This paper focuses on a grammar-based approach to semantic interpretation, which combines the notions of robust and weighted parsing. In restricted domains of application in infor...
Conventional n-best reranking techniques often suffer from the limited scope of the nbest list, which rules out many potentially good alternatives. We instead propose forest reran...
We present a novel semi-supervised training algorithm for learning dependency parsers. By combining a supervised large margin loss with an unsupervised least squares loss, a discr...
Parser self-training is the technique of taking an existing parser, parsing extra data and then creating a second parser by treating the extra data as further training data. Here ...
Inclusions from other languages can be a significant source of errors for monolingual parsers. We show this for English inclusions, which are sufficiently frequent to present a ...