The Effects of Semantic Annotations on Precision Parse Ranking
نویسندگان
چکیده
We investigate the effects of adding semantic annotations including word sense hypernyms to the source text for use as an extra source of information in HPSG parse ranking for the English Resource Grammar. The semantic annotations are coarse semantic categories or entries from a distributional thesaurus, assigned either heuristically or by a pre-trained tagger. We test this using two test corpora in different domains with various sources of training data. The best reduces error rate in dependency Fscore by 1% on average, while some methods produce substantial decreases in performance.
منابع مشابه
UWM: Applying an Existing Trainable Semantic Parser to Parse Robotic Spatial Commands
This paper describes Team UWM’s system for the Task 6 of SemEval 2014 for doing supervised semantic parsing of robotic spatial commands. An existing semantic parser, KRISP, was trained using the provided training data of natural language robotic spatial commands paired with their meaning representations in the formal robot command language. The entire process required very little manual effort....
متن کاملA Syntactic Candidate Ranking Method for Answering Questions with a Main Content Verb
We present a technique for ranking the candidate answers of questions that have a main content verb. This novel ranking method uses the question head (the most important noun phrase) as an anchor for selecting the target subtree in the parse tree of the candidate sentence. The semantic similarity of the action in the selected subtree to the action asked by the question is verified using WordNet...
متن کاملThe Effects of Multimedia Annotations on Iranian EFL Learners’ L2 Vocabulary Learning
In our modern technological world, Computer-Assisted Language learning (CALL) is a new realm towards learning a language in general, and learning L2 vocabulary in particular. It is assumed that the use of multimedia annotations promotes language learners’ vocabulary acquisition. Therefore, this study set out to investigate the effects of different multimedia annotations (still picture annotatio...
متن کاملParse Ranking with Semantic Dependencies and WordNet
In this paper, we investigate which features are useful for ranking semantic representations of text. We show that two methods of generalization improved results: extended grand-parenting and supertypes. The models are tested on a subset of SemCor that has been annotated with both Dependency Minimal Recursion Semantic representations and WordNet senses. Using both types of features gives a sign...
متن کاملUsing Lexical and Compositional Semantics to Improve HPSG Parse Selection
Using Lexical and Compositional Semantics to Improve HPSG Parse Selection Chair of the Supervisory Committee: Dr. Emily Bender University of Washington Accurate parse ranking is essential for deep linguistic processing applications and is one of the classic problems for academic research in NLP. Despite significant advances, there remains a big need for improvement, especially for domains where...
متن کامل