Zero-shot Entity Extraction from Web Pages

By Panupong Pasupat, Percy Liang. 2014

43 citations recorded by the source corpus.

In order to extract entities of a fine-grained category from semi-structured data in web pages, existing information extraction systems rely on seed examples or redundancy across multiple web pages. In this paper, we consider a new zero-shot learning task of extracting entities specified by a natural language query (in place of seeds) given only a single web page. Our approach defines a log-linear model over latent extraction predicates, which select lists of entities from the web page. The main challenge is to define features on widely varying candidate entity lists. We tackle this by

Subfields: Artificial Intelligence, Information Systems, 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 Information Systems

In Information Extraction

Citations in the corpus

The Art of Prompting: Event Detection based on Type Specific Prompts (2022, background): “, 2021) or there is no annotation available (Lyu et al., 2021; Zhang et al., 2021b; Pasupat and Liang, 2014).”
Language Models can Solve Computer Tasks (2023, background): “The automation of computer tasks is an important topic for both information retrieval and natural language processing [43, 50, 49, 31, 65].”
Fonduer: Knowledge Base Construction from Richly Formatted Data (2017, unknown): “In addition to existing knowledge bases, crowdsourcing [12] and heuristics from domain experts [29] have also proven to be effective weak supervision sources.”
A Survey of Zero-Shot Learning (2019, methodology): “…a vector and put into a binary classifier to decide whether they come from the same class (e.g., “input space view” model in [81] and method in [117])—this binary classifier acts as the compatibility function; and (4) the compatibility function in other forms (e.g., the compatibility function…”
Neural Enquirer: Learning to Query Tables (2015, background): “Another line of research takes a semi-supervised learning approach, and adopts the results of query execution (i.e., answers) as supervision signal [5, 3, 10, 11, 12].”
Simpler Context-Dependent Logical Forms via Model Projections (2016, background): “erant et al., 2013), or automatically learned from annotated logical forms (Kwiatkowski et al., 2010; Chen, 2012). Recent work on learning from denotations has moved away from anchored logical forms. Pasupat and Liang (2014) and Wang et al. (2015) proposed generating logical forms without alignments”