Importance of Semantic Representation: Dataless Classification

By Ming-Wei Chang, Lev-Arie Ratinov, Dan Roth, Vivek Srikumar. 2008

337 citations recorded by the source corpus.

How researchers see this paper

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

Citations in the corpus

Subspace Regularizers for Few-Shot Class Incremental Learning (2021, background): “…et al., 2021; Reed et al., 2016; Yan et al., 2021)—particularly in the zero-shot learning and generalized zero-shot learning where side information is the only source of information about the novel class (Chang et al., 2008; Larochelle et al., 2008; Akata et al., 2013; Pourpanah et al., 2020).”
Learning from Task Descriptions (2020, background): “Zero-shot learning (Chang et al., 2008; Socher et al., 2013; Norouzi et al., 2013) asks systems to generalize to unseen classes at test time.”
Benchmarking Zero-shot Text Classification: Datasets, Evaluation and Entailment Approach (2019, background): “• ESA : A dataless classiﬁer proposed in (Chang et al., 2008).”
MixText: Linguistically-Informed Interpolation of Hidden Space for Semi-Supervised Text Classification (2020, neutral): “Answers (Chang et al., 2008) and IMDB (Maas et al., 2011).”
An Empirical Survey of Data Augmentation for Limited Data Learning in NLP (2021, background): “, 2015b) and 20 News Group (Joachims, 1997)), topic classification (Yahoo Answer (Chang et al., 2008) and Pubmed (Dernoncourt and Lee, 2017)), and the GLUE meta-benchmark (Wang et al.”
Local and Global Algorithms for Disambiguation to Wikipedia (2011, background): “Recently, Wikification has been shown to form a valuable component for numerous natural language processing tasks including text classification (Gabrilovich and Markovitch, 2007b; Chang et al., 2008), measuring semantic similarity between texts (Gabrilovich and Markovitch, 2007a), crossdocument co-r”
A Survey on Deep Semi-Supervised Learning (2021, background): “Text classification AG News [95], BPpedia [96], Yahoo! Answers [97], IMDB [98], Yelp review [95], Snippets [99], Ohsumed [100], TagMyNews [101], MR [102], Elec [103], Rotten Tomatoes [102], RCV1 [104] [105], [106], [107], [108], [109], [110]”
Weakly-Supervised Neural Text Classification (2018, methodology): “based Models Embedding-based weakly supervised models use seed information to derive vectorized representations for documents and label names for the text classification task. Dataless classification [5, 24] takes categorynamesandprojectseachwordanddocumentintothesame semantic space of Wikipedia con”
Concept-Based Information Retrieval Using Explicit Semantic Analysis (2011, methodology): “… from large-scale human-built repositories such as Wikipedia.1 Since it was .rst proposed, ESA has been successfully applied to text categorization [Chang et al. 2008; Gabrilovich and Markovitch 2006; Gupta and Ratinov 2008], semantic relatedness calculation [Gabrilovich and Markovitch 2007;…”
True Few-Shot Learning with Prompts—A Real-World Perspective (2021, background): “…instruction-based learning, some works have investigated ways of informing classi-ﬁers about the meaning of different output classes both for text (Chang et al., 2008; Veeranna et al., 2016; Zhou et al., 2018) and image classiﬁcation (Norouzi et al., 2014; Romera-Paredes and Torr, 2015); actually…”