Do LSTMs really work so well for PoS tagging? -- A replication study

2017-09-01 · EMNLP 2017 9 · Tobias Horsmann, Torsten Zesch

A recent study by Plank et al. (2016) found that LSTM-based PoS taggers considerably improve over the current state-of-the-art when evaluated on the corpora of the Universal Dependencies project that use a coarse-grained tagset. We replicate this study using a fresh collection of 27 corpora of 21 languages that are annotated with fine-grained tagsets of varying size. Our replication confirms the result in general, and we additionally find that the advantage of LSTMs is even bigger for larger tagsets. However, we also find that for the very large tagsets of morphologically rich languages, hand-crafted morphological lexicons are still necessary to reach state-of-the-art performance.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Feature Engineering Part-Of-Speech TaggingPOSPOS Tagging

Multilingual Part-of-Speech Tagging with Bidirectional Long Short-Term Memory Models and Auxiliary Loss

2016-04-19 · ACL 2016 8 · Barbara Plank, Anders Søgaard, Yoav Goldberg

Bidirectional long short-term memory (bi-LSTM) networks have recently proven successful for various NLP sequence modeling tasks, but little is known about their reliance to input representations, target languages, data s…

Part-Of-Speech Tagging POS POS Tagging

Supertagging With LSTMs

2016-06-01 · NAACL 2016 6 · Ashish Vaswani, Yonatan Bisk, Kenji Sagae, Ryan Musa

CCG Supertagging Part-Of-Speech Tagging Semantic Parsing

An Empirical Exploration of Skip Connections for Sequential Tagging

2016-10-11 · COLING 2016 12 · Huijia Wu, Jiajun Zhang, Cheng-qing Zong

In this paper, we empirically explore the effects of various kinds of skip connections in stacked bidirectional LSTMs for sequential tagging. We investigate three kinds of skip connections connecting to LSTM cells: (a) s…

CCG Supertagging POS POS Tagging

LSTM Hypertagging

2018-11-01 · WS 2018 11 · Reid Fu, Michael White

Hypertagging, or supertagging for surface realization, is the process of assigning lexical categories to nodes in an input semantic graph. Previous work has shown that hypertagging significantly increases realization spe…

Text Generation

On Evaluation Validity in Music Autotagging

2014-09-30 · Fabien Gouyon, Bob L. Sturm, Joao Lobato Oliveira, Nuno Hespanhol 외

Music autotagging, an established problem in Music Information Retrieval, aims to alleviate the human cost required to manually annotate collections of recorded music with textual labels by automating the process. Many a…

Information Retrieval Music Information Retrieval