1 |
Domain-specific coreference resolution with lexicalized features
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Conundrums in noun phrase coreference resolution: making sense of the state-of-the-art
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Toward completeness in concept extraction and classification
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Corpus-based semantic lexicon induction with web-based corroboration
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Unified model of phrasal and sentential evidence for information extraction
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Semantic class learning from the web with hyponym pattern linkage graphs
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Effective information extraction with semantic affinity patterns and relevant regions
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Exploiting role-identifying nouns and expressions for information extraction
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Learning domain-specific information extraction patterns from the web
|
|
|
|
BASE
|
|
Show details
|
|
11 |
OpinionFinder: a system for subjectivity analysis
|
|
Wilson, Theresa; Hoffmann, Paul; Somasundaran, Swapna; Kessler, Jason; Wiebe, Janyce; Choi, Yejin; Cardie, Claire; Patwardhan, Siddharth; Riloff, Ellen M.. - : Association for Computational Linguistics, 2005
|
|
BASE
|
|
Show details
|
|
12 |
Identifying sources of opinions with conditional random fields and extraction patterns
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Unsupervised learning of contextual role knowledge for coreference resolution
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Learning subjective nouns using extraction pattern bootstrapping
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Exploiting strong syntactic heuristics and co-training to learn semantic lexicons
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Bootstrapping method for learning semantic lexicons using extraction pattern contexts
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Inducing information extraction systems for new languages via cross-language projection
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Looking under the hood: tools for diagnosing your question answering engine
|
|
|
|
Abstract:
Journal Article ; In this paper we analyze two question answering tasks : the TREC-8 question answering task and a set of reading comprehension exams. First, we show that Q/A systems perform better when there are multiple answer opportunities per question. Next, we analyze common approaches to two subproblems: term overlap for answer sentence identification, and answer typing for short answer extraction. We present general tools for analyzing the strengths and limitations of techniques for these subproblems. Our results quantify the limitations of both term overlap and answer typing to distinguish between competing answer candidates.
|
|
Keyword:
Information retrieval; Performance; Question-answering systems; TREC-8
|
|
URL: https://collections.lib.utah.edu/ark:/87278/s6891q96
|
|
BASE
|
|
Hide details
|
|
20 |
Rule-based question answering system for reading comprehension tests
|
|
|
|
BASE
|
|
Show details
|
|
|
|