Part-of-speech tagging

Summary

In corpus linguistics, part-of-speech tagging (POS tagging or PoS tagging or POST), also called grammatical tagging is the process of marking up a word in a text (corpus) as corresponding to a particular part of speech, based on both its definition and its context. A simplified form of this is commonly taught to school-age children, in the identification of words as nouns, verbs, adjectives, adverbs, etc. Once performed by hand, POS tagging is now done in the context of computational linguistics, using algorithms which associate discrete terms, as well as hidden parts of speech, by a set of descriptive tags. POS-tagging algorithms fall into two distinctive groups: rule-based and stochastic. E. Brill's tagger, one of the first and most widely used English POS-taggers, employs rule-based algorithms. Principle Part-of-speech tagging is harder than just having a list of words and their parts of speech, because some words can represent more than one part of speech at different

Official source

https://en.wikipedia.org/wiki/Part-of-speech_tagging

About this result

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Related publications (22)

Related publications

Related people (3)

, ,

Related people

Related units (1)

Related units

Related concepts (12)

Related concepts

Related courses (5)

The objective of this course is to present the main models, formalisms and algorithms necessary for the development of applications in the field of natural language information processing. The concepts introduced during the lectures will be applied during practical sessions.

This course introduces the key concepts and algorithms from the areas of information retrieval, data mining and knowledge bases, which constitute the foundations of today's Web-based distributed information systems.

The Deep Learning for NLP course provides an overview of neural network based methods applied to text. The focus is on models particularly suited to the properties of human language, such as categorical, unbounded, and structured representations, and very large input and output vocabularies.

Related courses

Related lectures (20)

Related lectures

, , , , , , ,

The aggregation-induced emission properties of tetraarylethenes (TAEs) have led to numerous applications in chemistry, biology, and materials science. Herein, we describe two fluorinated tetraarylethenes, which can be employed as universal tags for the synthesis of solid state luminogens. The tags are accessible in one or two steps from commercially available starting materials. Facile coupling reactions with ubiquitous substrates such as thiols, alcohols, amines, phosphines, aldehydes, and enamines allow preparing a wide range of TAE conjugates, including tagged amino acids, peptides, carbohydrates, steroids, and commercial polymers.

2022

Interpreting Language Models Through Knowledge Graph Extraction

Martin Jaggi, Angeliki Romanou, Vinitra Swamy

Transformer-based language models trained on large text corpora have enjoyed immense popularity in the natural language processing community and are commonly used as a starting point for downstream tasks. While these models are undeniably useful, it is a challenge to quantify their performance beyond traditional accuracy metrics. In this paper, we compare BERT-based language models through snapshots of acquired knowledge at sequential stages of the training process. Structured relationships from training corpora may be uncovered through querying a masked language model with probing tasks. We present a methodology to unveil a knowledge acquisition timeline by generating knowledge graph extracts from cloze "fill-in-the-blank" statements at various stages of RoBERTa's early training. We extend this analysis to a comparison of pretrained variations of BERT models (DistilBERT, BERT-base, RoBERTa). This work proposes a quantitative framework to compare language models through knowledge graph extraction (GED, Graph2Vec) and showcases a part-of-speech analysis (POSOR) to identify the linguistic strengths of each model variant. Using these metrics, machine learning practitioners can compare models, diagnose their models' behavioral strengths and weaknesses, and identify new targeted datasets to improve model performance.

2021

Detecting Trends in Job Advertisements

Pierre Dillenbourg, Khalil Mrini, Kshitij Sharma

We present an automatic method for trend detection in job ads. From a job-posting website, we collect job ads from 16 countries and in 8 languages and 6 job domains. We pre-process them by removing stop words, lemmatising and performing cross-domain filtering. Then, we improve the vocabulary by forming n-grams and restrict it by filtering based on named-entity and part-of-speech tags. We split the job ads to compare two time periods: the first halves of 2016 and 2017. A trending word is defined as a word with a higher TF-IDF weight in 2017 than in 2016. The results obtained show a close correlation between the position of a word in its text and its trendiness regardless of country, language or job domain.

2017