Compressive Summarization | 4 was converted into an ILP and fed to an off-the-she1f solver (Martins and Smith, 2009; Berg-Kirkpatrick et al., 2011; Woodsend and Lapata, 2012). |
Experiments | All these systems require ILP solvers. |
Experiments | We conducted another set of experiments to compare the runtime of our compressive summarizer based on AD3 with the runtimes achieved by GLPK, the ILP solver used by Berg-Kirkpatrick et al. |
Experiments | ROUGE-2 ILP Exact 10.394 12.40 LP-Relax. |
Extractive Summarization | This can be converted into an ILP and addressed with off-the-shelf solvers (Gillick et al., 2008). |
Extractive Summarization | A drawback of this approach is that solving an ILP exactly is NP-hard. |
Introduction | All approaches above are based on integer linear programming ( ILP ), suffering from slow runtimes, when compared to extractive systems. |
Introduction | A second inconvenience of ILP-based approaches is that they do not exploit the modularity of the problem, since the declarative specification required by ILP solvers discards important structural information. |
Connotation Induction Algorithms | Addressing limitations of graph-based algorithms (§2.2), we propose an induction algorithm based on Integer Linear Programming ( ILP ). |
Connotation Induction Algorithms | We formulate insights in Figure 2 using ILP as follows: |
Experimental Result I | Note that a direct comparison against ILP for top N words is tricky, as ILP does not rank results. |
Experimental Result I | ranks based on the frequency of words for ILP . |
Experimental Result I | Because of this issue, the performance of top le words of ILP should be considered only as a conservative measure. |
Precision, Coverage, and Efficiency | Efficiency One practical problem with ILP is efficiency and scalability. |
Precision, Coverage, and Efficiency | In particular, we found that it becomes nearly impractical to run the ILP formulation including all words in WordNet plus all words in the argument position in Google Web IT. |
Precision, Coverage, and Efficiency | Interpretation Unlike ILP , some of the variables result in fractional values. |
Decomposed Amortized Inference | problem cannot be solved using the procedure, then we can either solve the subproblem using a different approach (effectively giving us the standard Lagrangian relaxation algorithm for inference), or we can treat the full instance as a cache miss and make a call to an ILP solver. |
Experiments and Results | We used a database engine to cache ILP and their solutions along with identifiers for the equivalence class and the value of 6. |
Experiments and Results | For the margin-based algorithm and the Theorem 1 from (Srikumar et al., 2012), for a new inference problem p N [P], we retrieve all inference problems from the database that belong to the same equivalence class [P] as the test problem p and find the cached assignment y that has the highest score according to the coefficients of p. We only consider cached ILPs whose solution is y for checking the conditions of the theorem. |
Experiments and Results | We compare our approach to a state-of-the-art ILP solver2 and also to Theorem 1 from (Srikumar et al., 2012). |
Introduction | In these problems, the inference problem has been framed as an integer linear program ( ILP ). |
Margin-based Amortization | If no such problem exists, then we make a call to an ILP solver. |
Problem Definition and Notation | The language of 0-1 integer linear programs ( ILP ) provides a convenient analytical tool for representing structured prediction problems. |
Problem Definition and Notation | One approach to deal with the computational complexity of inference is to use an off-the-shelf ILP solver for solving the inference problem. |
Problem Definition and Notation | Let the set P 2 {p1, p2, - - - } denote previously solved inference problems, along with their respective solutions {yllm yfj, - - - An equivalence class of integer linear programs, denoted by [P], consists of ILPs which have the same number of inference variables and the same feasible set. |
Abstract | In this paper, we propose a bigram based supervised method for extractive document summarization in the integer linear programming ( ILP ) framework. |
Abstract | During testing, the sentence selection problem is formulated as an ILP problem to maximize the bigram gains. |
Abstract | We demonstrate that our system consistently outperforms the previous ILP method on different TAC data sets, and performs competitively compared to the best results in the TAC evaluations. |
Introduction | Many methods have been developed for this problem, including supervised approaches that use classifiers to predict summary sentences, graph based approaches to rank the sentences, and recent global optimization methods such as integer linear programming ( ILP ) and submodular methods. |
Introduction | Gillick and Favre (Gillick and Favre, 2009) introduced the concept-based ILP for summariza- |
Introduction | This ILP method is formally represented as below (see (Gillick and Favre, 2009) for more details): |
Candidate Types for Entities | Our solution is formalized as an Integer Linear Program ( ILP ). |
Candidate Types for Entities | In the following we develop two variants of this approach: a “hard” ILP with rigorous disj ointness constraints, and a “soft” ILP which considers type correlations. |
Candidate Types for Entities | “Hard” ILP with Type Disjointness Constraints. |
Abstract | We use integer linear programming ( ILP ) to model the inference process, which can easily incorporate both the power of existing error classifiers and prior knowledge on grammatical error correction. |
Inference with First Order Variables | The inference problem for grammatical error correction can be stated as follows: “Given an input sentence, choose a set of corrections which results in the best output sentence.” In this paper, this problem will be expressed and solved by integer linear programming ( ILP ). |
Introduction | ear programming ( ILP ). |
Introduction | Variables of ILP are indicators of possible grammatical error corrections, the objective function aims to select the best set of corrections, and the constraints help to enforce a valid and grammatical output. |
Introduction | Furthermore, ILP not only provides a method to solve the inference problem, but also allows for a natural integration of grammatical constraints into a machine learning approach. |
Related Work | The difference between their work and our ILP approach is that the beam-search decoder returns an approximate solution to the original inference problem, while ILP returns an exact solution to an approximate inference problem. |
Experiments | For joint inference, we used GLPK9 to provide the optimal ILP solution. |
Introduction | (2006), which proposed an ILP approach to jointly identify opinion holders, opinion expressions and their IS-FROM linking relations, and demonstrated the effectiveness of joint inference. |
Introduction | Their ILP formulation, however, does not handle implicit linking relations, i.e. |
Model | Note that in our ILP formulation, the label assignment for a candidate span involves one multiple-choice decision among different opinion entity labels and the “NONE” entity label. |
Model | This makes our ILP formulation advantageous over the ILP formulation proposed in Choi et al. |
Related Work | (2006), which jointly extracts opinion expressions, holders and their IS-FROM relations using an ILP approach. |
Related Work | In contrast, our approach (1) also considers the IS-AB OUT relation which is arguably more complex due to the larger variety in the syntactic structure exhibited by opinion expressions and their targets, (2) handles implicit opinion relations (opinion expressions without any associated argument), and (3) uses a simpler ILP formulation. |
Results | To demonstrate the effectiveness of different potentials in our joint inference model, we consider three variants of our ILP formulation that omit some potentials in the joint inference: one is ILP-W/O-ENTITY, which extracts opinion relations without integrating information from opinion entity identification; one is ILP-W-SINGLE-RE, which focuses on extracting a single opinion relation and ignores the information from the other relation; the third one is ILP-W/O-IMPLICIT—RE, which omits the potential for opinion-implicit-arg relation and assumes every opinion expression is linked to an explicit argument. |
Results | It can be viewed as an extension to the ILP approach in Choi et al. |
Results | (2006) that includes opinion targets and uses simpler ILP formulation with only one parameter and fewer binary variables and constraints to represent entity label assignments 11. |
Computing the Metric | ILP method. |
Computing the Metric | We can get an optimal solution using integer linear programming ( ILP ). |
Computing the Metric | Finally, we ask the ILP solver to maximize: |
Introduction | We investigate how to compute this metric and provide several practical and replicable computing methods by using Integer Linear Programming ( ILP ) and hill-climbing method. |
Using Smatch | 0 ILP : Integer Linear Programming |
Using Smatch | Each individual smatch score is a document-level score of 4 AMR pairs.3 ILP scores are optimal, so lower scores (in bold) indicate search errors. |
Using Smatch | Table 2 summarizes search accuracy as a percentage of smatch scores that equal that of ILP . |
Joint Model of Extraction and Compression | An optimization problem with this objective function cannot be regarded as an ILP problem because it contains nonlinear terms. |
Related Work | Integer linear programming ( ILP ) formulations can represent such flexible constraints, and they are commonly used to model text summarization (McDonald, 2007). |
Related Work | (2011) formulated a unified task of sentence extraction and sentence compression as an ILP . |
Related Work | However, it is hard to solve large-scale ILP problems exactly in a practical amount of time. |
Semantic Interpretation Model | We follow (Goldwasser et al., 2011; Clarke et al., 2010) and formalize semantic inference as an Integer Linear Program ( ILP ). |
Semantic Interpretation Model | We then proceed to augment this model with domain-independent information, and connect the two models by constraining the ILP model. |
Semantic Interpretation Model | We take advantage of the flexible ILP framework and encode these restrictions as global constraints. |
Experimentation | To achieve an optimal solution, we formulate the global inference problem as an Integer Linear Program ( ILP ), which leads to maximize the objective function. |
Experimentation | ILP is a mathematical method for constraint-based inference to find the optimal values for a set of variables that maximize an objective function in satisfying a certain number of constraints. |
Experimentation | In the literature, ILP has been widely used in many NLP applications (e.g., Barzilay and Lapata, 2006; Do et al., 2012; Li et al., 2012b). |