EDITS is a software package aimed at recognizing entailment relations between two portions of text, termed as T and H. The system is based on edit distance algorithms, and computes the T-H distance as the cost of the edit operations (i.e. insertion, deletion and substitution) that are necessary to transform T into H. EDITS requires that three modules are defined: an edit distance algorithm, a cost scheme for the three edit operations, and a set of rules expressing either entailment or contradiction. Each module can be easily configured by the user as well as the system parameters. EDITS can work at different levels of complexity, depending on the linguistic analysis carried on over T and H. Both linguistic processors and semantic resources that are available to the user can be integrated within EDITS, resulting in a flexible, modular and extensible approach to Textual Entailment.
EDITS 2.0 process entailment pair in parallel threads to fully utilize the CPU power of the user machine.
The user can now create easily configurations, cost schemes in a user friendly interface.
The user can use aliases instead of class names.
- Word Overlap
- Cosine Similarity
- Jaro-Winkler Similarity
- Longest Common Sub-sequence
- Jaccard Similarity
New entailment engines based on combination of edit distances are available. (Linear Combination and interface to Weka classifier).
Available as plugins:
- PSO - optimizer best on particle swarm optimization (JSWARM-PSO)
- Genetic - optimizer based on genetic algorithms (JGAP)
EDITS 2.0 is capable of generating automatically a cost scheme based on the distance algorithm and entailment rules defined in the configuration file.
The new format of the model is a zip file that contains all the information of an entailment engine (configuration, cost scheme, rules etc.).