Unsupervised Multilingual Sentence Boundary Detection

By Tibor Kiss, Jan Strunk. International Conference on Computational Logic, 2006

512 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/b6833a3be8ba09f04debe1fd23bf48d29575590a

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

Citations in the corpus

The Multilingual TEDx Corpus for Speech Recognition and Translation (2021, methodology): “We disallow this behavior on the source side, maintaining parallel Punkt-generated sentences across ASR and MT data for the same source talk.”
Self-Training for End-to-End Speech Recognition (2019, methodology): “First, we detect sentence boundaries using the “punkt” tokenizer [12] implemented in NLTK [13].”
Legal Information Retrieval with Generalized Language Models (2019, unknown): “By design, WordPiece will subdivide each token into multiple tokens, we consider in our preparation that this will double the number of tokens observed under a standard Punkt[6] tokenizer as implemented in NLTK[2].”
A Scalable Global Model for Summarization (2009, unknown): “We use the unsupervised Punkt system (Kiss and Strunk, 2006).”
Information Extraction over Structured Data: Question Answering with Freebase (2014, methodology): “We split each HTML document by sentences (Kiss and Strunk, 2006) using NLTK (Bird and Loper, 2004) and extracted those with at least two Freebase entities which has at least one direct established relation according to Freebase.”
Learning multilingual named entity recognition from Wikipedia (2013, methodology): “For each language, this list consists of frequent sentence starters from our sentence boundary detection models [33], and a list of words which occurred at least 50 times lowercase, and at least 50 times sentence-initially, in 100,000 Wikipedia articles.”
Opinion Mining and Information Fusion: A survey (2016, methodology): “Sentence Segmentation: procedure for separating paragraphs into sentences [38].”
Topic Modeling in Management Research: Rendering New Theory from Textual Data (2019, methodology): “, researchers have developed NLP methods to determine sentence boundaries in a common task called sentence segmentation (Kiss & Strunk, 2006).”
Depression and Self-Harm Risk Assessment in Online Forums (2017, methodology): “Sentence boundary detection was performed using the Punkt sentence tokenizer (Kiss and Strunk, 2006) available in NLTK (Bird et al., 2009).”
Interpretese vs. Translationese: The Uniqueness of Human Strategies in Simultaneous Interpretation (2016, methodology): “Segmentation: We use the punkt sentence seg-menter (Kiss and Strunk, 2006) from NLTK to detect sentences in a text chunk.”