Evaluation Methodology | For Model IM , we varied the number of user intents (K) in intervals from 100 to 400 (see Figure 3), under the assumption that multiple intents would eXist per entity type. |
Experimental Results | Further modeling the user intent in Model IM results in significantly better performance over all models and across all metrics. |
Experimental Results | Model IM shows its biggest gains in the first position of its ranking as evidenced by the PrecĀ©1 metric. |
Experimental Results | Table 2 reports results for Model IM using K = 200 user intents. |
Joint Model of Types and User Intents | 3.1 Intent-based Model ( IM ) |
Joint Model of Types and User Intents | In this section we describe our main model, IM , illustrated in Figure 1. |
Joint Model of Types and User Intents | Table 1: Model IM : Generative process for entity-bearing queries. |
Model Analysis and Discussion | ( IM (VB (target))(OBJ)) |
Model Analysis and Discussion | (VC(VB (target))(OBJ)) (VC(VBG(target))(OBJ)) (OPRD(TO)( IM (VB(target))(OBJ))) (PMOD(VBG(target))(OBJ)) |
Model Analysis and Discussion | (PRP(TO)( IM (VB (target))(OBJ))) |