A comprehensive survey on word representation models: From classical to state-of-the-art word representation language models
Word representation has always been an important research area in the history of natural
language processing (NLP). Understanding such complex text data is imperative, given that …
language processing (NLP). Understanding such complex text data is imperative, given that …
[PDF][PDF] What to do about bad language on the internet
J Eisenstein - Proceedings of the 2013 conference of the North …, 2013 - aclanthology.org
The rise of social media has brought computational linguistics in ever-closer contact with
bad language: text that defies our expectations about vocabulary, spelling, and syntax. This …
bad language: text that defies our expectations about vocabulary, spelling, and syntax. This …
Argumentation mining in user-generated web discourse
I Habernal, I Gurevych - Computational linguistics, 2017 - direct.mit.edu
The goal of argumentation mining, an evolving research field in computational linguistics, is
to design methods capable of analyzing people's argumentation. In this article, we go …
to design methods capable of analyzing people's argumentation. In this article, we go …
[图书][B] Natural language processing for social media
A Farzindar, D Inkpen, G Hirst - 2015 - Springer
In recent years, online social networking has revolutionized interpersonal communication.
The newer research on language analysis in social media has been increasingly focusing …
The newer research on language analysis in social media has been increasingly focusing …
[PDF][PDF] How noisy social media text, how diffrnt social media sources?
While various claims have been made about text in social media text being noisy, there has
never been a systematic study to investigate just how linguistically noisy or otherwise it is …
never been a systematic study to investigate just how linguistically noisy or otherwise it is …
A dependency parser for tweets
© 2014 Association for Computational Linguistics. We describe a new dependency parser
for English tweets, TWEEBOPARSER. The parser builds on several contributions: new …
for English tweets, TWEEBOPARSER. The parser builds on several contributions: new …
What to do about non-standard (or non-canonical) language in NLP
B Plank - arXiv preprint arXiv:1608.07836, 2016 - arxiv.org
Real world data differs radically from the benchmark corpora we use in natural language
processing (NLP). As soon as we apply our technologies to the real world, performance …
processing (NLP). As soon as we apply our technologies to the real world, performance …
[HTML][HTML] Building the essential resources for Finnish: the Turku Dependency Treebank
K Haverinen, J Nyblom, T Viljanen, V Laippala… - Language Resources …, 2014 - Springer
In this paper, we present the final version of a publicly available treebank of Finnish, the
Turku Dependency Treebank. The treebank contains 204,399 tokens (15,126 sentences) …
Turku Dependency Treebank. The treebank contains 204,399 tokens (15,126 sentences) …
Systematic patterning in phonologically‐motivated orthographic variation
J Eisenstein - Journal of Sociolinguistics, 2015 - Wiley Online Library
Social media features a wide range of non‐standard spellings, many of which appear
inspired by phonological variation. However, the nature of the connection between variation …
inspired by phonological variation. However, the nature of the connection between variation …
[PDF][PDF] Learning part-of-speech taggers with inter-annotator agreement loss
In natural language processing (NLP) annotation projects, we use inter-annotator
agreement measures and annotation guidelines to ensure consistent annotations. However …
agreement measures and annotation guidelines to ensure consistent annotations. However …