Grounded Task Prioritization with Context-Aware Sequential Ranking

People rely on task management applications and digital assistants to capture and track their tasks, and help with executing them. The burden of organizing and scheduling time for tasks continues to reside with users of these systems, despite the high cognitive load associated with these activities. Users stand to benefit greatly from a task management system capable of prioritizing their pending tasks, thus saving them time and effort. In this article, we make three main contributions. First, we propose the problem of task prioritization, formulating it as a ranking over a user’s pending tasks given a history of previous interactions with a task management system. Second, we perform an extensive analysis on the large-scale anonymized, de-identified logs of a popular task management application, deriving a dataset of grounded, real-world tasks from which to learn and evaluate our proposed system. We also identify patterns in how people record tasks as complete, which vary consistently with the nature of the task. Third, we propose a novel contextual deep learning solution capable of performing personalized task prioritization. In a battery of tests, we show that this approach outperforms several operational baselines and other sequential ranking models from previous work. Our findings have implications for understanding the ways people prioritize and manage tasks with digital tools, and in the design of support for users of task management applications.

Topic Difficulty: Collection and Query Formulation Effects

Several recent studies have explored the interaction effects between topics, systems, corpora, and components when measuring retrieval effectiveness. However, all of these previous studies assume that a topic or information need is represented by a single query. In reality, users routinely reformulate queries to satisfy an information need. In recent years, there has been renewed interest in the notion of “query variations” which are essentially multiple user formulations for an information need. Like many retrieval models, some queries are highly effective while others are not. This is often an artifact of the collection being searched which might be more or less sensitive to word choice. Users rarely have perfect knowledge about the underlying collection, and so finding queries that work is often a trial-and-error process. In this work, we explore the fundamental problem of system interaction effects between collections, ranking models, and queries. To answer this important question, we formalize the analysis using ANalysis Of VAriance (ANOVA) models to measure multiple components effects across collections and topics by nesting multiple query variations within each topic. Our findings show that query formulations have a comparable effect size of the topic factor itself, which is known to be the factor with the greatest effect size in prior ANOVA studies. Both topic and formulation have a substantially larger effect size than any other factor, including the ranking algorithms and, surprisingly, even query expansion. This finding reinforces the importance of further research in understanding the role of query rewriting in IR related tasks.

Nonmonotonic reasoning from conditional knowledge bases with system W

For nonmonotonic reasoning in the context of a knowledge base $\mathcal {R}$ R containing conditionals of the form If A then usually B, system P provides generally accepted axioms. Inference solely based on system P, however, is inherently skeptical because it coincides with reasoning that takes all ranking models of $\mathcal {R}$ R into account. System Z uses only the unique minimal ranking model of $\mathcal {R}$ R , and c-inference, realized via a complex constraint satisfaction problem, takes all c-representations of $\mathcal {R}$ R into account. C-representations constitute the subset of all ranking models of $\mathcal {R}$ R that are obtained by assigning non-negative integer impacts to each conditional in $\mathcal {R}$ R and summing up, for every world, the impacts of all conditionals falsified by that world. While system Z and c-inference license in general different sets of desirable entailments, the first major objective of this article is to present system W. System W fully captures and strictly extends both system Z and c-inference. Moreover, system W can be represented by a single strict partial order on the worlds over the signature of $\mathcal {R}$ R . We show that system W exhibits further inference properties worthwhile for nonmonotonic reasoning, like satisfying the axioms of system P, respecting conditional indifference, and avoiding the drowning problem. The other main goal of this article is to provide results on our investigations, underlying the development of system W, of upper and lower bounds that can be used to restrict the set of c-representations that have to be taken into account for realizing c-inference. We show that the upper bound of n − 1 is sufficient for capturing c-inference with respect to $\mathcal {R}$ R having n conditionals if there is at least one world verifying all conditionals in $\mathcal {R}$ R . In contrast to the previous conjecture that the number of conditionals in $\mathcal {R}$ R is always sufficient, we prove that there are knowledge bases requiring an upper bound of 2n− 1, implying that there is no polynomial upper bound of the impacts assigned to the conditionals in $\mathcal {R}$ R for fully capturing c-inference.

Neural ranking models for document retrieval

Ranking models are the main components of information retrieval systems. Several approaches to ranking are based on traditional machine learning algorithms using a set of hand-crafted features. Recently, researchers have leveraged deep learning models in information retrieval. These models are trained end-to-end to extract features from the raw data for ranking tasks, so that they overcome the limitations of hand-crafted features. A variety of deep learning models have been proposed, and each model presents a set of neural network components to extract features that are used for ranking. In this paper, we compare the proposed models in the literature along different dimensions in order to understand the major contributions and limitations of each model. In our discussion of the literature, we analyze the promising neural components, and propose future research directions. We also show the analogy between document retrieval and other retrieval tasks where the items to be ranked are structured documents, answers, images and videos.

On the influence of template size, canonicalization and exclusivity for retrosynthesis and reaction prediction applications

Heuristic and machine learning models for rank-ordering reaction templates comprise an important basis for computer-aided organic synthesis regarding both product prediction and retrosynthetic pathway planning. Their viability relies heavily on the quality and characteristics of the underlying template database. With the advent of automated reaction and template extraction software and consequently the creation of template databases too large to be curated manually, a data-driven approach to assess and improve the quality of template sets is needed. We therefore systematically studied the influence of template generality, canonicalization and exclusivity on the performance of different template ranking models. We find that duplicate and non-exclusive templates, \textit{i.e.} templates which describe the same chemical transformation on identical or overlapping sets of molecules, decrease both the accuracy of the ranking algorithm and the applicability of the respective top-ranked templates significantly. To remedy the negative effects of non-exclusivity, we developed a general and computationally efficient framework to deduplicate and hierarchically correct templates. As a result, performance improved for both heuristic and machine learning template ranking algorithms across different template sizes. The canonicalization and correction code was made freely available.

InfOCF-Web: An Online Tool for Nonmonotonic Reasoning with Conditionals and Ranking Functions

InfOCF-Web provides implementations of system P and system Z inference, and of inference relations based on c-representation with respect to various inference modes and different classes of minimal models. It has an easy-to-use online interface for computing ranking models of a conditional knowledge R, and for answering queries and comparing inference results of nonmonotonic inference relations induced by R.