Browsing by Subject "Natural language"
Now showing 1 - 2 of 2
Results Per Page
Sort Options
Item Answering questions about dynamic domains from natural language using ASP(2011-08) Todorova, Yana; Gelfond, Michael; Watson, Richard; Zhang, YuanlinAnswer Set Programming (ASP) is a knowledge representation methodology that has well-established theoretical foundations and good practical uses. The goal of my dissertation was to build an automatic system for answering non-trivial questions from texts in natural language. This is an important task, because the results are very useful in many areas. The final result of this work is an elaboration tolerant question answering system MQA capable of giving provably correct answers. We also used this research to test our reasoning techniques, such as reasoning in dynamic domains, where movement is involved, and reasoning about changes in cardinalities. The original discourse was written in our controlled language MCL , which allowed us to remove a variety of natural language phenomena and to focus on limited grammar rules and on a restricted vocabulary. For the actual reasoning, we used ASP, because of its nonmonotonic features, and its ability to represent defaults and dynamic domains. Thus, given a discourse and a question in our controlled natural language MCL, we first generated a new logic form representation. We represented the knowledge using action language ALM and we included background information not found in the original text. After that, we performed commonsense reasoning using ASP axioms. Finally, we obtained the correct and expected answer to the question.Item Semantic interpretation with distributional analysis(2012-05) Glass, Michael Robert; Barker, Ken, 1959-; Porter, Bruce, 1956-; Mooney, Ray; Erk, Katrin; Dhillon, InderjitUnstructured text contains a wealth of knowledge, however, it is in a form unsuitable for reasoning. Semantic interpretation is the task of processing natural language text to create or extend a coherent, formal knowledgebase able to reason and support question answering. This task involves entity, event and relation extraction, co-reference resolution, and inference. Many domains, from intelligence data to bioinformatics, would benefit by semantic interpretation. But traditional approaches to the subtasks typically require a large annotated corpus specific to a single domain and ontology. This dissertation describes an approach to rapidly train a semantic interpreter using a set of seed annotations and a large, unlabeled corpus. Our approach adapts methods from paraphrase acquisition and automatic thesaurus construction to extend seed syntactic to semantic mappings using an automatically gathered, domain specific, parallel corpus. During interpretation, the system uses joint probabilistic inference to select the most probable interpretation consistent with the background knowledge. We evaluate both the quality of the extended mappings as well as the performance of the semantic interpreter.