Semi-Supervised Learning for Natural Language

By Percy Liang. 2005

362 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

Natural Language Processing (Almost) from Scratch (2011, methodology): “In that respect, these convex experiments show the performance of our word embeddings in a classical NLP framework. ar Xi v Following the Ratinov and Roth (2009) and Koo et al. (2008) setups, we generated 1, 000 Brown clusters using the implementation17 from Liang (2005).”
Semi-supervised Learning with Deep Generative Models (2014, background): “…interest in a wide range of applications, including image search (Fergus et al., 2009), genomics (Shi and Zhang, 2011), natural language parsing (Liang, 2005), and speech analysis (Liu and Kirchhoff, 2013), where unlabelled data is abundant, but obtaining class labels is expensive or impossible…”
Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfaces (2018, background): “The problem of data sparsity is addressed by integrating features based on word clusters [27].”
Design Challenges and Misconceptions in Named Entity Recognition (2009, methodology): “In this work, we use the implementation and the clusters obtained in (Liang, 2005) from running the algorithm on the Reuters 1996 dataset, a superset of the CoNLL03 NER dataset.”
Let’s Make Your Request More Persuasive: Modeling Persuasive Strategies via Semi-Supervised Neural Nets on Crowdfunding Platforms (2019, methodology): “While in computer vision, there is a lot of prior work in using image global labels to uncover local pixel level labels and bounding boxes of objects (Oquab et al., 2015; Pinheiro and Collobert, 2015), the investigation of this task in NLP, to the best of our knowledge, is novel and could potentiall”
Pragmatic Neural Language Modelling in Machine Translation (2014, background): “We believe this is likely to be a result of the artiﬁcial hierarchy imposed by the tree over the vocabulary. et al., 1992; Liang, 2005) and frequency binning (Mikolov et al., 2011b).”
Joint POS Tagging and Transition-based Constituent Parsing in Chinese with Non-local Features (2014, methodology): “Given a large-scale unlabeled corpus (word segmentation should be performed), we employ the Brown cluster al-gorithm (Liang, 2005) to cluster all words into a binary tree.”
Word Representations: A Simple and General Method for Semi-Supervised Learning (2010, methodology): “This technique was used by a variety of researchers (Miller et al., 2004; Liang, 2005; Koo et al., 2008; Ratinov & Roth, 2009; Huang & Yates, 2009).”
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].”
A Systematic Exploration of Diversity in Machine Translation (2013, methodology): “Word Cluster LMs (WCLM): Using an implementation provided by Liang (2005), we performed Brown clustering (Brown et al., 1992) on 900k English sentences, including the NC corpus and random sentences from Gigaword.”
Fine-Grained Entity Recognition (2012, methodology): “We used Liang (2005)'s implementation to induce the word clusters.”
Improved Part-of-Speech Tagging for Online Conversational Text with Word Clusters (2013, neutral): “As implemented by Liang (2005), v.”
Phrase Dependency Machine Translation with Quasi-Synchronous Tree-to-Tree Features (2014, methodology): “Brown clusters (Brown et al. 1992) were generated using code provided by Liang (2005).”
Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing (2020, methodology): “hus a long-standing direction for alleviating the annotation bottleneck using transfer learning. Early methods focused on clustering related words using distributed similarity, such as Brown Clusters [12, 35]. With the revival of neural approaches, neural embedding has become the new staple for tran”
Bidirectional Helmholtz Machines (2015, background): “Semi-supervised learning is very useful in a variety of applications and it is needed in a broad range of problems that are of interest such as image search, genomics, natural language parsing, and speech analysis [29, 64, 65, 95].”
Simple Semi-supervised Dependency Parsing (2008, methodology): “We chose to work with the Brown algorithm due to its simplicity and prior success in other NLP applications (Miller et al., 2004; Liang, 2005).”