Information Extraction

2 papers with code • 0 benchmarks • 0 datasets

Information extraction is the task of automatically extracting structured information from unstructured and / or semi-structured machine-readable documents and other electronically represented sources (Source: Wikipedia).

textTOvec: Deep Contextualized Neural Autoregressive Topic Models of Language with Distributed Compositional Prior

pgcool/textTOvec ICLR 2019

We address two challenges of probabilistic topic modelling in order to better estimate the probability of a word in a given context, i. e., P(word|context): (1) No Language Structure in Context: Probabilistic topic models ignore word order by summarizing a given context as a "bag-of-word" and consequently the semantics of words in the context is lost.

24
09 Oct 2018

Closing the Loop: Fast, Interactive Semi-Supervised Annotation With Queries on Features and Instances

burrsettles/dualist Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing 2011

This paper describes DUALIST, an active learning annotation paradigm which solicits and learns from labels on both features (e. g., words) and instances (e. g., documents).

86
01 Jul 2011