Results 1 - 10
of
20
Extracting Lexically Divergent Paraphrases from Twitter
"... We present MULTIP (Multi-instance Learn-ing Paraphrase Model), a new model suited to identify paraphrases within the short mes-sages on Twitter. We jointly model para-phrase relations between word and sentence pairs and assume only sentence-level annota-tions during learning. Using this principled l ..."
Abstract
-
Cited by 12 (2 self)
- Add to MetaCart
(Show Context)
We present MULTIP (Multi-instance Learn-ing Paraphrase Model), a new model suited to identify paraphrases within the short mes-sages on Twitter. We jointly model para-phrase relations between word and sentence pairs and assume only sentence-level annota-tions during learning. Using this principled la-tent variable model alone, we achieve the per-formance competitive with a state-of-the-art method which combines a latent space model with a feature-based supervised classifier. Our model also captures lexically divergent para-phrases that differ from yet complement previ-ous methods; combining our model with pre-vious work significantly outperforms the state-of-the-art. In addition, we present a novel an-notation methodology that has allowed us to crowdsource a paraphrase corpus from Twit-ter. We make this new dataset available to the research community. 1
Combining Distant and Partial Supervision for Relation Extraction
"... Broad-coverage relation extraction either requires expensive supervised training data, or suffers from drawbacks inherent to distant supervision. We present an ap-proach for providing partial supervision to a distantly supervised relation extrac-tor using a small number of carefully se-lected exampl ..."
Abstract
-
Cited by 7 (1 self)
- Add to MetaCart
Broad-coverage relation extraction either requires expensive supervised training data, or suffers from drawbacks inherent to distant supervision. We present an ap-proach for providing partial supervision to a distantly supervised relation extrac-tor using a small number of carefully se-lected examples. We compare against es-tablished active learning criteria and pro-pose a novel criterion to sample examples which are both uncertain and representa-tive. In this way, we combine the ben-efits of fine-grained supervision for diffi-cult examples with the coverage of a large distantly supervised corpus. Our approach gives a substantial increase of 3.9 % end-to-end F1 on the 2013 KBP Slot Filling evaluation, yielding a net F1 of 37.7%. 1
Relation extraction from the web using distant supervision
- In Janowicz et al
"... Abstract. Extracting information from Web pages requires the ability to work at Web scale in terms of the number of documents, the number of domains and domain complexity. Recent approaches have used existing knowledge bases to learn to extract information with promising results. In this paper we pr ..."
Abstract
-
Cited by 6 (3 self)
- Add to MetaCart
(Show Context)
Abstract. Extracting information from Web pages requires the ability to work at Web scale in terms of the number of documents, the number of domains and domain complexity. Recent approaches have used existing knowledge bases to learn to extract information with promising results. In this paper we propose the use of distant supervision for relation extraction from the Web. Distant supervision is a method which uses background information from the Linking Open Data cloud to automatically label sentences with relations to create training data for relation classifiers. Although the method is promising, existing approaches are still not suitable for Web extraction as they suffer from three main issues: data sparsity, noise and lexical ambiguity. Our approach reduces the impact of data sparsity by making entity recognition tools more robust across domains, as well as extracting relations across sentence boundaries. We reduce the noise caused by lexical ambiguity by employing statistical methods to strategically select training data. Our experiments show that using a more robust entity recognition approach and expanding the scope of relation extraction results in about 8 times the number of extractions, and that strategically selecting training data can result in an error reduction of about 30%. 1
Distant supervision for relation extraction with matrix completion
- In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (ACL
, 2014
"... Abstract The essence of distantly supervised relation extraction is that it is an incomplete multi-label classification problem with sparse and noisy features. To tackle the sparsity and noise challenges, we propose solving the classification problem using matrix completion on factorized matrix of ..."
Abstract
-
Cited by 6 (1 self)
- Add to MetaCart
Abstract The essence of distantly supervised relation extraction is that it is an incomplete multi-label classification problem with sparse and noisy features. To tackle the sparsity and noise challenges, we propose solving the classification problem using matrix completion on factorized matrix of minimized rank. We formulate relation classification as completing the unknown labels of testing items (entity pairs) in a sparse matrix that concatenates training and testing textual features with training labels. Our algorithmic framework is based on the assumption that the rank of item-byfeature and item-by-label joint matrix is low. We apply two optimization models to recover the underlying low-rank matrix leveraging the sparsity of feature-label matrix. The matrix completion problem is then solved by the fixed point continuation (FPC) algorithm, which can find the global optimum. Experiments on two widely used datasets with different dimensions of textual features demonstrate that our low-rank matrix completion approach significantly outperforms the baseline and the state-of-the-art methods.
Improved Pattern Learning for Bootstrapped Entity Extraction
"... Bootstrapped pattern learning for entity extraction usually starts with seed entities and iteratively learns patterns and entities from unlabeled text. Patterns are scored by their ability to extract more positive en-tities and less negative entities. A prob-lem is that due to the lack of labeled da ..."
Abstract
-
Cited by 6 (0 self)
- Add to MetaCart
Bootstrapped pattern learning for entity extraction usually starts with seed entities and iteratively learns patterns and entities from unlabeled text. Patterns are scored by their ability to extract more positive en-tities and less negative entities. A prob-lem is that due to the lack of labeled data, unlabeled entities are either assumed to be negative or are ignored by the existing pat-tern scoring measures. In this paper, we improve pattern scoring by predicting the labels of unlabeled entities. We use var-ious unsupervised features based on con-trasting domain-specific and general text, and exploiting distributional similarity and edit distances to learned entities. Our system outperforms existing pattern scor-ing algorithms for extracting drug-and-treatment entities from four medical fo-rums. 1
Type-Aware Distantly Supervised Relation Extraction with Linked Arguments
"... Distant supervision has become the lead-ing method for training large-scale rela-tion extractors, with nearly universal adop-tion in recent TAC knowledge-base pop-ulation competitions. However, there are still many questions about the best way to learn such extractors. In this paper we investigate f ..."
Abstract
-
Cited by 5 (1 self)
- Add to MetaCart
Distant supervision has become the lead-ing method for training large-scale rela-tion extractors, with nearly universal adop-tion in recent TAC knowledge-base pop-ulation competitions. However, there are still many questions about the best way to learn such extractors. In this paper we investigate four orthogonal improvements: integrating named entity linking (NEL) and coreference resolution into argument identification for training and extraction, enforcing type constraints of linked argu-ments, and partitioning the model by rela-tion type signature. We evaluate sentential extraction perfor-mance on two datasets: the popular set of NY Times articles partially annotated by Hoffmann et al. (2011) and a new dataset, called GORECO, that is comprehensively annotated for 48 common relations. We find that using NEL for argument identi-fication boosts performance over the tra-ditional approach (named entity recogni-tion with string match), and there is further improvement from using argument types. Our best system boosts precision by 44% and recall by 70%. 1
Seed Selection for Distantly Supervised Web-Based Relation Extraction
"... In this paper we consider the problem of distant supervision to extract relations (e.g. origin(musical artist, location)) for entities (e.g. ‘The Beatles’) of certain classes (e.g. musical artist) from Web pages by using background information from the Linking Open Data cloud to automatically label ..."
Abstract
-
Cited by 3 (3 self)
- Add to MetaCart
In this paper we consider the problem of distant supervision to extract relations (e.g. origin(musical artist, location)) for entities (e.g. ‘The Beatles’) of certain classes (e.g. musical artist) from Web pages by using background information from the Linking Open Data cloud to automatically label Web documents which are then used as training data for relation classifiers. Distant supervision approaches typically suffer from the problem of ambiguity when automatically labelling text, as well as the problem of incompleteness of background data to judge whether a mention is a true relation mention. This paper explores the hypothesis that simple statistical methods based on background data can help to filter unreliable training data and thus improve the precision of relation extractors. Experiments on a Web corpus show that an error reduction of 35 % can be achieved by strategically selecting seed data. 1
Joint Information Extraction from the Web using Linked Data
- Proceedings of ISWC (2014) Augenstein et al. / Distantly Supervised Web Relation Extraction for Knowledge Base Population 13
"... Abstract. Almost all of the big name Web companies are currently engaged in building ‘knowledge graphs ’ and these are showing significant results in improving search, email, calendaring, etc. Even the largest openly-accessible ones, such as Freebase and Wikidata, are far from complete, partly becau ..."
Abstract
-
Cited by 3 (2 self)
- Add to MetaCart
(Show Context)
Abstract. Almost all of the big name Web companies are currently engaged in building ‘knowledge graphs ’ and these are showing significant results in improving search, email, calendaring, etc. Even the largest openly-accessible ones, such as Freebase and Wikidata, are far from complete, partly because new information is emerging so quickly. Most of the missing information is available on Web pages. To access that knowledge and populate knowledge bases, information extraction methods are necessitated. The bottleneck for information extraction systems is obtaining training data to learn classifiers. In this doctoral research, we investigate how existing data in knowledge bases can be used to automatically annotate training data to learn classifiers to in turn extract more data to expand knowledge bases. We discuss our hypotheses, approach, evaluation methods and present preliminary results. 1 Problem Statement Since the emergence of the Semantic Web, many Linked datasets such as Freebase [5], Wikidata [31] and DBpedia [4] have been created, not only for research, but also com-
Infusion of labeled data into distant supervision for relation extraction
- In ACL. Sebastian Riedel, Limin
, 2014
"... Distant supervision usually utilizes only unlabeled data and existing knowledge bases to learn relation extraction models. However, in some cases a small amount of human labeled data is available. In this paper, we demonstrate how a state-of-the-art multi-instance multi-label model can be modified t ..."
Abstract
-
Cited by 3 (0 self)
- Add to MetaCart
(Show Context)
Distant supervision usually utilizes only unlabeled data and existing knowledge bases to learn relation extraction models. However, in some cases a small amount of human labeled data is available. In this paper, we demonstrate how a state-of-the-art multi-instance multi-label model can be modified to make use of these reli-able sentence-level labels in addition to the relation-level distant supervision from a database. Experiments show that our ap-proach achieves a statistically significant increase of 13.5 % in F-score and 37 % in area under the precision recall curve. 1
Robust domain adaptation for relation extraction via clustering consistency
- In ACL. Denis Paperno, The Nghia
, 2014
"... Abstract We propose a two-phase framework to adapt existing relation extraction classifiers to extract relations for new target domains. We address two challenges: negative transfer when knowledge in source domains is used without considering the differences in relation distributions; and lack of a ..."
Abstract
-
Cited by 1 (0 self)
- Add to MetaCart
Abstract We propose a two-phase framework to adapt existing relation extraction classifiers to extract relations for new target domains. We address two challenges: negative transfer when knowledge in source domains is used without considering the differences in relation distributions; and lack of adequate labeled samples for rarer relations in the new domain, due to a small labeled data set and imbalance relation distributions. Our framework leverages on both labeled and unlabeled data in the target domain. First, we determine the relevance of each source domain to the target domain for each relation type, using the consistency between the clustering given by the target domain labels and the clustering given by the predictors trained for the source domain. To overcome the lack of labeled samples for rarer relations, these clusterings operate on both the labeled and unlabeled data in the target domain. Second, we trade-off between using relevance-weighted sourcedomain predictors and the labeled target data. Again, to overcome the imbalance distribution, the source-domain predictors operate on the unlabeled target data. Our method outperforms numerous baselines and a weakly-supervised relation extraction method on ACE 2004 and YAGO.
