity is designed to interpretably decompose whichever discriminative signals are present in the data - enabling generalization even when supervision blends stylistic and semantic factors.

Milad Alshomary, Nikhil Reddy Varimalla, Vishal Anand et al.

We propose a new approach for the authorship attribution task that leverages the various linguistic representations learned at different layers of pre-trained transformer-based models. We evaluate our approach on three datasets, comparing it to a state-of-the-art baseline in in-domain and out-of-domain scenarios. We found that utilizing various transformer layers improves the robustness of authorship attribution models when tested on out-of-domain data, resulting in new state-of-the-art results. Our analysis gives further insights into how our model's different layers get specialized in representing certain stylistic features that benefit the model when tested out of the domain.

Vishal Anand, Yuki Miura

The machine learning community has recently had increased interest in the climate and disaster damage domain due to a marked increased occurrences of natural hazards (e.g., hurricanes, forest fires, floods, earthquakes). However, not enough attention has been devoted to mitigating probable destruction from impending natural hazards. We explore this crucial space by predicting building-level damages on a before-the-fact basis that would allow state actors and non-governmental organizations to be best equipped with resource distribution to minimize or preempt losses. We introduce PreDisM that employs an ensemble of ResNets and fully connected layers over decision trees to capture image-level and meta-level information to accurately estimate weakness of man-made structures to disaster-occurrences. Our model performs well and is responsive to tuning across types of disasters and highlights the space of preemptive hazard damage modelling.

Vishal Anand, Ravi Shukla, Ashwani Gupta et al.

Inappropriate and profane content on social media is exponentially increasing and big corporations are becoming more aware of the type of content on which they are advertising and how it may affect their brand reputation. But with a huge surge in content being posted online it becomes seemingly difficult to filter out related videos on which they can run their ads without compromising brand name. Advertising on youtube videos generates a huge amount of revenue for corporations. It becomes increasingly important for such corporations to advertise on only the videos that don't hurt the feelings, community or harmony of the audience at large. In this paper, we propose a system to identify inappropriate content on YouTube and leverage it to perform a first of its kind, large scale, quantitative characterization that reveals some of the risks of YouTube ads consumption on inappropriate videos. Customization of the architecture have also been included to serve different requirements of corporations. Our analysis reveals that YouTube is still plagued by such disturbing videos and its currently deployed countermeasures are ineffective in terms of detecting them in a timely manner. Our framework tries to fill this gap by providing a handy, add on solution to filter the videos and help corporations and companies to push ads on the platform without worrying about the content on which the ads are displayed.

Vishal Anand, S. R. Sreeja, Debasis Samanta

Critical task and cognition-based environments, such as in military and defense operations, aviation user-technology interaction evaluation on UI, understanding intuitiveness of a hardware model or software toolkit, etc. require an assessment of how much a particular task is generating mental workload on a user. This is necessary for understanding how those tasks, operations, and activities can be improvised and made better suited for the users so that they reduce the mental workload on the individual and the operators can use them with ease and less difficulty. However, a particular task can be gauged by a user as simple while for others it may be difficult. Understanding the complexity of a particular task can only be done on user level and we propose to do this by understanding the mental workload (MWL) generated on an operator while performing a task which requires processing a lot of information to get the task done. In this work, we have proposed an experimental setup which replicates modern day workload on doing regular day job tasks. We propose an approach to automatically evaluate the task complexity perceived by an individual by using electroencephalogram (EEG) data of a user during operation. Few crucial steps that are addressed in this work include extraction and optimization of different features and selection of relevant features for dimensionality reduction and using supervised machine learning techniques. In addition to this, performance results of the classifiers are compared using all features and also using only the selected features. From the results, it can be inferred that machine learning algorithms perform better as compared to traditional approaches for mental workload estimation.

Andreas Veit, Michael Wilber, Rajan Vaish et al.

When crowdsourcing systems are used in combination with machine inference systems in the real world, they benefit the most when the machine system is deeply integrated with the crowd workers. However, if researchers wish to integrate the crowd with "off-the-shelf" machine classifiers, this deep integration is not always possible. This work explores two strategies to increase accuracy and decrease cost under this setting. First, we show that reordering tasks presented to the human can create a significant accuracy improvement. Further, we show that greedily choosing parameters to maximize machine accuracy is sub-optimal, and joint optimization of the combined system improves performance.

Vishal Anand, Ramani S

Fault identification and testing has always been the most specific concern in the field of software development. To identify and testify the bug we should be aware of the source of the failure or any unwanted issue. In this paper, we are trying to extract the location of failure and trying to cope up with the bug. Using directed graph, we tried to obtain the dependency of multiple activities in live environment to trace the origin of fault. Software development comes up with series of activities and we tried to show the dependency of multiple activities on each other. Critical activities are considered as they cause abnormal functioning of the whole system. The paper discuss about the priorities of activities of dependency of software failure on the critical activities. Matrix representation of activities as part of the software is chosen to determine root of the failure using concept of dependency. It can vary with the topography of network and software environment. When faults occur, the possible symptoms will be reflected in the dependency matrix with high probability in fault itself. Thus, independent faults are located in the main diagonal of dependency matrix.