Background | proved that this optimization problem, which we term Max-Trans-Graph, is NP-hard, and so described it as an Integer Linear Program ( ILP ). |
Background | Let 137;]- be a binary variable indicating the eXistence of an edge 73 —> j in E. Then, X = {mij : 73 7E j} are the variables of the following ILP for Max-Trans-Graph: |
Background | Since ILP is NP-hard, applying an ILP solver directly does not scale well because the number of variables is O( | V |2) and the number of constraints is O( | V|3). |
Forest-reducible Graphs | In these experiments we show that exactly solving Max-Trans-Graph and Max-Trans-Forest (with an ILP solver) results in nearly identical performance. |
Forest-reducible Graphs | An ILP formulation for Max-Trans-Forest is simple — a transitive graph is an FRG if all nodes in its reduced graph have no more than one parent. |
Forest-reducible Graphs | Therefore, the ILP is formulated by adding this linear constraint to ILP (l): |
Introduction | Since finding the optimal set of edges respecting transitivity is NP-hard, they employed Integer Linear Programming ( ILP ) to find the exact solution. |
Introduction | (Berant et al., 2011) introduced a more efficient exact algorithm, which decomposes the graph into connected components and then applies an ILP solver over each component. |
Sequential Approximation Algorithms | This is dramatically more efficient and scalable than applying an ILP solver. |
Introduction | We employ Integer Linear Programming ( ILP ) as an optimization framework that has been used successfully in other generation tasks (e.g., Clarke and Lapata (2006), Martins and Smith (2009), Woodsend and Lapata (2010)). |
Introduction | Our ILP formulation encodes a rich set of linguistically motivated constraints and weights that incorporate multiple aspects of the generation process. |
Introduction | For a query image, we first retrieve candidate descriptive phrases from a large image-caption database using measures of visual similarity We then generate a coherent description from these candidates using ILP formulations for content planning (§4) and surface realization |
Overview of ILP Formulation | The ILP formulation of §4 addresses T1 & T2, i.e., content-planning, and the ILP of §5 addresses T3 & T4, i.e., surface realization.1 |
Overview of ILP Formulation | 1It is possible to create one conjoined ILP formulation to address all four operations T1—T4 at once. |
Surface Realization | This trick helps the ILP solver to generate sentences with varying number of phrases, rather than always selecting the maximum number of phrases allowed. |
Surface Realization | Baselines: We compare our ILP approaches with two nontrivial baselines: the first is an HMM approach (comparable to Yang et al. |
Surface Realization | HMM HMM ILP ILP cognitive phrases: with w/o with w/o | | 0.111 | 0.114 1 0.114 1 0.116 | |
Abstract | However, they are better applied to a word-based model, thus an integer linear programming ( ILP ) formulation is proposed. |
Abstract | In recent work, interesting results are reported for applications of integer linear programming ( ILP ) such as semantic role labeling (SRL) (Roth and Yih, 2005), dependency parsing (Martins et al., 2009) and so on. |
Abstract | In an ILP formulation, ’nonlocal’ deterministic constraints on output structures can be naturally incorporated, such as ”a verb cannot take two subject arguments” for SRL, and the projectiv-ity constraint for dependency parsing. |
Introduction | tween the lines.” We present an experimental evaluation of our resulting system on a realistic test corpus from DARPA’s Machine Reading project, and demonstrate improved performance compared to a purely logical approach based on Inductive Logic Programming ( ILP ) (Lavrac and DZeroski, 1994), and an alternative SRL approach based on Markov Logic Networks (MLNs) (Domingos and Lowd, 2009). |
Learning BLPs to Infer Implicit Facts | We then learn first-order rules from these extracted facts using LIME (Mc-creath and Sharma, 1998), an ILP system designed for noisy training data. |
Learning BLPs to Infer Implicit Facts | Typically, an ILP system takes a set of positive and negative instances for a target relation, along with a background knowledge base (in our case, other facts extracted from the same document) from which the positive instances are potentially inferable. |
Learning BLPs to Infer Implicit Facts | We initially tried using the popular ALEPH ILP system (Srinivasan, 2001), but it did not produce useful rules, probably due to the high level of noise in our training data. |
Related Work | (2010) modify an ILP system similar to FOIL (Quinlan, 1990) to learn rules with probabilistic conclusions. |
Related Work | (2010) use FARMER (Nijssen and Kok, 2003), an existing ILP system, to learn first-order rules. |
Results and Discussion | However, in contrast to MLNs, BLPs that use first-order rules that are learned by an off-the-shelf ILP system and given simple intuitive hand-coded weights, are able to provide fairly high-precision inferences that augment the output of an IE system and allow it to effectively “read between the lines.” |