Finding an adequate paraphrase representation formalism is a challenging issue in Natural Language Processing. In this paper, we analyse the performance of Tree Edit Distance as a paraphrase representation baseline. Our experiments using Edit Distance Textual Entailment Suite show that, as Tree Edit Distance consists of a purely syntactic approach, paraphrase alternations not based on structural reorganizations do not find an adequate representation. They also show that there is much scope for better modelling of the way trees are aligned
The edit distance (or Levenshtein distance) between two strings x, y is the minimum number of charac...
this paper is to study the definition of edit distances with convex gap weights for trees. In the sp...
An intuitive way for a human to write paraphrase sentences is to replace words or phrases in the ori...
Finding an adequate paraphrase representation formalism is a challenging issue in Natural Language P...
Encontrar un formalismo adecuado para representar la paráfrasis constituye un reto para el Procesami...
Paaßen B, Gallicchio C, Micheli A, Hammer B. Tree Edit Distance Learning via Adaptive Symbol Embeddi...
Metric learning has the aim to improve classification accuracy by learning a distance measure which ...
The string correction problem looks at minimal ways to modify one stringinto another using fixed ope...
Paraphrase, as a general concept, is a very mutable thing; at one extreme, paraphrase is the relatio...
The tree edit distance (TED), defined as the minimum-cost sequence of node operations that transform...
We present an algorithm to approximate edit distance between two ordered and rooted trees of bounded...
This thesis addresses the problem of Recognizing Textual Entailment (i.e. recognizing that ...
Paaßen B. Revisiting the tree edit distance and its backtracing: A tutorial. arXiv:1805.06869. Draft...
Abstract. This work intends to capture the concept of similarity between phrases. The algorithm is b...
We describe tree edit models for representing sequences of tree transformations involving complex re...
The edit distance (or Levenshtein distance) between two strings x, y is the minimum number of charac...
this paper is to study the definition of edit distances with convex gap weights for trees. In the sp...
An intuitive way for a human to write paraphrase sentences is to replace words or phrases in the ori...
Finding an adequate paraphrase representation formalism is a challenging issue in Natural Language P...
Encontrar un formalismo adecuado para representar la paráfrasis constituye un reto para el Procesami...
Paaßen B, Gallicchio C, Micheli A, Hammer B. Tree Edit Distance Learning via Adaptive Symbol Embeddi...
Metric learning has the aim to improve classification accuracy by learning a distance measure which ...
The string correction problem looks at minimal ways to modify one stringinto another using fixed ope...
Paraphrase, as a general concept, is a very mutable thing; at one extreme, paraphrase is the relatio...
The tree edit distance (TED), defined as the minimum-cost sequence of node operations that transform...
We present an algorithm to approximate edit distance between two ordered and rooted trees of bounded...
This thesis addresses the problem of Recognizing Textual Entailment (i.e. recognizing that ...
Paaßen B. Revisiting the tree edit distance and its backtracing: A tutorial. arXiv:1805.06869. Draft...
Abstract. This work intends to capture the concept of similarity between phrases. The algorithm is b...
We describe tree edit models for representing sequences of tree transformations involving complex re...
The edit distance (or Levenshtein distance) between two strings x, y is the minimum number of charac...
this paper is to study the definition of edit distances with convex gap weights for trees. In the sp...
An intuitive way for a human to write paraphrase sentences is to replace words or phrases in the ori...