This paper describes the UMass TREC 2005 Robust Track experiments. We focus on approaches that use term proximity and pseudo-relevance feedback using external collections. Our results indicate both approaches are highly effective.

It is well known that listeners can ignore disturbances in speech and rely on context to interpolate the message. This fact is used to determine the importance of individual words for projecting Transition Relevance Places, TRPs. Subjects were asked to shadow manipulated pre-recorded dialogs with minimal responses, saying ‘ah’ when they feel it is appropriate. In these dialogs, at random, of ea...

Depending on the task or the environment, we read texts at different speeds. Recently, a substantial amount of literature has risen in the field of predicting relevance of text documents through eye-derived metrics to improve personalization of information retrieval systems. Nevertheless, no academic work has yet addressed the possibility of such measures behaving differently when reading at di...

Prices in a wide variety of contexts come in three parts: an “original” or “suggested” price, a discount off that price, and the final price. Little empirical evidence is available that speaks to how each pricing component affects purchase behavior, even as theories abound. This paper outlines the main theories of fictitious pricing with their corresponding predictions and examines their releva...

This paper discusses our participation in INEX using the TIJAH XML-IR system. We have enriched the TIJAH system, which follows a standard layered database architecture, with several new features. An extensible conceptual level processing unit has been added to the system. The algebra on the logical level and the implementation on the physical level have been extended to support phrase search an...

In TREC 2013 Session Track, we experiment the Query Change Model (QCM) for session search on the new document collection ClueWeb12 CatB. We use structured query formulation and pseudo-relevance feedback for RL1. The QCM approach is used in RL2 and it studies query change between adjacent queries and models session search as a Markov Decision Process. We further add information from other sessio...

A system that can retrieve logically relevant 3D captured motions is useful in game and animation production. We presented a robust logical relevance metric based on the relative distances among the joints. Existing methods select a universal subset of features for all kinds of queries which may not well characterize the variations in different queries. To break through this limitation we propo...

In this year’s Enterprise track experiment, we focused on testing Blind Relevance Feedback, especially using online Wikipedia as query expansion collection. We demonstrated that using Wikipedia as query expansion collection returns better infNDCG than not using it.

This paper presents an automatic relevance feedback method for improving retrieval accuracy in video database. We first demonstrate a representation based on a template-frequency model (TFM) that allows the full use of the temporal dimension. We then integrate the TFM with a self-training neural network structure to adaptively capture different degrees of visual importance in a video sequence. ...