1 |
Unsupervised Translation of German--Lower Sorbian: Exploring Training and Novel Transfer Methods on a Low-Resource Language ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
On the Effectiveness of Dataset Embeddings in Mono-lingual,Multi-lingual and Zero-shot Conditions ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Multilingual Unsupervised Neural Machine Translation with Denoising Adapters ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Multilingual Unsupervised Neural Machine Translation with Denoising Adapters ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
From Masked Language Modeling to Translation: Non-English Auxiliary Tasks Improve Zero-shot Spoken Language Understanding ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
On the Difficulty of Translating Free-Order Case-Marking Languages ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
UDapter: Language Adaptation for Truly Universal Dependency Parsing ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Incorporating word embeddings in unsupervised morphological segmentation
|
|
|
|
In: 2020 ; 1 ; 21 (2020)
|
|
BASE
|
|
Show details
|
|
10 |
Characters or morphemes: how to represent words?
|
|
|
|
Abstract:
© 2018 The Authors. Published by Association for Computational Linguistics. This is an open access article available under a Creative Commons licence. The published version can be accessed at the following link on the publisher’s website: http://dx.doi.org/10.18653/v1/W18-3019 ; In this paper, we investigate the effects of using subword information in representation learning. We argue that using syntactic subword units effects the quality of the word representations positively. We introduce a morpheme-based model and compare it against to word-based, character-based, and character n-gram level models. Our model takes a list of candidate segmentations of a word and learns the representation of the word based on different segmentations that are weighted by an attention mechanism. We performed experiments on Turkish as a morphologically rich language and English with a comparably poorer morphology. The results show that morpheme-based models are better at learning word representations of morphologically complex languages compared to character-based and character n-gram level models since the morphemes help to incorporate more syntactic knowledge in learning, that makes morpheme-based models better at syntactic tasks. ; This research was supported by TUBITAK (The Scientific and Technological Research Council of Turkey) grant number 115E464. ; Published version
|
|
URL: http://hdl.handle.net/2436/623576 https://doi.org/10.18653/v1/w18-3019
|
|
BASE
|
|
Hide details
|
|
11 |
A Trie-Structured Bayesian Model for Unsupervised Morphological Segmentation ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Turkish PoS Tagging by Reducing Sparsity with Morpheme Tags in Small Datasets ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|