Automatic accuracy prediction for AMR parsing
Abstract Meaning Representation (AMR) represents sentences as directed, acyclic and rooted graphs, aiming at capturing their meaning in a machine readable format. AMR parsing converts natural language sentences into such graphs. However, evaluating a parser on new data by means of comparison to manu...
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Dokumenttyp: | Article (Journal) Kapitel/Artikel |
| Sprache: | Englisch |
| Veröffentlicht: |
17 Apr 2019
|
| In: |
Arxiv
Year: 2019, Pages: 1-12 |
| Online-Zugang: | Verlag, Volltext: http://arxiv.org/abs/1904.08301
|
| Verfasserangaben: | Juri Opitz and Anette Frank |
MARC
| LEADER | 00000caa a2200000 c 4500 | ||
|---|---|---|---|
| 001 | 1669121089 | ||
| 003 | DE-627 | ||
| 005 | 20220816191604.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 190715s2019 xx |||||o 00| ||eng c | ||
| 035 | |a (DE-627)1669121089 | ||
| 035 | |a (DE-599)KXP1669121089 | ||
| 035 | |a (OCoLC)1341233694 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rda | ||
| 041 | |a eng | ||
| 084 | |a 28 |2 sdnb | ||
| 245 | 0 | 0 | |a Automatic accuracy prediction for AMR parsing |c Juri Opitz and Anette Frank |
| 264 | 1 | |c 17 Apr 2019 | |
| 300 | |a 12 | ||
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Gesehen am 15.07.2019 | ||
| 520 | |a Abstract Meaning Representation (AMR) represents sentences as directed, acyclic and rooted graphs, aiming at capturing their meaning in a machine readable format. AMR parsing converts natural language sentences into such graphs. However, evaluating a parser on new data by means of comparison to manually created AMR graphs is very costly. Also, we would like to be able to detect parses of questionable quality, or preferring results of alternative systems by selecting the ones for which we can assess good quality. We propose AMR accuracy prediction as the task of predicting several metrics of correctness for an automatically generated AMR parse - in absence of the corresponding gold parse. We develop a neural end-to-end multi-output regression model and perform three case studies: firstly, we evaluate the model's capacity of predicting AMR parse accuracies and test whether it can reliably assign high scores to gold parses. Secondly, we perform parse selection based on predicted parse accuracies of candidate parses from alternative systems, with the aim of improving overall results. Finally, we predict system ranks for submissions from two AMR shared tasks on the basis of their predicted parse accuracy averages. All experiments are carried out across two different domains and show that our method is effective. | ||
| 650 | 4 | |a Computer Science - Computation and Language | |
| 700 | 1 | |a Opitz, Juri |d 1988- |e VerfasserIn |0 (DE-588)117985876X |0 (DE-627)1067540032 |0 (DE-576)518394263 |4 aut | |
| 700 | 1 | |a Frank, Anette |e VerfasserIn |0 (DE-588)1020288108 |0 (DE-627)691172161 |0 (DE-576)36005689X |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Arxiv |d Ithaca, NY : Cornell University, 1991 |g (2019), Artikel-ID 1904.08301, Seite 1-12 |h Online-Ressource |w (DE-627)509006531 |w (DE-600)2225896-6 |w (DE-576)28130436X |7 nnas |a Automatic accuracy prediction for AMR parsing |
| 773 | 1 | 8 | |g year:2019 |g elocationid:1904.08301 |g pages:1-12 |g extent:12 |a Automatic accuracy prediction for AMR parsing |
| 787 | 0 | 8 | |i Forschungsdaten |t AMR parse quality prediction [Source code] |d Heidelberg : Universität, 2019 |h 1 Online-Ressource (1 File) |w (DE-627)1669120643 |
| 856 | 4 | 0 | |u http://arxiv.org/abs/1904.08301 |x Verlag |3 Volltext |
| 951 | |a AR | ||
| 992 | |a 20190715 | ||
| 993 | |a Article | ||
| 994 | |a 2019 | ||
| 998 | |g 1020288108 |a Frank, Anette |m 1020288108:Frank, Anette |d 90000 |d 90500 |e 90000PF1020288108 |e 90500PF1020288108 |k 0/90000/ |k 1/90000/90500/ |p 2 |y j | ||
| 998 | |g 117985876X |a Opitz, Juri |m 117985876X:Opitz, Juri |d 90000 |d 90500 |e 90000PO117985876X |e 90500PO117985876X |k 0/90000/ |k 1/90000/90500/ |p 1 |x j | ||
| 999 | |a KXP-PPN1669121089 |e 3493289022 | ||
| BIB | |a Y | ||
| JSO | |a {"note":["Gesehen am 15.07.2019"],"origin":[{"dateIssuedDisp":"17 Apr 2019","dateIssuedKey":"2019"}],"title":[{"title_sort":"Automatic accuracy prediction for AMR parsing","title":"Automatic accuracy prediction for AMR parsing"}],"type":{"media":"Online-Ressource","bibl":"edited-book"},"name":{"displayForm":["Juri Opitz and Anette Frank"]},"physDesc":[{"extent":"12 S."}],"recId":"1669121089","relHost":[{"part":{"pages":"1-12","year":"2019","extent":"12","text":"(2019), Artikel-ID 1904.08301, Seite 1-12"},"titleAlt":[{"title":"Arxiv.org"},{"title":"Arxiv.org e-print archive"},{"title":"Arxiv e-print archive"},{"title":"De.arxiv.org"}],"language":["eng"],"id":{"eki":["509006531"],"zdb":["2225896-6"]},"recId":"509006531","physDesc":[{"extent":"Online-Ressource"}],"disp":"Automatic accuracy prediction for AMR parsingArxiv","type":{"media":"Online-Ressource","bibl":"edited-book"},"title":[{"title_sort":"Arxiv","title":"Arxiv"}],"note":["Gesehen am 28.05.2024"],"origin":[{"publisherPlace":"Ithaca, NY ; [Erscheinungsort nicht ermittelbar]","dateIssuedKey":"1991","publisher":"Cornell University ; Arxiv.org","dateIssuedDisp":"1991-"}],"pubHistory":["1991 -"]}],"id":{"eki":["1669121089"]},"person":[{"role":"aut","given":"Juri","family":"Opitz","display":"Opitz, Juri"},{"family":"Frank","display":"Frank, Anette","given":"Anette","role":"aut"}],"language":["eng"]} | ||
| SRT | |a OPITZJURIFAUTOMATICA1720 | ||