321 |
Applying N-gram Alignment Entropy to Improve Feature Decay Algorithms
|
|
|
|
In: Prague Bulletin of Mathematical Linguistics , Vol 108, Iss 1, Pp 245-256 (2017) (2017)
|
|
BASE
|
|
Show details
|
|
322 |
Comparative Human and Automatic Evaluation of Glass-Box and Black-Box Approaches to Interactive Translation Prediction
|
|
|
|
In: Prague Bulletin of Mathematical Linguistics , Vol 108, Iss 1, Pp 97-108 (2017) (2017)
|
|
BASE
|
|
Show details
|
|
323 |
Historical Documents Modernization
|
|
|
|
In: Prague Bulletin of Mathematical Linguistics , Vol 108, Iss 1, Pp 295-306 (2017) (2017)
|
|
BASE
|
|
Show details
|
|
324 |
Maintaining Sentiment Polarity in Translation of User-Generated Content
|
|
|
|
In: Prague Bulletin of Mathematical Linguistics , Vol 108, Iss 1, Pp 73-84 (2017) (2017)
|
|
Abstract:
The advent of social media has shaken the very foundations of how we share information, with Twitter, Facebook, and Linkedin among many well-known social networking platforms that facilitate information generation and distribution. However, the maximum 140-character restriction in Twitter encourages users to (sometimes deliberately) write somewhat informally in most cases. As a result, machine translation (MT) of user-generated content (UGC) becomes much more difficult for such noisy texts. In addition to translation quality being affected, this phenomenon may also negatively impact sentiment preservation in the translation process. That is, a sentence with positive sentiment in the source language may be translated into a sentence with negative or neutral sentiment in the target language. In this paper, we analyse both sentiment preservation and MT quality per se in the context of UGC, focusing especially on whether sentiment classification helps improve sentiment preservation in MT of UGC. We build four different experimental setups for tweet translation (i) using a single MT model trained on the whole Twitter parallel corpus, (ii) using multiple MT models based on sentiment classification, (iii) using MT models including additional out-of-domain data, and (iv) adding MT models based on the phrase-table fill-up method to accompany the sentiment translation models with an aim of improving MT quality and at the same time maintaining sentiment polarity preservation. Our empirical evaluation shows that despite a slight deterioration in MT quality, our system significantly outperforms the Baseline MT system (without using sentiment classification) in terms of sentiment preservation. We also demonstrate that using an MT engine that conveys a sentiment different from that of the UGC can even worsen both the translation quality and sentiment preservation.
|
|
Keyword:
Computational linguistics. Natural language processing; P98-98.5
|
|
URL: https://doaj.org/article/e0f59b17b6224cb18d537c99ffa4bde7 https://doi.org/10.1515/pralin-2017-0010
|
|
BASE
|
|
Hide details
|
|
325 |
Is Neural Machine Translation the New State of the Art?
|
|
|
|
In: Prague Bulletin of Mathematical Linguistics , Vol 108, Iss 1, Pp 109-120 (2017) (2017)
|
|
BASE
|
|
Show details
|
|
326 |
Linguistically Motivated Vocabulary Reduction for Neural Machine Translation from Turkish to English
|
|
|
|
In: Prague Bulletin of Mathematical Linguistics , Vol 108, Iss 1, Pp 331-342 (2017) (2017)
|
|
BASE
|
|
Show details
|
|
327 |
Learning Morphological Normalization for Translation from and into Morphologically Rich Languages
|
|
|
|
In: Prague Bulletin of Mathematical Linguistics , Vol 108, Iss 1, Pp 49-60 (2017) (2017)
|
|
BASE
|
|
Show details
|
|
328 |
Continuous Learning from Human Post-Edits for Neural Machine Translation
|
|
|
|
In: Prague Bulletin of Mathematical Linguistics , Vol 108, Iss 1, Pp 233-244 (2017) (2017)
|
|
BASE
|
|
Show details
|
|
329 |
Fine-Grained Human Evaluation of Neural Versus Phrase-Based Machine Translation
|
|
|
|
In: Prague Bulletin of Mathematical Linguistics , Vol 108, Iss 1, Pp 121-132 (2017) (2017)
|
|
BASE
|
|
Show details
|
|
330 |
A Neural Network Architecture for Detecting Grammatical Errors in Statistical Machine Translation
|
|
|
|
In: Prague Bulletin of Mathematical Linguistics , Vol 108, Iss 1, Pp 133-145 (2017) (2017)
|
|
BASE
|
|
Show details
|
|
331 |
A Linguistic Evaluation of Rule-Based, Phrase-Based, and Neural MT Engines
|
|
|
|
In: Prague Bulletin of Mathematical Linguistics , Vol 108, Iss 1, Pp 159-170 (2017) (2017)
|
|
BASE
|
|
Show details
|
|
332 |
Neural Networks Classifier for Data Selection in Statistical Machine Translation
|
|
|
|
In: Prague Bulletin of Mathematical Linguistics , Vol 108, Iss 1, Pp 283-294 (2017) (2017)
|
|
BASE
|
|
Show details
|
|
333 |
Empirical Investigation of Optimization Algorithms in Neural Machine Translation
|
|
|
|
In: Prague Bulletin of Mathematical Linguistics , Vol 108, Iss 1, Pp 13-25 (2017) (2017)
|
|
BASE
|
|
Show details
|
|
334 |
Parallelization of Neural Network Training for NLP with Hogwild!
|
|
|
|
In: Prague Bulletin of Mathematical Linguistics , Vol 109, Iss 1, Pp 29-38 (2017) (2017)
|
|
BASE
|
|
Show details
|
|
335 |
Neural Monkey: An Open-source Tool for Sequence Learning
|
|
|
|
In: Prague Bulletin of Mathematical Linguistics , Vol 107, Iss 1, Pp 5-17 (2017) (2017)
|
|
BASE
|
|
Show details
|
|
336 |
Difference between Written and Spoken Czech: The Case of Verbal Nouns Denoting an Action
|
|
|
|
In: Prague Bulletin of Mathematical Linguistics , Vol 107, Iss 1, Pp 19-38 (2017) (2017)
|
|
BASE
|
|
Show details
|
|
337 |
Comparative Quality Estimation for Machine Translation Observations on Machine Learning and Features
|
|
|
|
In: Prague Bulletin of Mathematical Linguistics , Vol 108, Iss 1, Pp 307-318 (2017) (2017)
|
|
BASE
|
|
Show details
|
|
338 |
Learnability and falsifiability of Construction Grammars
|
|
|
|
In: Proceedings of the Linguistic Society of America; Vol 2 (2017): Proceedings of the Linguistic Society of America; 1:1–15 ; 2473-8689 (2017)
|
|
BASE
|
|
Show details
|
|
339 |
Variation in the pronunciation/silence of the prepositions in locative determiners
|
|
|
|
In: Proceedings of the Linguistic Society of America; Vol 2 (2017): Proceedings of the Linguistic Society of America; 22:1–15 ; 2473-8689 (2017)
|
|
BASE
|
|
Show details
|
|
|
|