Sujay Kumar Jauhar


2022

pdf bib
MS-LaTTE: A Dataset of Where and When To-do Tasks are Completed
Sujay Kumar Jauhar | Nirupama Chandrasekaran | Michael Gamon | Ryen White
Proceedings of the Thirteenth Language Resources and Evaluation Conference

Tasks are a fundamental unit of work in the daily lives of people, who are increasingly using digital means to keep track of, organize, triage, and act on them. These digital tools – such as task management applications – provide a unique opportunity to study and understand tasks and their connection to the real world, and through intelligent assistance, help people be more productive. By logging signals such as text, timestamp information, and social connectivity graphs, an increasingly rich and detailed picture of how tasks are created and organized, what makes them important, and who acts on them, can be progressively developed. Yet the context around actual task completion remains fuzzy, due to the basic disconnect between actions taken in the real world and telemetry recorded in the digital world. Thus, in this paper we compile and release a novel, real-life, large-scale dataset called MS-LaTTE that captures two core aspects of the context surrounding task completion: location and time. We describe our annotation framework and conduct a number of analyses on the data that were collected, demonstrating that it captures intuitive contextual properties for common tasks. Finally, we test the dataset on the two problems of predicting spatial and temporal task co-occurrence, concluding that predictors for co-location and co-time are both learnable, with a BERT fine-tuned model outperforming several other baselines. The MS-LaTTE dataset provides an opportunity to tackle many new modeling challenges in contextual task understanding and we hope that its release will spur future research in task intelligence more broadly.

pdf bib
One Document, Many Revisions: A Dataset for Classification and Description of Edit Intents
Dheeraj Rajagopal | Xuchao Zhang | Michael Gamon | Sujay Kumar Jauhar | Diyi Yang | Eduard Hovy
Proceedings of the Thirteenth Language Resources and Evaluation Conference

Document authoring involves a lengthy revision process, marked by individual edits that are frequently linked to comments. Modeling the relationship between edits and comments leads to a better understanding of document evolution, potentially benefiting applications such as content summarization, and task triaging. Prior work on understanding revisions has primarily focused on classifying edit intents, but falling short of a deeper understanding of the nature of these edits. In this paper, we present explore the challenge of describing an edit at two levels: identifying the edit intent, and describing the edit using free-form text. We begin by defining a taxonomy of general edit intents and introduce a new dataset of full revision histories of Wikipedia pages, annotated with each revision’s edit intent. Using this dataset, we train a classifier that achieves a 90% accuracy in identifying edit intent. We use this classifier to train a distantly-supervised model that generates a high-level description of a revision in free-form text. Our experimental results show that incorporating edit intent information aids in generating better edit descriptions. We establish a set of baselines for the edit description task, achieving a best score of 28 ROUGE, thus demonstrating the effectiveness of our layered approach to edit understanding.

pdf bib
LITE: Intent-based Task Representation Learning Using Weak Supervision
Naoki Otani | Michael Gamon | Sujay Kumar Jauhar | Mei Yang | Sri Raghu Malireddi | Oriana Riva
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Users write to-dos as personal notes to themselves, about things they need to complete, remember or organize. To-do texts are usually short and under-specified, which poses a challenge for current text representation models. Yet, understanding and representing their meaning is the first step towards providing intelligent assistance for to-do management. We address this problem by proposing a neural multi-task learning framework, LITE, which extracts representations of English to-do tasks with a multi-head attention mechanism on top of a pre-trained text encoder. To adapt representation models to to-do texts, we collect weak-supervision labels from semantically rich external resources (e.g., dynamic commonsense knowledge bases), following the principle that to-do tasks with similar intents have similar labels. We then train the model on multiple generative/predictive training objectives jointly. We evaluate our representation model on four downstream tasks and show that our approach consistently improves performance over baseline models, achieving error reduction of up to 38.7%.

2021

pdf bib
Learning to Decompose and Organize Complex Tasks
Yi Zhang | Sujay Kumar Jauhar | Julia Kiseleva | Ryen White | Dan Roth
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

People rely on digital task management tools, such as email or to-do apps, to manage their tasks. Some of these tasks are large and complex, leading to action paralysis and feelings of being overwhelmed on the part of the user. The micro-productivity literature has shown that such tasks could benefit from being decomposed and organized, in order to reduce user cognitive load. Thus in this paper, we propose a novel end-to-end pipeline that consumes a complex task and induces a dependency graph from unstructured text to represent sub-tasks and their relationships. Our solution first finds nodes for sub-tasks from multiple ‘how-to’ articles on the web by injecting a neural text generator with three key desiderata – relevance, abstraction, and consensus. Then we resolve and infer edges between these subtask nodes by learning task dependency relations. We collect a new dataset of complex tasks with their sub-task graph to develop and evaluate our solutions. Both components of our graph induction solution are evaluated in experiments, demonstrating that our models outperform a state-of-the-art text generator significantly. Our generalizable and scalable end-to-end solution has important implications for boosting user productivity and assisting with digital task management.

2019

pdf bib
Modeling the Relationship between User Comments and Edits in Document Revision
Xuchao Zhang | Dheeraj Rajagopal | Michael Gamon | Sujay Kumar Jauhar | ChangTien Lu
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

Management of collaborative documents can be difficult, given the profusion of edits and comments that multiple authors make during a document’s evolution. Reliably modeling the relationship between edits and comments is a crucial step towards helping the user keep track of a document in flux. A number of authoring tasks, such as categorizing and summarizing edits, detecting completed to-dos, and visually rearranging comments could benefit from such a contribution. Thus, in this paper we explore the relationship between comments and edits by defining two novel, related tasks: Comment Ranking and Edit Anchoring. We begin by collecting a dataset with more than half a million comment-edit pairs based on Wikipedia revision histories. We then propose a hierarchical multi-layer deep neural-network to model the relationship between edits and comments. Our architecture tackles both Comment Ranking and Edit Anchoring tasks by encoding specific edit actions such as additions and deletions, while also accounting for document context. In a number of evaluation settings, our experimental results show that our approach outperforms several strong baselines significantly. We are able to achieve a precision@1 of 71.0% and a precision@3 of 94.4% for Comment Ranking, while we achieve 74.4% accuracy on Edit Anchoring.

2017

pdf bib
Embedded Semantic Lexicon Induction with Joint Global and Local Optimization
Sujay Kumar Jauhar | Eduard Hovy
Proceedings of the 6th Joint Conference on Lexical and Computational Semantics (*SEM 2017)

Creating annotated frame lexicons such as PropBank and FrameNet is expensive and labor intensive. We present a method to induce an embedded frame lexicon in an minimally supervised fashion using nothing more than unlabeled predicate-argument word pairs. We hypothesize that aggregating such pair selectional preferences across training leads us to a global understanding that captures predicate-argument frame structure. Our approach revolves around a novel integration between a predictive embedding model and an Indian Buffet Process posterior regularizer. We show, through our experimental evaluation, that we outperform baselines on two tasks and can learn an embedded frame lexicon that is able to capture some interesting generalities in relation to hand-crafted semantic frames.

2016

pdf bib
Tables as Semi-structured Knowledge for Question Answering
Sujay Kumar Jauhar | Peter Turney | Eduard Hovy
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

2015

pdf bib
Ontologically Grounded Multi-sense Representation Learning for Semantic Vector Space Models
Sujay Kumar Jauhar | Chris Dyer | Eduard Hovy
Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

pdf bib
Retrofitting Word Vectors to Semantic Lexicons
Manaal Faruqui | Jesse Dodge | Sujay Kumar Jauhar | Chris Dyer | Eduard Hovy | Noah A. Smith
Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

pdf bib
Resolving Discourse-Deictic Pronouns: A Two-Stage Approach to Do It
Sujay Kumar Jauhar | Raul Guerra | Edgar Gonzàlez Pellicer | Marta Recasens
Proceedings of the Fourth Joint Conference on Lexical and Computational Semantics

2014

pdf bib
Inducing Latent Semantic Relations for Structured Distributional Semantics
Sujay Kumar Jauhar | Eduard Hovy
Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers

2013

pdf bib
Identifying Metaphorical Word Use with Tree Kernels
Dirk Hovy | Shashank Srivastava | Sujay Kumar Jauhar | Mrinmaya Sachan | Kartik Goyal | Huying Li | Whitney Sanders | Eduard Hovy
Proceedings of the First Workshop on Metaphor in NLP

pdf bib
A Structured Distributional Semantic Model : Integrating Structure with Semantics
Kartik Goyal | Sujay Kumar Jauhar | Huiying Li | Mrinmaya Sachan | Shashank Srivastava | Eduard Hovy
Proceedings of the Workshop on Continuous Vector Space Models and their Compositionality

pdf bib
A Structured Distributional Semantic Model for Event Co-reference
Kartik Goyal | Sujay Kumar Jauhar | Huiying Li | Mrinmaya Sachan | Shashank Srivastava | Eduard Hovy
Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

pdf bib
Prosody-Based Unsupervised Speech Summarization with Two-Layer Mutually Reinforced Random Walk
Sujay Kumar Jauhar | Yun-Nung Chen | Florian Metze
Proceedings of the Sixth International Joint Conference on Natural Language Processing

2012

pdf bib
SemEval-2012 Task 1: English Lexical Simplification
Lucia Specia | Sujay Kumar Jauhar | Rada Mihalcea
*SEM 2012: The First Joint Conference on Lexical and Computational Semantics – Volume 1: Proceedings of the main conference and the shared task, and Volume 2: Proceedings of the Sixth International Workshop on Semantic Evaluation (SemEval 2012)

pdf bib
UOW-SHEF: SimpLex – Lexical Simplicity Ranking based on Contextual and Psycholinguistic Features
Sujay Kumar Jauhar | Lucia Specia
*SEM 2012: The First Joint Conference on Lexical and Computational Semantics – Volume 1: Proceedings of the main conference and the shared task, and Volume 2: Proceedings of the Sixth International Workshop on Semantic Evaluation (SemEval 2012)