Creating labeled training data for relation extraction is expensive.

In this paper, we study relation extraction in a special weakly-supervised setting when we have only a few seed instances of the target relation type we want to extract but we also have a large amount of labeled instances of other relation types.

Observing that different relation types can share certain common structures, we propose to use a multitask learning method coupled with human guidance to address this weakly-supervised relation extraction problem.

Relation extraction is the task of detecting and characterizing semantic relations between entities from free text.

Recent work on relation extraction has shown that supervised machine learning coupled with intelligent feature engineering or kernel design provides state-of-the-art solutions to the problem (Culotta and Sorensen, 2004; Zhou et al., 2005; Bunescu and Mooney, 2005; Qian et al., 2008).

While transfer learning was proposed more than a decade ago (Thrun, 1996; Caruana, 1997), its application in natural language processing is still a relatively new territory (Blitzer et al., 2006; Daume III, 2007; J iang and Zhai, 2007a; Arnold et al., 2008; Dredze and Crammer, 2008), and its application in relation extraction is still unexplored.

Recent work on relation extraction has been dominated by feature-based and kernel-based supervised learning methods.

(2005) and Zhao and Grishman (2005) studied various features and feature combinations for relation extraction .

We systematically explored the feature space for relation extraction (Jiang and Zhai, 2007b) .

This paper presents an unsupervised relation extraction method for discovering and enhancing relations in which a specified concept in Wikipedia participates.

Machine learning approaches for relation extraction tasks require substantial human effort, particularly when applied to the broad range of documents, entities, and relations existing on the Web.

Linguistic analysis is another effective technology for semantic relation extraction , as described in many reports such as (Kambhatla, 2004); (Bunescu and Mooney, 2005); (Harabagiu et al., 2005); (Nguyen et al., 2007).

Currently, linguistic approaches for semantic relation extraction are mostly supervised, relying on pre-specification of the desired relation or initial seed words or patterns from hand-coding.

(Rosenfeld and Feldman, 2006) showed that the clusters discovered by URI are useful for seeding a semi-supervised relation extraction system.

In this paper, we propose an unsupervised relation extraction method that combines patterns of two types: surface patterns and dependency patterns.

Surface patterns are generated from the Web corpus to provide redundancy information for relation extraction .

Modem models of relation extraction for tasks like ACE are based on supervised learning of relations from small hand-labeled corpora.

Supervised relation extraction suffers from a number of problems, however.

Our algorithm uses Freebase (Bollacker et al., 2008), a large semantic database, to provide distant supervision for relation extraction .

cal (word sequence) features in relation extraction .

Except for the unsupervised algorithms discussed above, previous supervised or bootstrapping approaches to relation extraction have typically relied on relatively small datasets, or on only a small number of distinct relations.

Many early algorithms for relation extraction used little or no syntactic information.