Prepositional Phrase Attachment without Oracles
Bibliographic Data
| ID | 12155778 |
|---|---|
| Authors | Michaela Atterer (Institute for Natural Language Processing, University of Stuttgart, Azenbergstr. 12, 70174 Stuttgart, Germany.., corresponding author), Hinrich Schütze (Institute for Natural Language Processing, University of Stuttgart, Azenbergstr. 12, 70174 Stuttgart, Germany..) |
| Year | 2007 |
| Volume | 33 |
| Issue | 4 |
| Pages | 469-476 |
| Publication date | 2007-12-01 |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | Computational Linguistics (JOURNAL) |
| Journal identifiers | ISSN: 0891-2017 • E-ISSN: 1530-9312 |
| Publisher | Association for Computational Linguistics (PUBLISHER • US) |
| DOI | 10.1162/coli.2007.33.4.469 |
| OpenAlex | W2075790020 |
| Language | EN |
| Citations received | 3 |
| References cited | 3 |
Work on prepositional phrase (PP) attachment resolution generally assumes that there is an oracle that provides the two hypothesized structures that we want to choose between. The information that there are two possible attachment sites and the information about the lexical heads of those phrases is usually extracted from gold-standard parse trees. We show that the performance of reattachment methods is higher with such an oracle than without. Because oracles are not available in NLP applications, this indicates that the current evaluation methodology for PP attachment does not produce realistic performance numbers. We argue that PP attachment should not be evaluated in isolation, but instead as an integral component of a parsing system, without using information from the gold-standard oracle
Component (thermodynamics · Isolation (microbiology · Natural language processing · Oracle · Parsing · Phrase · Programming language · Resolution (logic · Computer Science · Natural Language Processing Techniques · Speech and dialogue systems · Topic Modeling · Artificial Intelligence
| Citations per year | 0.15 |
|---|---|
| Citation span | 2006 - 2011 (6) |
| Highly cited | No |