Relation extraction suffers from a performance loss when a model is applied to out-of-domain data.

This has fostered the development of domain adaptation techniques for relation extraction .

This paper evaluates word embeddings and clustering on adapting feature-based relation extraction systems.

Our relation extraction system is hierarchical (Bunescu and Mooney, 2005b; Sun et a1., 2011) and apply maximum entropy (MaxEnt) in the MALLET3 toolkit as the machine 1eaming tool.

The goal of Relation Extraction (RE) is to detect and classify relation mentions between entity pairs into predefined relation types such as Employ-mentor Citizenship relationships.

The only study explicitly targeting this problem so far is by Plank and Moschitti (2013) who find that the out-of-domain performance of kemel-based relation extractors can be improved by embedding semantic similarity information generated from word clustering and latent semantic analysis (LSA) into syntactic tree kernels.

We will demonstrate later that the adaptability of relation extractors can benefit significantly from the addition of word cluster

Given the more general representations provided by word representations above, how can we learn a relation extractor from the labeled source domain data that generalizes well to new domains?

Exploiting the shared interest in generalization performance with traditional machine learning, in domain adaptation for RE, we would prefer the relation extractor that fits the source domain data, but also circumvents the overfitting problem

In relation extraction , distant supervision seeks to extract relations between entities from text by using a knowledge base, such as Freebase, as a source of supervision.

In the experiment, we also found that our wrong label reduction boosted the performance of relation extraction .

Experiment 2 aimed to evaluate how much our wrong label reduction in Section 4 improved the performance of relation extraction .

Machine learning approaches have been developed to address relation extraction , which is the task of extracting semantic relations between entities expressed in text.

0 We applied our method to Wikipedia articles using Freebase as a knowledge base and found that (i) our model identified patterns expressing a given relation more accurately than baseline methods and (ii) our method led to better extraction performance than the original DS (Mintz et al., 2009) and MultiR (Hoffmann et al., 2011), which is a state-of-the-art multi-instance learning system for relation extraction (see Section 7).

In this section, we describe DS for relation extraction .

Relation extraction seeks to extract relation instances from text.

DS uses a knowledge base to create labeled data for relation extraction by heuristically matching entity pairs.

(2009) who used Freebase as a knowledge base by making the DS assumption and trained relation extractors on Wikipedia.

Bootstrapping for relation extraction (Riloff and Jones, 1999; Pantel and Pennacchiotti, 2006; Carlson et al., 2010) is related to our method.

For relation extraction , we train a classifier for entity pairs using the resultant labeled data.

Although researchers have conducted extensive studies on relation extraction in the last decade, supervised approaches are still limited because they require large amounts of training data to achieve high performances.

To build a relation extractor without significant annotation effort, we can exploit cross-lingual annotation projection, which leverages parallel corpora as external resources for supervision.

This paper proposes a novel graph-based projection approach and demonstrates the merits of it by using a Korean relation extraction system based on projected dataset from an English—Korean parallel corpus.

Relation extraction aims to identify semantic relations of entities in a document.

Although many supervised machine learning approaches have been successfully applied to relation extraction tasks (Ze-lenko et al., 2003; Kambhatla, 2004; Bunescu and Mooney, 2005; Zhang et al., 2006), applications of these approaches are still limited because they require a sufficient number of training examples to obtain good extraction results.

Although these datasets encourage the development of relation extractors for these major languages, there are few labeled training samples for learning new systems in

Although much work on relation extraction has aimed at obtaining static facts, many of the target relations are actually flaents, as their validity is naturally anchored to a certain time period.

This paper proposes a methodological approach to temporally anchored relation extraction .

Results show that our implementation for temporal anchoring is able to achieve a 69% of the upper bound performance imposed by the relation extraction step.

To perform relation extraction , our proposal follows a distant supervision approach (Mintz et al., 2009), which has also inspired other slot filling systems (Agirre et al., 2009; Surdeanu et al., 2010).

Our system was one of the five that took part in the task.We have evaluated the overall system and the two main components of the architecture: Relation Extraction , and Temporal Anchoring of the relations.

6.1 Evaluation of Relation Extraction

As pointed out in (Ling and Weld, 2010), while much research in automatic relation extraction has focused on distilling static facts from text, many of the target relations are in fact flaents, dynamic relations whose truth value is dependent on time (Russell and Norvig, 2010).

The Temporally anchored relation extraction problem consists in, given a natural language text document corpus, C, a target entity, 6, and a target

ed Relation Extraction

The entity mention extraction and relation extraction tasks we are addressing are those of the Automatic Content Extraction (ACE) program2.

Most previous research on relation extraction assumed that entity mentions were given In this work we aim to address the problem of end-to-end entity mention and relation extraction from raw texts.

In order to develop a baseline system representing state-of-the-art pipelined approaches, we trained a linear-chain Conditional Random Fields model (Lafferty et al., 2001) for entity mention extraction and a Maximum Entropy model for relation extraction .

Most previous work on ACE relation extraction has reported results on ACE’04 data set.

We use the standard F1 measure to evaluate the performance of entity mention extraction and relation extraction .

Furthermore, we combine these two criteria to evaluate the performance of end-to-end entity mention and relation extraction .

The goal of end-to-end entity mention and relation extraction is to discover relational structures of entity mentions from unstructured texts.

This problem has been artificially broken down into several components such as entity mention boundary identification, entity type classification and relation extraction .

We present a simple semi-supervised relation extraction system with large-scale word clustering.

3.1 Relation Extraction

One of the well defined relation extraction tasks is the Automatic Content Extraction1 (ACE) program sponsored by the U.S. government.

Relation extraction is an important information extraction task in natural language processing (NLP), with many practical applications.

The goal of relation extraction is to detect and characterize semantic relations between pairs of entities in text.

For example, a relation extraction system needs to be able to extract an Employment relation between the entities US soldier and US in the phrase US soldier.

A second difference between this work and the above ones is that we utilize word clusters in the task of relation extraction which is very different from sequence labeling tasks such as name tagging and chunking.

(2005) and Chan and Roth (2010) used word clusters in relation extraction , they shared the same limitation as the above approaches in choosing clusters.

In this paper, we propose an Omni—word feature and a soft constraint method for Chinese relation extraction .

The results show a significant improvement in Chinese relation extraction , outperforming other methods in F-score by 10% in 6 relation types and 15% in 18 relation subtypes.

The performance of relation extraction is still unsatisfactory with a F-score of 67.5% for English (23 subtypes) (Zhou et al., 2010).

Chinese relation extraction also faces a weak performance having F-score about 66.6% in 18 subtypes (Dandan et al., 2012).

Therefore, the Chinese relation extraction is more difficult.

There are two paradigms extracting the relationship between two entities: the Open Relation Extraction (ORE) and the Traditional Relation Extraction (TRE) (Banko et al., 2008).

In the field of Chinese relation extraction , Liu et al.

(2008) experimented with different kernel methods and inferred that simply migrating from English kernel methods can result in a bad performance in Chinese relation extraction .

We propose a two-phase framework to adapt existing relation extraction classifiers to extract relations for new target domains.

Our method outperforms numerous baselines and a weakly-supervised relation extraction method on ACE 2004 and YAGO.

Recent work on relation extraction has demonstrated that supervised machine learning coupled with intelligent feature engineering can provide state-of-the-art performance (Jiang and Zhai, 2007b).

Instead, it can be more cost-effective to adapt an existing relation extraction system to the new domain using a small set of labeled data.

This paper considers relation adaptation, where a relation extraction system trained on many source domains is adapted to a new target domain.

Relation extraction is usually considered a classification problem: determine if two given entities in a sentence have a given relation.

However, purely supervised relation extraction methods assume the availability of sufficient labeled data, which may be costly to obtain for new domains.

Bootstrapping methods (Zhu et al., 2009; Agichtein and Gravano, 2000; Xu et al., 2010; Pasca et al., 2006; Riloff and Jones, 1999) to relation extraction are attractive because they require fewer training instances than supervised approaches.

Most existing relation extraction models make predictions for each entity pair locally and individually, while ignoring implicit global clues available in the knowledge base, sometimes leading to conflicts among local predictions from different entity pairs.

Experimental results on three datasets, in both English and Chinese, show that our framework outperforms the state-of-the-art relation extraction models when such clues are applicable to the datasets.

In the literature, relation extraction (RE) is usually investigated in a classification style, where relations are simply treated as isolated class labels, while their definitions or background information are sometimes ignored.

On the other hand, most previous relation extractors process each entity pair (we will use entity pair and entity tuple exchangeably in the rest of the paper) locally and individually, i.e., the extractor makes decisions solely based on the sentences containing the current entity pair and ignores other related pairs, therefore has difficulties to capture possible disagreements among different entity pairs.

In this paper, we will address how to derive and exploit two categories of these clues: the expected types and the cardinality requirements of a relation’s arguments, in the scenario of relation extraction .

Since traditional supervised relation extraction methods (Soderland et al., 1995; Zhao and Gr-ishman, 2005) require manual annotations and are often domain-specific, nowadays many efforts focus on semi-supervised or unsupervised methods (Banko et al., 2007; Fader et al., 2011).

To bridge the gaps between the relations extracted from open information extraction and the canonicalized relations in KBs, Yao et al.

Since we will focus on the open domain relation extraction , we still follow the distant supervision paradigm to collect our training data guided by a KB, and train the local extractor accordingly.

Traditionally, both lexical features and syntactic features are used in relation extraction .

addition to lexical and syntactic features, we also use n-gram features to train our preliminary relation extraction model.

In the literature, the mainstream research on relation extraction adopts statistical machine learning methods, which can be grouped into supervised learning (Zelenko et al., 2003; Culotta and Soresen, 2004; Zhou et al., 2005; Zhang et al., 2006; Qian et al., 2008; Chan and Roth, 2011), semi-supervised learning (Zhang et al., 2004; Chen et al., 2006; Zhou et al., 2008; Qian et al., 2010) and unsupervised learning (Hase-gawa et al., 2004; Zhang et al., 2005) in terms of the amount of labeled training data they need.

It is trivial to validate, as we will do later in this paper, that active learning can also alleviate the annotation burden for relation extraction in one language while retaining the extraction performance.

However, there are cases when we may exploit relation extraction in multiple languages and there are corpora with relation instances annotated for more than one language, such as the ACE RDC 2005 English and Chinese corpora.

Relation Extraction (RE) is the task of extracting semantic relationships between entities in text.

Recent studies on relation extraction are mostly supervised.

In this paper, we propose to combine (i) term generalization approaches such as word clustering and latent semantic analysis (LSA) and (ii) structured kernels to improve the adaptability of relation extractors to new text genres/domains.

(2006), including gold-standard information on entity and mention type substantially improves relation extraction performance.

We treat relation extraction as a multi-class classification problem and use SVM-light-TK4 to train the binary classifiers.

Relation extraction is the task of extracting semantic relationships between entities in text, e.g.

Recent studies on relation extraction have shown that supervised approaches based on either feature or kernel methods achieve state-of-the-art accuracy (Ze-lenko et al., 2002; Culotta and Sorensen, 2004;

However, to the best of our knowledge, there is almost no work on adapting relation extraction (RE) systems to new domains.1 There are some prior studies on the related tasks of malti-task transfer learning (Xu et al., 2008; Jiang, 2009) and distant supervision (Mintz et al., 2009), which are clearly related but different: the former is the problem of how to transfer knowledge from old to new relation types, while distant supervision tries to learn new relations from unlabeled text by exploiting weak-supervision in the form of a knowledge resource (e.g.

Thus, we present a novel application of semantic syntactic tree kernels and Brown clusters for domain adaptation of tree-kernel based relation extraction .

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 .

In this paper, we present a manifold model for medical relation extraction .

2.2 Relation Extraction

Relation extraction plays a key role in information extraction.

To construct a medical relation extraction system, several challenges have to be addressed:

The medical corpus underlying our relation extraction system contains 80M sentences (ll gigabytes pure text).

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) .

We adopted the evaluation metrics for entity and relation extraction from Choi et al.

We trained the classifiers for relation extraction using L1-regu1arized logistic regression with default parameters using the LIBLINEAR (Fan et al., 2008) package.

Three relation extraction techniques were used in the baselines:

2007; Yang and Cardie, 2012)) and relation extraction techniques have been proposed to extract opinion holders and targets based on their linking relations to the opinion expressions (e. g. Kim and Hovy (2006), Kobayashi et al.

We model entity identification as a sequence tagging problem and relation extraction as binary classification.

In this section, we will describe how we model opinion entity identification and opinion relation extraction , and how we combine them in a joint inference model.

3.2 Opinion Relation Extraction

In the following we will not distinguish these two relations, since they can both be characterized as relations between opinion expressions and opinion arguments, and the methods for relation extraction are the same.

The essence of distantly supervised relation extraction is that it is an incomplete multi-label classification problem with sparse and noisy features.

In this paper, we contributed two noise-tolerant optimization models”, DRMC-b and DRMC-l, for distantly supervised relation extraction task from a novel perspective.

Our proposed models also leave open questions for distantly supervised relation extraction task.

Relation Extraction (RE) is the process of generating structured relation knowledge from unstructured natural language texts.

Figure 1: Training corpus generated by the basic alignment assumption of distantly supervised relation extraction .

In essence, distantly supervised relation extraction is an incomplete multi-label classification task with sparse and noisy features.

Our models for relation extraction are based on the theoretic framework proposed by Goldberg et al.

11It is the abbreviation for Distant supervision for Relation extraction with Matrix Completion

(2012) proposed a novel approach to multi-instance multi-label learning for relation extraction , which jointly modeled all the sentences in texts and all labels in knowledge bases for a given entity pair.

Our method exploits the data co-occarrence phenomena that is very useful for relation extractions .

Table 4: F all-abbreviation Relation Extraction Precision

To further show the advantage of our relation extraction algorithm (see Section 3.3), in the third column of Table 4 we report the results on a simple baseline.

As shown in Table 4, the baseline performs significantly worse than our relation extraction algorithm.

3.3 F all-abbreviation Relation Extraction from Chinese Monolingual Corpora

3.3.2 F all-abbreviation Relation Extraction Algorithm

Figure 2 presents the pseudocode of the full-abbreviation relation extraction algorithm.

raditional Relation Extraction

We also plan to explore the capacity of Open IE to automatically provide labeled training data, when traditional relation extraction is a more appropriate choice.

4.2 Stacked Relation Extraction

Relation Extraction (RE) is the task of recognizing the assertion of a particular relationship between two or more entities in text.

Given a relation name, labeled examples of the relation, and a corpus, traditional Relation Extraction (RE) systems output instances of the given relation found in the corpus.

Figure 1: Relation Extraction as Sequence Labeling: A CRF is used to identify the relationship, born in, between Kafka and Prague

Linear-chain CRFs have been applied to a variety of sequential text processing tasks including named-entity recognition, part-of—speech tagging, word segmentation, semantic role identification, and recently relation extraction (Culotta et al., 2006).

In this section, we show that many relationships are consistently expressed using a compact set of relation-independent lexico-syntactic patterns, and quantify their frequency based on a sample of 500 sentences selected at random from an IE training corpus developed by (Bunescu and Mooney, 2007).1 This observation helps to explain the success of open relation extraction , which learns a relation-independent extraction model as described in Section 3.1.

In this paper, we express the semantics of precondition relations extracted from text in terms of planning operations.

When applied to a complex virtual world and text describing that world, our relation extraction technique performs on par with a supervised baseline, yielding an F-measure of 66% compared to the baseline’s 65%.

While using planning feedback as its only source of supervision, our method for relation extraction achieves a performance on par with that of a supervised baseline.

Evaluation Metrics We use our manual annotations to evaluate the type-level accuracy of relation extraction .

Baselines To evaluate the performance of our relation extraction , we compare against an SVM classifier8 trained on the Gold Relations.

The central idea of our work is to express the semantics of precondition relations extracted from text in terms of planning operations.

We build on the intuition that the validity of precondition relations extracted from text can be informed by the execution of a low-level planner.3 This feedback can enable us to learn these relations without annotations.

Our results demonstrate the strength of our relation extraction technique — while using planning feedback as its only source of supervision, it achieves a precondition relation extraction accuracy on par with that of a supervised SVM baseline.

Relation Extraction Figure 5 shows the performance of our method on identifying preconditions in text.

Distant supervision usually utilizes only unlabeled data and existing knowledge bases to learn relation extraction models.

Thus, our approach outperforms state-of-the-art model for relation extraction using much less labeled data that was used by Zhang et al., (2012) to outper-

We show that relation extractors trained with distant supervision can benefit significantly from a small number of human labeled examples.

We show how to incorporate these guidelines into an existing state-of-art model for relation extraction .

Relation extraction is the task of tagging semantic relations between pairs of entities from free text.

Recently, distant supervision has emerged as an important technique for relation extraction and has attracted increasing attention because of its effective use of readily available databases (Mintz et al., 2009; Bunescu and Mooney, 2007; Snyder and Barzilay, 2007; Wu and Weld, 2007).

1t Supervision for Relation Extraction

Conflicts cannot be limited to those cases where all the features in two examples are the same; this would almost never occur, because of the dozens of features used by a typical relation extractor (Zhou et al., 2005).

Tree kernel is an effective technique for relation extraction .

Relation Extraction (RE) aims to identify a set of predefined relations between pairs of entities in text.

In recent years, relation extraction has received considerable research attention.

An effective technique is the tree kernel (Zelenko et al., 2003; Zhou et al., 2007; Zhang et al., 2006; Qian et al., 2008), which can exploit syntactic parse tree information for relation extraction .

This method is evaluated on two temporal relation extraction tasks and demonstrates its advantage over rich syntactic representations.

2.2 Temporal Relation Extraction

Among NLP tasks that use syntactic information, temporal relation extraction has been drawing growing attention because of its wide applications in multiple domains.

Many methods exist for synthesizing syntactic information for temporal relation extraction , and most use traditional tree kernels with various feature representations.

Future work will explore 1) a composite kernel which uses DPK for PET trees, SST for BT and PT, and feature kernel for flat features, so that different tree kernels can work with their ideal syntactic representations; 2) incorporate dependency structures for tree kernel analysis 3) applying DPK to other relation extraction tasks on various corpora.

We applied DPK to two published temporal relation extraction systems: (Miller et al., 2013) in the clinical domain and Cleartk—TimeML (Bethard, 2013) in the general domain respectively.

Table 2: Comparison of tree kernel performance for temporal relation extraction on THYME and TempEval-2013 data.

We further show that we can use these paraphrases to generate surface patterns for relation extraction .

While we believe that more work needs to be done to improve the system recall (some of which we are investigating), this seems to be a good first step towards developing a minimally supervised, easy to implement, and scalable relation extraction system.

5.3 Relation Extraction

Moving to the task of relation extraction , we see from table 5 that our system has a much lower relative recall compared to the baseline.

Claim 2: These paraphrases can then be used for generating high precision surface patterns for relation extraction .

Another task related to our work is relation extraction .

The parser is trained by jointly optimizing performance on a syntactic parsing task and a distantly-supervised relation extraction task.

Using the relation instances and Wikipedia sentences, we constructed a data set for distantly-supervised relation extraction .

Comparing against this parser lets us measure the effect of the relation extraction task on syntactic parsing.

Our parser is trained by combining a syntactic parsing task with a distantly-supervised relation extraction task.

Training is performed by minimizing a joint objective function combining a syntactic parsing task and a distantly-supervised relation extraction task.

The syntactic component Osyn is a standard syntactic parsing objective constructed using the syntactic resource L. The semantic component Osem is a distantly-supervised relation extraction task based on the semantic constraint from Krishnamurthy and Mitchell (2012).

The semantic objective corresponds to a distantly-supervised relation extraction task that constrains the logical forms produced by the semantic parser.

We have described a new distant supervision model with which to learn patterns for relation extraction with no manual intervention.

In the case of nationality, however, even though the extracted sentences do not support the relation (P@50 = 0.34 for intertext), the new relations extracted are mostly correct (P@50 = 0.86) as most presidents and ministers in the real world have the nationality of the country where they govern.

Open Information Extraction (Sekine, 2006; Banko et al., 2007; Bollegala et al., 2010) started as an effort to approach relation extraction in

A different family of unsupervised methods for relation extraction is unsupervised semantic parsing, which aims at clustering entity mentions and relation surface forms, thus generating a semantic representation of the texts on which inference may be used.

The main contribution of this work is presenting a variant of distance supervision for relation extraction where we do not use heuristics in the selection of the training data.

Figure 1: Example of a generated set of document collections from a news corpus 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.

(Mintz et al., 2009) uses Freebase to provide distant supervision for relation extraction .

They applied a similar heuristic by matching Freebase tuples with unstructured sentences (Wikipedia articles in their experiments) to create features for learning relation extractors .

(Akbik and BroB, 2009) annotated 10,000 sentences parsed with LinkGrammar and selected 46 general linkpaths as patterns for relation extraction .

noted in (de Marneffe and Manning, 2008), this collapsed format often yields simplified patterns which are useful for relation extraction .

This paper presents LUCHS, an autonomous, self-supervised system, which learns 5025 relational extractors — an order of magnitude greater than any previous effort.

In order to handle sparsity in its heuristically- generated training data, LUCHS generates custom lexicon features when learning each relational extractor .

Our experiments demonstrate a high Fl score, 61%, across the 5025 relational extractors learned.

We therefore choose a hierarchical approach that combines both article classifiers and relation extractors .

is likely to contain a schema, does LUCHS run that schema’s relation extractors .

3.1 Comparable Relation Extraction

An important observation for the task of comparable relation extraction is that many relations are complex multiword expressions, and thus their automatic detection is not trivial.

ger (Lafferty et al., 2001) to the task, since CRF was shown to be state-of-the-art for sequential relation extraction (Mooney and Bunescu, 2005; Culotta et al., 2006; J indal and Liu, 2006).

Our extraction of comparable relations falls within the field of Relation Extraction , in which CRF is a state-of-the-art method (Mooney and Bunescu, 2005; Culotta et al., 2006).

Rel-LDA: Generative models have been successfully applied to unsupervised relation extraction (Rink and Harabagiu, 2011; Yao et al., 2011).

Relation extraction (RE) is the task of determining semantic relations between entities mentioned in text.

Here, the relation extractor simultaneously discovers facts expressed in natural language, and the ontology into which they are assigned.

Many generative probabilistic models have been applied to relation extraction .

Concretely, we cast user profile prediction as binary relation extraction (Brin, 1999), e.g., SPOUSE(User,—, Userj), EDUCATION(User,—, Entityj) and EMPLOYER(Userz-, Entityj).

Rather than relying on mention-level annotations, which are expensive and time consuming to generate, distant supervision leverages readily available structured data sources as a weak source of supervision for relation extraction from related text corpora (Craven et al., 1999).

In addition to the wide use in text entity relation extraction (Mintz et al., 2009; Ritter et al., 2013; Hoffmann et al., 2011; Surdeanu et al., 2012; Takamatsu et al., 2012), distant supervision has been applied to multiple

fields such as protein relation extraction (Craven et al., 1999; Ravikumar et al., 2012), event extraction from Twitter (Benson et al., 2011), sentiment analysis (Go et al., 2009) and Wikipedia infobox generation (Wu and Weld, 2007).

Knowledge-based weak supervision, using structured data to heuristically label a training corpus, works towards this goal by enabling the automated learning of a potentially unbounded number of relation extractors .

automatically learn a nearly unbounded number of relational extractors .

(2009) used Freebase facts to train 100 relational extractors on Wikipedia.

Bunescu and Mooney (2007) connect weak supervision with multi-instance learning and extend their relational extraction kernel to this context.

In this paper, we observe that there exists a second dimension to the relation extraction (RE) problem that is orthogonal to the relation type dimension.

Relation extraction (RE) has been defined as the task of identifying a given set of semantic binary relations in text.

In this paper we build on the observation that there exists a second dimension to the relation extraction problem that is orthogonal to the relation type dimension: all relation types are expressed in one of several constrained syntactico-semantic structures.

In the next section, we describe our relation extraction framework that leverages the syntactico-semantic structures.

Dependency Tree Kernel for Relation Extraction .

Kernel Methods for Relation Extraction .

Exploring Syntactic Features for Relation Extraction using a Convolution Tree Kernel.

Indeed, using kernel methods to mine structural knowledge has shown success in some NLP applications like parsing (Collins and Duffy, 2001; Moschitti, 2004) and relation extraction (Zelenko et al., 2003; Zhang et al., 2006).

In order to deduce the speaker of the utterance, we need to combine the three pieces of information: (a) the utterance is addressed to Lizzy (vocative prediction), (b) the utterance is produced by Lizzy’s father (pronoun resolution), and (c) Mr. Bennet is the father of Lizzy ( relationship extraction ).

A joint approach to resolving speaker attribution, relationship extraction , co-reference resolution, and alias-to-character mapping would not only improve the accuracy on all these tasks, but also represent a step towards deeper understanding of complex plots and stories.

A preliminary manual inspection of the set of relations extracted by this method (Makazhanov et al., 2012) indicates that all of them are correct, and include about 40% all personal relations that can be inferred by a human reader from the text of the novel.

We also leverage synonym-matching techniques for comparing relations extracted from text with Freebase relations.

Our techniques for comparing relations fit into this line of work, but they are novel in their application of these techniques to the task of comparing database relations and relations extracted from text.

Schema matching in the database sense often considers complex matches between relations (Dhamanka et al., 2004), whereas as our techniques are currently restricted to matches involving one database relation and one relation extracted from text.

The results indicate that the learned types can be used to in relation extraction tasks.

Our goal is to find semantic type candidates in the data, and apply them in relation extraction to see which ones are best suited.

In relation extraction , we have to identify the relation elements, and then map the arguments to types.

ConceptResolver performs both word sense induction and synonym resolution on relations extracted from text using an ontology and a small amount of labeled data.

The relations extracted by systems like NELL actually apply to concepts, not to noun phrases.

Synonym resolution on relations extracted from web text has been previously studied by Resolver (Yates and Etzioni, 2007), which finds synonyms in relation triples extracted by TextRunner (Banko et al., 2007).