Semi-Supervised Sequential Labeling and Segmentation Using Giga-Word Scale Unlabeled Data

By Jun Suzuki, Hideki Isozaki. 2008

154 citations recorded by the source corpus.

Subfields: Natural Language Processing, Representation & Self-Supervised Learning

How researchers see this paper

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

In Natural Language Processing

In Representation & Self-Supervised Learning

Citations in the corpus

Semi-supervised sequence tagging with bidirectional language models (2017, background): “, 2000; Mohit and Hwa, 2005), structural learning (Ando and Zhang, 2005) and maximum discriminant functions (Suzuki et al., 2007; Suzuki and Isozaki, 2008).”
Natural Language Processing (Almost) from Scratch (2011, neutral): “• Parameter sharing approaches such as (Ando and Zhang, 2005; Suzuki and Isozaki, 2008).”
Deep multi-task learning with low level tasks supervised at lower layers (2016, background): “Suzuki and Isozaki (2008), for example, reported an F 1 -score of 95.15% on the C HUNKS data.”
Lexicon Infused Phrase Embeddings for Named Entity Resolution (2014, background): “Many different neural language models have been proposed (Bengio et al., 2003; Morin and Bengio, 2005; Bengio, 2008; Mnih and Hinton, 2008; Collobert and Weston, 2008; Mikolov et al., 2010).”
Design Challenges and Misconceptions in Named Entity Recognition (2009, background): “Recent successful semi-supervised systems (Ando and Zhang, 2005; Suzuki and Isozaki, 2008) have illustrated that unlabeled text can be used to improve the performance of NER systems.”
Sequence Classification Restricted Boltzmann Machines With Gated Units (2020, methodology): “The results of the experiments as well as the state-of-the-art results reported in [41], [17], [42], [43], [44], are shown in Table II.”
Open-Source Tools for Morphology, Lemmatization, POS Tagging and Named Entity Recognition (2014, unknown): “For example, the systems which published high scores on the CoNLL-2003 task include (Suzuki and Isozaki, 2008), (Ando and Zhang, 2005) and to our knowledge, the best currently known results on this dataset were published by (Ratinov and Roth, 2009).”
Phrase Clustering for Discriminative Learning (2009, methodology): “Suzuki and Isozaki (2008), on the other hand, used the automatically labeled corpus to train HMMs. Ando and Zhang (2005) defined an objective function that combines the original problem on the labeled data with a set of auxiliary problems on unlabeled data.”
Recognizing Named Entities in Tweets (2011, background): “Suzuki and Isozaki (2008) is one such example.”
Learning multilingual named entity recognition from Wikipedia (2013, background): “, 2009; Liao and Veeramachaneni, 2009); jointly modelling labelled and unlabelled (Suzuki and Isozaki, 2008) or partially-labelled (Fernandes and Brefeld, 2011) language; or induced word class features (Kazama and Torisawa, 2008; Ratinov and Roth, 2009).”
Strong Baselines for Neural Semi-Supervised Learning under Domain Shift (2018, background): “In parsing it proved successful only with small datasets (Reichart and Rappoport, 2007) or when a generative component is used together with a reranker in high-data conditions (McClosky et al., 2006b; Suzuki and Isozaki, 2008).”
Word Representations: A Simple and General Method for Semi-Supervised Learning (2010, methodology): “We apply clustering and distributed representations to NER and chunking, which allows us to compare our semi-supervised models to those of Ando and Zhang (2005) and Suzuki and Isozaki (2008).”
Generalized Expectation Criteria for Semi-Supervised Learning with Weakly Labeled Data (2010, methodology): “Another twist on this technique is to blend generative and discriminative models, by combining ML estimates over the labeled data with EM parameter estimates over the unlabeled data, for a joint model which combines a CRF and a HMM (Suzuki et al., 2007; Suzuki and Isozaki, 2008).”
Improving Language Understanding by Generative Pre-Training (2018, methodology): “This paradigm has attracted signiﬁcant interest, with applications to tasks like sequence labeling [24, 33, 57] or text classiﬁcation [41, 70].”
Practical Very Large Scale CRFs (2010, background): “test) data, which compares favorably with some of the best results for this task (for instance (Toutanova et al., 2003; Shen et al., 2007; Suzuki and Isozaki, 2008)).”