Matches in SemOpenAlex for { <https://semopenalex.org/work/W2399340618> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W2399340618 endingPage "136" @default.
- W2399340618 startingPage "123" @default.
- W2399340618 abstract "A realistic Chinese word segmentation tool must adapt to textual variations with minimal training input and yet robust enough to yield reliable segmentation result for all variants. Various lexicon-driven approaches to Chinese segmentation, e.g. [1,16], achieve high f-scores yet require massive training for any variation. Text-driven approach, e.g. [12], can be easily adapted for domain and genre changes yet has difficulty matching the high f-scores of the lexicon-driven approaches. In this paper, we refine and implement an innovative text-driven word boundary decision (WBD) segmentation model proposed in [15]. The WBD model treats word segmentation simply and efficiently as a binary decision on whether to realize the natural textual break between two adjacent characters as a word boundary. The WBD model allows simple and quick training data preparation converting characters as contextual vectors for learning the word boundary decision. Machine learning experiments with four different classifiers show that training with 1,000 vectors and 1 million vectors achieve comparable and reliable results. In addition, when applied to SigHAN Bakeoff 3 competition data, the WBD model produces OOV recall rates that are higher than all published results. Unlike all previous work, our OOV recall rate is comparable to our own F-score. Both experiments support the claim that the WBD model is a realistic model for Chinese word segmentation as it can be easily adapted for new variants with robust result. In conclusion, we will discuss linguistic ramifications as well as future implications for the WBD approach." @default.
- W2399340618 created "2016-06-24" @default.
- W2399340618 creator A5006834833 @default.
- W2399340618 creator A5062585774 @default.
- W2399340618 creator A5067410809 @default.
- W2399340618 creator A5086612355 @default.
- W2399340618 date "2008-12-01" @default.
- W2399340618 modified "2023-09-26" @default.
- W2399340618 title "A Realistic and Robust Model for Chinese Word Segmentation" @default.
- W2399340618 cites W121758096 @default.
- W2399340618 cites W1513618424 @default.
- W2399340618 cites W1558333962 @default.
- W2399340618 cites W2117364574 @default.
- W2399340618 cites W2147880316 @default.
- W2399340618 cites W2163377725 @default.
- W2399340618 cites W2165345215 @default.
- W2399340618 cites W2252066972 @default.
- W2399340618 cites W2252264945 @default.
- W2399340618 cites W2289748525 @default.
- W2399340618 cites W2402385743 @default.
- W2399340618 cites W591436815 @default.
- W2399340618 cites W69683902 @default.
- W2399340618 hasPublicationYear "2008" @default.
- W2399340618 type Work @default.
- W2399340618 sameAs 2399340618 @default.
- W2399340618 citedByCount "1" @default.
- W2399340618 crossrefType "proceedings-article" @default.
- W2399340618 hasAuthorship W2399340618A5006834833 @default.
- W2399340618 hasAuthorship W2399340618A5062585774 @default.
- W2399340618 hasAuthorship W2399340618A5067410809 @default.
- W2399340618 hasAuthorship W2399340618A5086612355 @default.
- W2399340618 hasConcept C134306372 @default.
- W2399340618 hasConcept C153180895 @default.
- W2399340618 hasConcept C154945302 @default.
- W2399340618 hasConcept C204321447 @default.
- W2399340618 hasConcept C2524010 @default.
- W2399340618 hasConcept C2778121359 @default.
- W2399340618 hasConcept C33923547 @default.
- W2399340618 hasConcept C41008148 @default.
- W2399340618 hasConcept C62354387 @default.
- W2399340618 hasConcept C89600930 @default.
- W2399340618 hasConcept C90805587 @default.
- W2399340618 hasConcept C98501671 @default.
- W2399340618 hasConceptScore W2399340618C134306372 @default.
- W2399340618 hasConceptScore W2399340618C153180895 @default.
- W2399340618 hasConceptScore W2399340618C154945302 @default.
- W2399340618 hasConceptScore W2399340618C204321447 @default.
- W2399340618 hasConceptScore W2399340618C2524010 @default.
- W2399340618 hasConceptScore W2399340618C2778121359 @default.
- W2399340618 hasConceptScore W2399340618C33923547 @default.
- W2399340618 hasConceptScore W2399340618C41008148 @default.
- W2399340618 hasConceptScore W2399340618C62354387 @default.
- W2399340618 hasConceptScore W2399340618C89600930 @default.
- W2399340618 hasConceptScore W2399340618C90805587 @default.
- W2399340618 hasConceptScore W2399340618C98501671 @default.
- W2399340618 hasLocation W23993406181 @default.
- W2399340618 hasOpenAccess W2399340618 @default.
- W2399340618 hasPrimaryLocation W23993406181 @default.
- W2399340618 hasRelatedWork W105466489 @default.
- W2399340618 hasRelatedWork W196636961 @default.
- W2399340618 hasRelatedWork W2072150326 @default.
- W2399340618 hasRelatedWork W2166987457 @default.
- W2399340618 hasRelatedWork W2198517985 @default.
- W2399340618 hasRelatedWork W24662179 @default.
- W2399340618 hasRelatedWork W2809887676 @default.
- W2399340618 hasRelatedWork W2949766927 @default.
- W2399340618 hasRelatedWork W2950396480 @default.
- W2399340618 hasRelatedWork W2952094673 @default.
- W2399340618 hasRelatedWork W2952531073 @default.
- W2399340618 hasRelatedWork W2960992944 @default.
- W2399340618 hasRelatedWork W2964173597 @default.
- W2399340618 hasRelatedWork W2969485575 @default.
- W2399340618 hasRelatedWork W3042539794 @default.
- W2399340618 hasRelatedWork W3049650565 @default.
- W2399340618 hasRelatedWork W3090635823 @default.
- W2399340618 hasRelatedWork W3103968805 @default.
- W2399340618 hasRelatedWork W3112439891 @default.
- W2399340618 hasRelatedWork W3182635321 @default.
- W2399340618 isParatext "false" @default.
- W2399340618 isRetracted "false" @default.
- W2399340618 magId "2399340618" @default.
- W2399340618 workType "article" @default.