tailieunhanh - Báo cáo khoa học: "Tagging Inflective Languages: Prediction of Morphological Categories for a Rich, Structured Tagset"

The major obstacle in morphological (sometimes called morpho-syntactic, or extended POS) tagging of highly inflective languages, such as Czech or Russian, is - given the resources possibly available - the tagset size. Typically, it is in the order of thousands. Our method uses an exponential probabilistic model based on automatically selected features. The parameters of the model are computed using simple estimates (which makes training much faster than when one uses Maximum Entropy) to directly minimize the error rate on training data. The results obtained so far not only show good performance on disambiguation of most of the individual. | Tagging Inflective Languages Prediction of Morphological Categories for a Rich Structured Tagset Jan Hajic and Barbora Hladká Institute of Formal and Applied Linguistics MFF UK Charles University Prague Czech Republic hajic hladka @ Abstrakt cesky This short abstract is in Czech. For illustration purposes it has been tagged by our tagger errors are printed underlined and corrections are shown. Hlavnim AAIS7---1A problémem NNIS7-----A pfi RR 6-------- morfologickém AANS6----1A znackovani NNNS6----A zI-----------nekdy Db------------ tez Db---------- zvanem AAIS6----1A Correct N morfologicko A2----------- - Z ---------- svntaktické AAIPl---1A Correct NS jazykủ NNIP2----A s RR 7---------- bohatou AAFS7---1A flexi NNFS7-----A Z ------------ jako J ----------- je VB-S 3P-AA-napfiklad Db----------- cestina NNFSl---A nebo J ----------- rustina NNFSl---A Z ---------- je VB-S----3P-AA- - Z ---------- pfi RR 6-------- omezene AAFS6-----1A velikosti NNFS2-A Correct 6 zdrojủ NNIP2----A - Z ---------- pocet NNISl-----A moznych AAFP2-----1A znacek NNFP2----A Z ----------- který P4YSl--------- jde VB-S---3P-AA- obvykle Dg------1A do RR--2 ------- tisícủ NNIP2-------A . Z ----------- Nase PSHSl-Pl----- metoda NNFSl------A pfitom Db------------ vyuziva VB-S---3P-AA- exponenciálního AAIS2---1A pravdẽpodobnostního AAIS2----1A modelu NNIS2 -----A zalozeneho AAIS2--1A na RR 6----------- automaticky Dg-------1A vybranych AAMP6---1A Correct I rysech NNIP6------A . Z ---------- Parametry NNIPl------A tohoto PDZS2--------- modelu NNIS2------A se P7-X4---------- pocitaji VB-P--3P-AA- pomoci NNFS7------A Correct RR 2 - jednoduchych AAIP2---1A odhadu NNIP2------A z trénink NNISl-----A je VB-S----3P-AA- tak Db----------- mnohem Db----------- rychlejsi AAFSl--2A Z -- -------- nez J ----------- kdybychom J -P 1------- pouzili VpMP---XR-AA- metodu NNFS4-----A maximal AAFS4------1A entropie NNFS2---A Z - a J ----------- pfitom Db----------- se P7-X4--------- pfimo Dg-------1A .

crossorigin="anonymous">
Đã phát hiện trình chặn quảng cáo AdBlock
Trang web này phụ thuộc vào doanh thu từ số lần hiển thị quảng cáo để tồn tại. Vui lòng tắt trình chặn quảng cáo của bạn hoặc tạm dừng tính năng chặn quảng cáo cho trang web này.