An Encoder-Decoder Approach to the Paradigm Cell Filling Problem

被引：0

作者：

Silfverberg, Miikka ^{[1
,2
]}

Hulden, Mans ^{[1
]}

机构：

[1] Univ Colorado, Dept Linguist, Boulder, CO 80309 USA

[2] Univ Helsinki, Helsinki, Finland

来源：

2018 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP 2018) | 2018年

关键词：

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The Paradigm Cell Filling Problem in morphology asks to complete word inflection tables from partial ones. We implement novel neural models for this task, evaluating them on 18 data sets in 8 languages, showing performance that is comparable with previous work with far less training data. We also publish a new dataset for this task and code implementing the system described in this paper.(1)

引用

页码：2883 / 2889

页数：7

共 24 条

[1]

Ackerman Farrell, 2009, PARTS WHOLES IMPLICA, P54

[2] Morphological Inflection Generation with Hard Monotonic Attention [J].

Aharoni, Roee ;

Goldberg, Yoav .

PROCEEDINGS OF THE 55TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2017), VOL 1, 2017, :2004-2015

[3]

Ahlberg M., 2015, Proc. of the 2015 Conf. of the North American Chapter of the ACL: Human Language Technologies, Denver, P1024

[4]

Ahlberg Malin., 2014, P 14 C EUROPEAN CHAP, P569

[5]

[Anonymous], 2013, P 17 C COMP NAT LANG

[6]

Bahdanau D, 2016, Arxiv, DOI arXiv:1409.0473

[7]

Blevins James P., 2009, ANALOGY IN GRAMMAR

[8]

Cotterell R., 2017, Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, P714

[9]

Cotterell R, 2016, P 14 SIGMORPHON WORK, P10, DOI DOI 10.18653/V1/W16-2002

[10]

Cotterell Ryan, 2017, P CONLL SIGMORPHON 2, P1

← 1 2 3 →