Lexical Normalisation of Short Text Messages: Makn Sens a #twitter

By Bo Han, Timothy Baldwin. Annual Meeting of the Association for Computational Linguistics, 2011

575 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/3de7ef76a010e624b47255b93bffa1a7c48e35a9

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

TwiNER: named entity recognition in targeted twitter stream (2012, background): “Also acknowledging the error-prone nature of tweets, Han and Baldwin [6] proposed to normalize illformed words in tweets to make the contents more formal.”
What to do about bad language on the internet (2013, methodology): “Approaches to normalization include the noisy-channel model (Cook and Stevenson, 2009), string and distributional similarity (Han and Baldwin, 2011; Han et al., 2012), sequence labeling (Choudhury et al.”
Robust Training under Linguistic Adversity (2017, background): “…and microblogs, humans are remarkably resilient to “noise”, in terms of typos, lexical and syntactic disﬂuencies, and the large variety of semantically-equivalent ways of expressing the same content (Han and Baldwin, 2011; Eisenstein, 2013; Baldwin et al., 2013; Pavlick and Callison-Burch, 2016).”
On learning and representing social meaning in NLP: a sociolinguistic perspective (2021, background): “(Han and Baldwin, 2011; Liu et al., 2011).”
Named Entity Recognition in Tweets: An Experimental Study (2011, background): “Recent work (Han and Baldwin, 2011; Gouws et al., 2011) has proposed lexical normalization of tweets which may be useful as a preprocessing step for the upstream tasks like POS tagging and”
Exponential Reservoir Sampling for Streaming Language Models (2014, methodology): “We expect that our language model could improve other Social Media tasks, for example lexical normalisation (Han and Baldwin, 2011) or even event detection (Lin et al., 2011).”
Normalizing tweets with edit scripts and recurrent neural embeddings (2014, methodology): “…2 fxckin fucking 2 dha the 2 de the 2 d the 2 bhee be 2 bb baby Gouws et al. (2011); S-dict is the automatically constructed dictionary from (Han et al., 2012); Dict-combo are all the dictionaries combined and Dict-combo+HB-norm are all dictionaries combined with approach of Han and Baldwin (2011).”
Analysis of named entity recognition and linking for tweets (2014, methodology): “Information gainbased langid.py (Lui & Baldwin, 2012) uses n-grams to learn a multinomial event model, with a feature selection process designed to cope with variations of expression between text domains.”
TweetEval: Unified Benchmark and Comparative Evaluation for Tweet Classification (2020, background): “…platform-speciﬁc restrictions (e.g., Twitter’s character limit), requires tackling additional challenges, for example, POS tagging (Derczynski et al., 2013), lexical normalization (Han and Baldwin, 2011; Baldwin et al., 2015), or named entity recognition (Ritter et al., 2011; Baldwin et al., 2013).”
Improved Part-of-Speech Tagging for Online Conversational Text with Word Clusters (2013, background): “We do not attempt to do Twitter “normalization” into traditional written English (Han and Baldwin, 2011), which we view as a lossy translation task.”