Jaspreet Singh

Jaspreet Singh, Zhenye Wang, Megha Khosla et al.

Learning-to-rank (LTR) is a class of supervised learning techniques that apply to ranking problems dealing with a large number of features. The popularity and widespread application of LTR models in prioritizing information in a variety of domains makes their scrutability vital in today's landscape of fair and transparent learning systems. However, limited work exists that deals with interpreting the decisions of learning systems that output rankings. In this paper we propose a model agnostic local explanation method that seeks to identify a small subset of input features as explanation to a ranking decision. We introduce new notions of validity and completeness of explanations specifically for rankings, based on the presence or absence of selected features, as a way of measuring goodness. We devise a novel optimization problem to maximize validity directly and propose greedy algorithms as solutions. In extensive quantitative experiments we show that our approach outperforms other model agnostic explanation approaches across pointwise, pairwise and listwise LTR models in validity while not compromising on completeness.

Jaspreet Singh, Avishek Anand

Longitudinal corpora like legal, corporate and newspaper archives are of immense value to a variety of users, and time as an important factor strongly influences their search behavior in these archives. While many systems have been developed to support users temporal information needs, questions remain over how users utilize these advances to satisfy their needs. Analyzing their search behavior will provide us with novel insights into search strategy, guide better interface and system design and highlight new problems for further research. In this paper we propose a set of search tasks, with varying complexity, that IIR researchers can utilize to study user search behavior in archives. We discuss how we created and refined these tasks as the result of a pilot study using a temporal search engine. We not only propose task descriptions but also pre and post-task evaluation mechanisms that can be employed for a large-scale study (crowdsourcing). Our initial findings show the viability of such tasks for investigating search behavior in archives.

Jaspreet Singh, Wolfgang Nejdl, Avishek Anand

Longitudinal corpora like newspaper archives are of immense value to historical research, and time as an important factor for historians strongly influences their search behaviour in these archives. While searching for articles published over time, a key preference is to retrieve documents which cover the important aspects from important points in time which is different from standard search behavior. To support this search strategy, we introduce the notion of a Historical Query Intent to explicitly model a historian's search task and define an aspect-time diversification problem over news archives. We present a novel algorithm, HistDiv, that explicitly models the aspects and important time windows based on a historian's information seeking behavior. By incorporating temporal priors based on publication times and temporal expressions, we diversify both on the aspect and temporal dimensions. We test our methods by constructing a test collection based on The New York Times Collection with a workload of 30 queries of historical intent assessed manually. We find that HistDiv outperforms all competitors in subtopic recall with a slight loss in precision. We also present results of a qualitative user study to determine wether this drop in precision is detrimental to user experience. Our results show that users still preferred HistDiv's ranking.

Jaspreet Singh, Avishek Anand

Given the recent interest in arguably accurate yet non-interpretable neural models, even with textual features, for document ranking we try to answer questions relating to how to interpret rankings. In this paper we take first steps towards a framework for the interpretability of retrieval models with the aim of answering 3 main questions "What is the intent of the query according to the ranker?", "Why is a document ranked higher than another for the query?" and "Why is a document relevant to the query?" Our framework is predicated on the assumption that text based retrieval model behavior can be estimated using query expansions in conjunction with a simpler retrieval model irrespective of the underlying ranker. We conducted experiments with the Clueweb test collection. We show how our approach performs for both simpler models with a closed form notation (which allows us to measure the accuracy of the interpretation) and neural ranking models. Our results indicate that we can indeed interpret more complex models with reasonable accuracy under certain simplifying assumptions. In a case study we also show our framework can be employed to interpret the results of the DRMM neural retrieval model in various scenarios.

Jaspreet Singh, Avishek Anand

Retrieval models in information retrieval are used to rank documents for typically under-specified queries. Today machine learning is used to learn retrieval models from click logs and/or relevance judgments that maximizes an objective correlated with user satisfaction. As these models become increasingly powerful and sophisticated, they also become harder to understand. Consequently, it is hard for to identify artifacts in training, data specific biases and intents from a complex trained model like neural rankers even if trained purely on text features. EXS is a search system designed specifically to provide its users with insight into the following questions: `What is the intent of the query according to the ranker?', `Why is this document ranked higher than another?' and `Why is this document relevant to the query?'. EXS uses a version of a popular posthoc explanation method for classifiers -- LIME, adapted specifically to answer these questions. We show how such a system can effectively help a user understand the results of neural rankers and highlight areas of improvement.

Jaspreet Singh, Avishek Anand

Predictive models are omnipresent in automated and assisted decision making scenarios. But for the most part they are used as black boxes which output a prediction without understanding partially or even completely how different features influence the model prediction avoiding algorithmic transparency. Rankings are ordering over items encoding implicit comparisons typically learned using a family of features using learning-to-rank models. In this paper we focus on how best we can understand the decisions made by a ranker in a post-hoc model agnostic manner. We operate on the notion of interpretability based on explainability of rankings over an interpretable feature space. Furthermore we train a tree based model (inherently interpretable) using labels from the ranker, called secondary training data to provide explanations. Consequently, we attempt to study how well does a subset of features, potentially interpretable, explain the full model under different training sizes and algorithms. We do experiments on the learning to rank datasets with 30k queries and report results that serve show in certain settings we can learn a faithful interpretable ranker.