This paper presents a novel method for recognizing textual entailment which derives the hypothesis from the text through a sequence of parse tree transformations. Unlike related approaches based on tree-edit-distance, we employ transformations which better capture linguistic structures of entailment. This is achieved by (a) extending an earlier deterministic knowledge-based algorithm with syntactically-motivated on-the-fly transformations, and (b) by introducing an algorithm that uniformly learns costs for all types of transformations. Our evaluations and analysis support the validity of this approach. 1

Accurate and robust metrics for automatic evaluation are key to the development of statistical machine translation (MT) systems. We first introduce a new regression model that uses a probabilistic finite state machine (pFSM) to compute weighted edit distance as predictions of translation quality. We also propose a novel pushdown automaton extension of the pFSM model for modeling word swapping and cross alignments that cannot be captured by standard edit distance models. Our models can easily incorporate a rich set of linguistic features, and automatically learn their weights, eliminating the need for ad-hoc parameter tuning. Our methods achieve state-of-the-art correlation with human judgments on two different prediction tasks across a diverse set of standard evaluations (NIST OpenMT06,08; WMT06-08). 1