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. |
Introduction | Joint methods have also been proposed that invoke integer linear programming ( ILP ) formulations to simultaneously consider multiple structural inference problems—both over n-grams and input dependencies (Martins and Smith, 2009) or n-grams and all possible dependencies (Thadani and McKeown, 2013). |
Introduction | However, it is well-established that the utility of ILP for optimal inference in structured problems is often outweighed by the worst-case performance of ILP solvers on large problems without unique integral solutions. |
Introduction | In this work, we develop approximate inference strategies to the joint approach of Thadani and McKeown (2013) which trade the optimality guarantees of exact ILP for faster inference by separately solving the n-gram and dependency subproblems and using Lagrange multipliers to enforce consistency between their solutions. |
Multi-Structure Sentence Compression | The primary advantage of this technique is the ability to leverage the underlying structure of the problems in inference rather than relying on a generic ILP formulation while still often producing exact solutions. |
Multi-Structure Sentence Compression | Even if ILP-based approaches perform reasonably at the scale of single-sentence compression problems, the exponential worst-case complexity of general-purpose ILPs will inevitably pose challenges when scaling up to (a) handle larger inputs, (b) use higher-order structural fragments, or (c) incorporate additional models. |
Multi-Structure Sentence Compression | In order to produce a solution to this subproblem, we use an LP relaxation of the relevant portion of the ILP from Thadani and McKeown (2013) by omitting integer constraints over the token and dependency variables in x and 2 respectively. |
Experiments | It tends to result in a high recall, and its weakness of low precision is perfectly fixed by the ILP model. |
Experiments | Our ILP model and its variants all outperform Mintz++ in precision in both datasets, indicating that our approach helps filter out incorrect predictions from the output of MaxEnt model. |
Experiments | Compared to ILP-2cand and original ILP , ILP-lcand leads to slightly lower precision but much lower recall, showing that selecting more candidates may help us collect more potentially correct predictions. |
Introduction | We use integer linear programming ( ILP ) as the solver and evaluate our framework on English and Chinese datasets. |
Related Work | de Lacalle and Lapata (2013) encode general domain knowledge as FOL rules in a topic model while our instantiated constraints are directly operated in an ILP model. |
The Framework | In this paper, we propose to solve the problem by using an ILP tool, IBM ILOG Cplexl. |
The Framework | By adopting ILP , we can combine the local information including MaXEnt confidence scores and the implicit relation backgrounds that are embedded into global consistencies of the entity tuples together. |
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. |
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. |
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 | 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): |
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. |
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. |
Abstract | The model adopts the Inductive Logic Programming ( ILP ) algorithm, which provides a relational way to organize different knowledge of entities and mentions. |
Abstract | The evaluation on the ACE data set shows that the ILP based entity-mention model is effective for the coreference resolution task. |
Entity-mention Model with ILP | This requirement motivates our use of Inductive Logic Programming ( ILP ), a learning algorithm capable of inferring logic programs. |
Entity-mention Model with ILP | The relational nature of ILP makes it possible to explicitly represent relations between an entity and its mentions, and thus provides a powerful expressiveness for the coreference resolution task. |
Entity-mention Model with ILP | ILP uses logic programming as a uniform representation for examples, background knowledge and hypotheses. |
Introduction | The model employs Inductive Logic Programming ( ILP ) to represent the relational knowledge of an active mention, an entity, and the mentions in the entity. |
Modelling Coreference Resolution | In the next section, we will present a more expressive entity-mention model by using ILP . |
Related Work | Inductive Logic Programming ( ILP ) has been applied to some natural language processing tasks, including parsing (Mooney, 1997), POS disambiguation (Cussens, 1996), lexicon construction (Claveau et al., 2003), WSD (Specia et al., 2007), and so on. |
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 | 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 | |
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. |
Abstract | We present an ILP-based model of zero anaphora detection and resolution that builds on the joint determination of anaphoricity and coreference model proposed by Denis and Baldridge (2007), but revises it and extends it into a three-way ILP problem also incorporating subject detection. |
Introduction | task, for which Integer Linear Programming ( ILP )—introduced to NLP by Roth and Yih (2004) and successfully applied by Denis and Baldridge (2007) to the task of jointly inferring anaphoricity and determining the antecedent—would be appropriate. |
Introduction | In this work we developed, starting from the ILP system proposed by Denis and Baldridge, an ILP approach to zero anaphora detection and resolution that integrates (revised) versions of Denis and Baldridge’s constraints with additional constraints between the values of three distinct classifiers, one of which is a novel one for subject prediction. |
Introduction | We next present our new ILP formulation in Section 3. |
Dependency Parsing | dence vectors can be cast as an ILP . |
Dependency Parsing as an ILP | By formulating inference as an ILP , nonlocal features can be easily accommodated in our model; furthermore, by using a relaxation technique we can still make learning tractable. |
Dependency Parsing as an ILP | If we add the constraint x E Zd, then the above is called an integer linear program ( ILP ). |
Dependency Parsing as an ILP | Of course, this need not happen: solving a general ILP is an NP-complete problem. |
Introduction | Much attention has recently been devoted to integer linear programming ( ILP ) formulations of NLP problems, with interesting results in applications like semantic role labeling (Roth and Yih, 2005; Punyakanok et al., 2004), dependency parsing (Riedel and Clarke, 2006), word alignment for machine translation (Lacoste-Julien et al., 2006), summarization (Clarke and Lapata, 2008), and coreference resolution (Denis and Baldridge, 2007), among others. |
Introduction | In general, the rationale for the development of ILP formulations is to incorporate nonlocal features or global constraints, which are often difficult to handle with traditional algorithms. |
Introduction | ILP formulations focus more on the modeling of problems, rather than algorithm design. |
Abstract | Inference in our model can be cast as an ILP and thereby solved in reasonable time; we also present a fast approximation scheme which achieves similar performance. |
Efficient Prediction | We show how to perform prediction with the extractive and compressive models by solving ILPs . |
Efficient Prediction | For many instances, a generic ILP solver can find exact solutions to the prediction problems in a matter of seconds. |
Efficient Prediction | 4.1 ILP for extraction |
Introduction | Inference in our model can be cast as an integer linear program (ILP) and solved in reasonable time using a generic ILP solver; we also introduce a fast approximation scheme which achieves similar performance. |
Background | Last, we formulate our optimization problem as an Integer Linear Program ( ILP ). |
Background | ILP is an optimization problem where a linear objective function over a set of integer variables is maximized under a set of linear constraints. |
Background | Scaling ILP is challenging since it is an NP-complete problem. |
Introduction | (2010) proposed a global graph optimization procedure that uses Integer Linear Programming ( ILP ) to find the best set of entailment rules under a transitivity constraint. |
Introduction | The second challenge is scalability: ILP solvers do not scale well since ILP is an NP-complete problem. |
Introduction | Their method employs a local learning approach, while the number of predicates in their data is too large to be handled directly by an ILP solver. |
Learning Typed Entailment Graphs | Section 4.2 gives an ILP formulation for the optimization problem. |
Learning Typed Entailment Graphs | 4.2 ILP formulation |
Learning Typed Entailment Graphs | Thus, employing ILP is an appealing approach for obtaining an optimal solution. |
Experimental Setup | solved an ILP for each document. |
Experimental Setup | The ILP model (see Equation (1)) was parametrized as follows: the maximum number of highlights NS was 4, the overall limit on length LT was 75 tokens, the length of each highlight was in the range of [8, 28] tokens, and the topic coverage set ‘T contained the top 5 tf.idf words. |
Experimental Setup | These parameters were chosen to capture the properties seen in the majority of the training set; they were also relaxed enough to allow a feasible solution of the ILP model (with hard constraints) for all the documents in the test set. |
Introduction | We encode these constraints through the use of integer linear programming ( ILP ), a well-studied optimization framework that is able to search the entire solution space efficiently. |
Modeling | Our approach therefore uses an ILP formulation which will provide a globally optimal solution, and which can be efficiently solved using standard optimization tools. |
Modeling | These edges are important to our formulation, as they will be represented by binary decision variables in the ILP . |
Modeling | ILP model The merged phrase structure tree, such as shown in Figure 2(b), is the actual input to our model. |
Related work | Martins and Smith (2009) formulate a joint sentence extraction and summarization model as an ILP . |
Related work | Headline generation models typically extract individual words from a document to produce a very short summary, whereas we extract phrases and ensure that they are combined into grammatical sentences through our ILP constraints. |
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 . |
Introduction | We estimate the parameters of our model using the perceptron algorithm augmented with an integer linear programming ( ILP ) formulation, run over a training set of example articles in the given domain. |
Method | Using the perceptron framework augmented with an ILP formulation for global optimization, the system is trained to select the best excerpt for each document d, and each topic tj. |
Method | .wk, and the same ILP formulation for global optimization as in training. |
Method | To select the optimal excerpts, we employ integer linear programming ( ILP ). |
Background | We formulate our constraints using Integer Linear Programming ( ILP ). |
Background | No segmentation model is used and no ILP constraints are enforced. |
Background | ILP constraints are enforced between these models. |
Background | variables are integers, the problem is termed an Integer Linear Program ( ILP ). |
Experimental Evaluation | Global algorithms We experimented with all 6 combinations of the following two dimensions: (1) Target functions: score-based, probabilistic and Snow et al.’s (2) Optimization algorithms: Snow et al.’s greedy algorithm and a standard ILP solver. |
Experimental Evaluation | This is the type of global consideration that is addressed in an ILP formulation, but is ignored in a local approach and often overlooked when employing a greedy algorithm. |
Experimental Evaluation | Comparing our use of an ILP algorithm to the greedy one reveals that tuned-LP significantly outperforms its greedy counterpart on both measures (p< .01). |
Introduction | The optimization problem is formulated as an Integer Linear Program (ILP) and solved with an ILP solver. |
Introduction | We show that this leads to an optimal solution with respect to the global function, and demonstrate that the algorithm outperforms methods that utilize only local information by more than 10%, as well as methods that employ a greedy optimization algorithm rather than an ILP solver (Section 6). |
Learning Entailment Graph Edges | Since the variables are binary, both formulations are integer linear programs with O(|V|2) variables and O(|V|3) transitivity constraints that can be solved using standard ILP packages. |
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.” |
Conclusion | Second, there is less engineering overhead for us to perform, because we do not need to generate ILPs for each document. |
Experimental Setup | 11 POS tagging is performed with TnT ver2.2;12 for our dependency-based features we use MaltParser 1.0.0.13 For inference in our models we use Cutting Plane Inference (Riedel, 2008) with ILP as a base solver. |
Introduction | In order to repair the contradictions that the local classifier predicts, Chambers and Jurafsky (2008) proposed a global framework based on Integer Linear Programming ( ILP ). |
Introduction | Instead of combining the output of a set of local classifiers using ILP , we approach the problem of joint temporal relation identification using Markov Logic (Richardson and Domingos, 2006). |
Introduction | 2 In particular, we do not need to manually construct ILPs for each document we encounter. |
Proposed Markov Logic Network | Surely it is possible to incorporate weighted constraints into ILPs , but how to learn the corresponding weights is not obvious. |
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. |
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). |
Argument Identification | (2008) we use the log-probability of the local classifiers as a score in an integer linear program ( ILP ) to assign roles subject to hard constraints described in §5.4 and §5.5. |
Argument Identification | We use an off-the-shelf ILP solver for inference. |
Experiments | ILP constraints For FrameNet, we used three ILP constraints during argument identification (§4). |
Introduction | We also compare the proposed methods with an Integer Linear Programming ( ILP ) based method for timeline construction (Do et al., 2012). |
Problem Description | Moreover, it also outperforms the integer linear programming ( ILP ) method for timeline construction proposed in (Do et al., 2012). |
Problem Description | We observe that in case of MSA, the optimal solution using ILP is still intractable as the number of constraints increases exponentially with the number of sequences. |
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. |