Matches in SemOpenAlex for { <https://semopenalex.org/work/W122290181> ?p ?o ?g. }
- W122290181 abstract "Current efforts in syntactic parsing are largely data-driven. These methods require labeled examples of syntactic structures to learn statistical patterns governing these structures. Labeled data typically requires expert annotators which makes it both time consuming and costly to produce. Furthermore, once training data has been created for one textual domain, portability to similar domains is limited. This domain-dependence has inspired a large body of work since syntactic parsing aims to capture syntactic patterns across an entire language rather than just a specific domain. The simplest approach to this task is to assume that the target domain is essentially the same as the source domain. No additional knowledge about the target domain is included. A more realistic approach assumes that only raw text from the target domain is available. This assumption lends itself well to semi-supervised learning methods since these utilize both labeled and unlabeled examples. This dissertation focuses on a family of semi-supervised methods called self-training. Self-training creates semi-supervised learners from existing supervised learners with minimal effort. We first show results on self-training for constituency parsing within a single domain. While self-training has failed here in the past, we present a simple modification which allows it to succeed, producing state-of-the-art results for English constituency parsing. Next, we show how self-training is beneficial when parsing across domains and helps further when raw text is available from the target domain. One of the remaining issues is that one must choose a training corpus appropriate for the target domain or performance may be severely impaired. Humans can do this in some situations, but this strategy becomes less practical as we approach larger data sets. We present a technique, Any Domain Parsing, which automatically detects useful source domains and mixes them together to produce a customized parsing model. The resulting models perform almost as well as the best seen parsing models (oracle) for each target domain. As a result, we have a fully automatic syntactic constituency parser which can produce high-quality parses for all types of text, regardless of domain." @default.
- W122290181 created "2016-06-24" @default.
- W122290181 creator A5005380528 @default.
- W122290181 creator A5029071304 @default.
- W122290181 date "2010-01-01" @default.
- W122290181 modified "2023-09-23" @default.
- W122290181 title "Any domain parsing: automatic domain adaptation for natural language parsing" @default.
- W122290181 cites W102233799 @default.
- W122290181 cites W10704533 @default.
- W122290181 cites W1517284397 @default.
- W122290181 cites W151797160 @default.
- W122290181 cites W1535015163 @default.
- W122290181 cites W1567277581 @default.
- W122290181 cites W1567570606 @default.
- W122290181 cites W1590397582 @default.
- W122290181 cites W1632114991 @default.
- W122290181 cites W1648311451 @default.
- W122290181 cites W1818857488 @default.
- W122290181 cites W1859173823 @default.
- W122290181 cites W1885010341 @default.
- W122290181 cites W1953828586 @default.
- W122290181 cites W1965897786 @default.
- W122290181 cites W1966784040 @default.
- W122290181 cites W1976606095 @default.
- W122290181 cites W1982944197 @default.
- W122290181 cites W1986543644 @default.
- W122290181 cites W2000359198 @default.
- W122290181 cites W2002586403 @default.
- W122290181 cites W2005126631 @default.
- W122290181 cites W2006734720 @default.
- W122290181 cites W2012012028 @default.
- W122290181 cites W2026976290 @default.
- W122290181 cites W2032235985 @default.
- W122290181 cites W2037894654 @default.
- W122290181 cites W2044122727 @default.
- W122290181 cites W2046240571 @default.
- W122290181 cites W2046731689 @default.
- W122290181 cites W2048679005 @default.
- W122290181 cites W2069699492 @default.
- W122290181 cites W2069912724 @default.
- W122290181 cites W2082024724 @default.
- W122290181 cites W2087165009 @default.
- W122290181 cites W2092481996 @default.
- W122290181 cites W2097480711 @default.
- W122290181 cites W2098050104 @default.
- W122290181 cites W2103504425 @default.
- W122290181 cites W2104936489 @default.
- W122290181 cites W2107968230 @default.
- W122290181 cites W2108059661 @default.
- W122290181 cites W2118681326 @default.
- W122290181 cites W2120354757 @default.
- W122290181 cites W2121170334 @default.
- W122290181 cites W2122922578 @default.
- W122290181 cites W2123893795 @default.
- W122290181 cites W2128092251 @default.
- W122290181 cites W2128634885 @default.
- W122290181 cites W2130903752 @default.
- W122290181 cites W2134275125 @default.
- W122290181 cites W2134729743 @default.
- W122290181 cites W2138382875 @default.
- W122290181 cites W2139621418 @default.
- W122290181 cites W2140076625 @default.
- W122290181 cites W2140526624 @default.
- W122290181 cites W2140702357 @default.
- W122290181 cites W2142708806 @default.
- W122290181 cites W2145208835 @default.
- W122290181 cites W2145837098 @default.
- W122290181 cites W2155693943 @default.
- W122290181 cites W2158108973 @default.
- W122290181 cites W2158195707 @default.
- W122290181 cites W2159230276 @default.
- W122290181 cites W2159642183 @default.
- W122290181 cites W2159757335 @default.
- W122290181 cites W2161795601 @default.
- W122290181 cites W2163302275 @default.
- W122290181 cites W2163568299 @default.
- W122290181 cites W2167434254 @default.
- W122290181 cites W2167980204 @default.
- W122290181 cites W2168194229 @default.
- W122290181 cites W2170206653 @default.
- W122290181 cites W2174538811 @default.
- W122290181 cites W2396955895 @default.
- W122290181 cites W2528606233 @default.
- W122290181 cites W2759437203 @default.
- W122290181 cites W3021452258 @default.
- W122290181 cites W3198494294 @default.
- W122290181 cites W168104154 @default.
- W122290181 hasPublicationYear "2010" @default.
- W122290181 type Work @default.
- W122290181 sameAs 122290181 @default.
- W122290181 citedByCount "80" @default.
- W122290181 countsByYear W1222901812012 @default.
- W122290181 countsByYear W1222901812013 @default.
- W122290181 countsByYear W1222901812014 @default.
- W122290181 countsByYear W1222901812015 @default.
- W122290181 countsByYear W1222901812016 @default.
- W122290181 countsByYear W1222901812017 @default.
- W122290181 countsByYear W1222901812018 @default.
- W122290181 countsByYear W1222901812019 @default.
- W122290181 countsByYear W1222901812020 @default.