U
Ulf Hermjakob
Researcher at University of Southern California
Publications - 46
Citations - 3433
Ulf Hermjakob is an academic researcher from University of Southern California. The author has contributed to research in topics: Parsing & Question answering. The author has an hindex of 22, co-authored 44 publications receiving 3096 citations. Previous affiliations of Ulf Hermjakob include Information Sciences Institute & University of Texas at Austin.
Papers
More filters
Proceedings ArticleDOI
Learning parse and translation decisions from examples with rich context
Ulf Hermjakob,Raymond J. Mooney +1 more
TL;DR: The authors presented a knowledge and context-based system for parsing and translating natural language and evaluate it on sentences from the Wall Street Journal, using parse action examples acquired under supervision to generate a deterministic shift-reduce parser.
Proceedings ArticleDOI
Automated question answering in Webclopedia: a demonstration
TL;DR: This demonstration presents work in the Webclopedia project on semantics-based answer pinpointing through a live interface, where users type in their questions in the query window or select a TREC10 question and the system will parse the question and return the top 5 answers.
Proceedings Article
Rapid parser development: a machine learning approach for Korean
TL;DR: This paper demonstrates that machine learning is a suitable approach for rapid parser development by generating a deterministic shift-reduce parser from 1000 newly treebanked Korean sentences.
Proceedings Article
Using Knowledge to Facilitate Pinpointing of Factoid Answers
TL;DR: In this article, the Webclopedia QA system employs a range of knowledge resources, including a QA Typology with answer patterns, WordNet, information about typical numerical answer ranges, and semantic relations identified by a robust parser, to filter out likely-looking but wrong candidate answers.
Posted Content
Using Syntax-Based Machine Translation to Parse English into Abstract Meaning Representation
TL;DR: This work transforms the AMR structure into a form suitable for the mechanics of SBMT and useful for modeling, and introduces an AMR-specific language model and adds data and features drawn from semantic resources.