Book Review: Natural Language Processing with Python by Steven Bird, Ewan Klein, and Edward Loper

By Michael Elhadad. 2009

1,598 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

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

In Artificial Intelligence

In Natural Language Processing

Citations in the corpus

Beyond CCA: Moment Matching for Multi-View Models (2016, methodology): “For stemming, the SnowballStemmer of the NLTK toolbox by Bird et al. (2009) was used for both English and French languages.”
Neural Approaches to Conversational AI (2018, neutral): “nt responses user engagement, measured in CPS top-level bot understanding of user top-level intent options user engagement, measured in CPS Figure 1.3: Traditional NLP Component Stack. Figure credit: Bird et al. (2009). continue improving it. In the paper, we will survey these ML approaches and thei”
Automated Hate Speech Detection and the Problem of Offensive Language (2017, methodology): “We then test a variety of models that have been used in prior work: logistic regression, na¨ıve Bayes, decision trees, random forests, and linear SVMs.”
A Dataset and Exploration of Models for Understanding Video Data through Fill-in-the-Blank Question-Answering (2016, methodology): “ields results that correspond well with human assessment. 5.1. Experimental Settings 5.1.1 Text Preprocessing We preprocess the questions and the answer with wordpunct tokenizer from the NLTK toolbox [2]. We then lowercase Table 2. Fill-in-the-blank accuracy results for single models and estimated h”
Explicit Knowledge-based Reasoning for Visual Question Answering (2015, methodology): “eve this Quepy requires a set of templates, framed in terms of regular expressions. It is these templates which form the basis of Table 1. Quepy begins by tagging each word in the question using NLTK [5], which is composed of a tokenizer, a part-of-speech tagger and a lemmatizer. The tagged question”
Women through the glass ceiling: gender asymmetries in Wikipedia (2016, background): “[6] Steven Bird, Ewan Klein, and Edward Loper.”
Mining Discourse Markers for Unsupervised Sentence Representation Learning (2019, methodology): “Some markers are missing because of NLTK errors, which mainly result from morphological issues.3”
FeatureInsight: Visual support for error-driven feature ideation in text classification (2015, background): “Although there are many requirements for ML systems (e.g., high quality data, appropriate model choice, parameter tuning), both researchers [1], [2], [3], [4] and practitioners [5], [6] recognize feature engineering as crucial to the machine learning process.”
Opinion Mining and Information Fusion: A survey (2016, background): “This step presents its own challenges since periods are often used to mark the ending of a sentence but also to denote abbreviations and decimal numbers [39].”
Characterizing long COVID in an international cohort: 7 months of symptoms and their impact (2020, neutral): “Participants answered the Fatigue Assessment Scale (FAS) questionnaire [21,22], which includes10 questions that assess both physical and mental fatigue.”
A Bayesian Model of Diachronic Meaning Change (2016, methodology): “We tokenized, lemmatized, and part of speech tagged DATE using the NLTK (Bird et al., 2009).”
Artificial error generation for translation-based grammatical error correction (2016, methodology): “Sentence segmentation, tokenisation and PoS tagging were carried out using NLTK (Bird et al., 2009) for consistency with the CoNLL shared task data, which means that the extracted PoS patterns use the Penn Treebank tagset2 (see Appendix D).”
Discover and Learn New Objects from Documentaries (2017, methodology): “To identify them, we apply Part-Of-Speech (POS) tagging using a parser [4].”