Flexible Text Segmentation with Structured Multilabel Classification

By Ryan T. McDonald, Koby Crammer, Fernando C Pereira. 2005

100 citations recorded by the source corpus.

Many language processing tasks can be reduced to breaking the text into segments with prescribed properties. Such tasks include sentence splitting, tokenization, named-entity extraction, and chunking. We present a new model of text segmentation based on ideas from multilabel classification. Using this model, we can naturally represent segmentation problems involving overlapping and non-contiguous segments. We evaluate the model on entity extraction and noun-phrase chunking and show that it is more accurate for overlapping and non-contiguous segments, but it still performs well on simpler data sets for which sequential tagging has been the best method.

Subfields: Artificial Intelligence, Natural Language Processing, Information Extraction

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

In Information Extraction

Citations in the corpus

Natural Language Processing (Almost) from Scratch (2011, background): “Since then, a certain number of systems based on second-order random fields were reported (Sha and Pereira, 2003; McDonald et al., 2005; Sun et al., 2008), all reporting around 94.3% F1 score.”
Domain Adaptation with Structural Correspondence Learning (2006, methodology): “MIRA has been used successfully for both sequence analysis (McDonald et al., 2005a) and dependency parsing (McDonald et al., 2005b).”
Bidirectional LSTM-CRF Models for Sequence Tagging (2015, neutral): “…2001) 93.91 Second order CRF (Sha and Pereira, 2003) 94.30 Specialized HMM + voting scheme (Shen and Sarkar, 2005) 95.23 Second order CRF (Mcdonald et al., 2005) 94.29 Second order CRF (Sun et al., 2008) 94.34 Conv-CRF (Collobert et al., 2011) 90.33 Conv network tagger (senna) (Collobert…”
Global inference for sentence compression : an integer linear programming approach (2008, methodology): “The algorithm is an extension of Viterbi for the case in which scores factor over dynamic sub-strings (Sarawagi & Cohen, 2004; McDonald, Crammer, & Pereira, 2005a ).”
Natural language processing: state of the art, current trends and challenges (2017, methodology): “, 2008) [83, 122, 130] used CoNLL test data for chunking and used features composed of words, POS tags, and tags.”
Nested Named Entity Recognition (2009, methodology): “When evaluating onall entities our model does well, with F-scores ranging from slightly worse than performance on top-level only, to substantially better than top-level only.”
Database-Text Alignment via Structured Multilabel Classification (2007, background): “…on developing local ranking models aiming to minimize the number of incorrect labels predicted above correct ones, often ignoring threshold selection or treating it as a secondary concern [Elisseeff and Weston, 2001; Crammer and Singer, 2002; McDonald et al., 2005; Schapire and Singer, 1999].”
Modeling Latent-Dynamic in Shallow Parsing: A Latent Conditional Model with Improved Inference (2008, methodology): “As for the task of shallow parsing, CRFs also outperform many other state-of-the-art models (Sha & Pereira 2003; McDonald et al. 2005).”
Online Learning of Approximate Dependency Parsing Algorithms (2006, methodology): “By defining a graph in which the words in a sentence are the vertices and there is a directed edge between all words with a score as calculated above, McDonald et al. (2005c) showed that dependency parsing is equivalent to finding the MST in this graph.”