Transition-Based Generation from Abstract Meaning Representations
This work addresses a specific problem in natural language generation for computational linguistics, representing an incremental improvement over prior methods.
The paper tackles the problem of generating English sentences from Abstract Meaning Representation (AMR) graphs by transforming them into dependency-like structures and using maximum entropy models to predict actions, achieving a Bleu score of 27.4 on the LDC2014T12 test set, which is the best result without using additional silver standard annotations.
This work addresses the task of generating English sentences from Abstract Meaning Representation (AMR) graphs. To cope with this task, we transform each input AMR graph into a structure similar to a dependency tree and annotate it with syntactic information by applying various predefined actions to it. Subsequently, a sentence is obtained from this tree structure by visiting its nodes in a specific order. We train maximum entropy models to estimate the probability of each individual action and devise an algorithm that efficiently approximates the best sequence of actions to be applied. Using a substandard language model, our generator achieves a Bleu score of 27.4 on the LDC2014T12 test set, the best result reported so far without using silver standard annotations from another corpus as additional training data.