Abstract | Since no large amount of labeled training data for our new notion of sentiment relevance is available, we investigate two semi-supervised methods for creating sentiment relevance classifiers: a distant supervision approach that leverages structured information about the domain of the reviews; and transfer learning on feature representations based on lexical taxonomies that enables knowledge transfer. |
Distant Supervision | In this section, we show how to bootstrap a sentiment relevance classifier by distant supervision (DS) . |
Distant Supervision | Even though we do not have sentiment relevance annotations, there are sources of metadata about the movie domain that we can leverage for distant supervision . |
Distant Supervision | We call these labels inferred from NE metadata distant supervision (DS) labels. |
Features | Distant supervision and transfer learning are settings where exact training data is unavailable. |
Introduction | The first approach is distant supervision (DS). |
Introduction | results of our experiments on distant supervision (Section 6) and transfer learning (Section 7). |
Related Work | Their setup differs from ours as our focus lies on pattern-based distant supervision instead of distant supervision using documents for sentence classification. |
Abstract | Distant supervision usually utilizes only unlabeled data and existing knowledge bases to learn relation extraction models. |
Abstract | In this paper, we demonstrate how a state-of-the-art multi-instance multi-label model can be modified to make use of these reliable sentence-level labels in addition to the relation-level distant supervision from a database. |
Available at http://nlp. stanford.edu/software/mimlre. shtml. | We also compare Guided DS with three state-of-the-art models: 1) MultiR and 2) MIML are two distant supervision models that support multi-instance learning and overlapping relations; 3) Mintz++ is a single-instance learning algorithm for distant supervision . |
Guided DS | Our goal is to jointly model human-labeled ground truth and structured data from a knowledge base in distant supervision . |
Introduction | 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). |
Introduction | One of most crucial problems in distant supervision is the inherent errors in the automatically generated training data (Roth et al., 2013). |
Introduction | Surdeanu et al., 2012) have been proposed to address the issue by loosening the distant supervision assumption. |
The Challenge | Simply taking the union of the hand-labeled data and the corpus labeled by distant supervision is not effective since hand-labeled data will be swamped by a larger amount of distantly labeled data. |
Abstract | Our experiments use Freebase, a large semantic database of several thousand relations, to provide distant supervision . |
Architecture | The intuition of our distant supervision approach is to use Freebase to give us a training set of relations and entity pairs that participate in those relations. |
Architecture | The distant supervision assumption is that if two entities participate in a relation, any sentence that contain those two entities might express that relation. |
Discussion | Our results show that the distant supervision algorithm is able to extract high-precision patterns for a reasonably large number of relations. |
Introduction | Distant supervision is an extension of the paradigm used by Snow et al. |
Introduction | Our algorithm uses Freebase (Bollacker et al., 2008), a large semantic database, to provide distant supervision for relation extraction. |
Introduction | The intuition of distant supervision is that any sentence that contains a pair of entities that participate in a known Freebase relation is likely to express that relation in some way. |
Previous work | Perhaps most similar to our distant supervision algorithm is the effective method of Wu and Weld (2007) who extract relations from a Wikipedia page by using supervision from the page’s infobox. |
Discussion and Future Work | Our discriminative joint models treat latent syntax as a structured-feature to be optimized for the end-task of SRL, while our other grammar induction techniques optimize for unlabeled data likelihood—optionally with distant supervision . |
Experiments | WSJ"o Distant Supervision SAJM’ 10 44.8 none SAJ’ 13 64.4 none _ SJA’10 _ _ _ _ _ _ ' _ _5_O._4_ _HT_ML_ _ _ ' NB’ 11 59.4 ACE05 _ DMVZbE) _ _ _ _ _ ' _ ‘24—8_ _n_one_ _ _ _ ' DMV+C (bc) 44.8 SRL Marginalized, IGC 48.8 SRL Marginalized, IGB 5 8 .9 SRL |
Experiments | Interestingly, the marginalized grammars best the DMV grammar induction method; however, this difference is less pronounced when the DMV is constrained using SRL labels as distant supervision . |
Experiments | We contrast with methods using distant supervision (Naseem and Barzilay, 2011; Spitkovsky et al., 2010b) and fully unsupervised dependency parsing (Spitkovsky et al., 2013). |
Introduction | In the pipeline models, we develop a novel approach to unsupervised grammar induction and explore performance using SRL as distant supervision . |
Related Work | In our low-resource pipelines, we assume that the syntactic parser is given no labeled parses—however, it may optionally utilize the semantic parses as distant supervision . |
Related Work | Grammar induction work has further demonstrated that distant supervision in the form of ACE-style relations (Naseem and Barzilay, 2011) or HTML markup (Spitkovsky et al., 2010b) can lead to considerable gains. |
Abstract | We present an approach to training a joint syntactic and semantic parser that combines syntactic training information from CCGbank with semantic training information from a knowledge base via distant supervision . |
Parameter Estimation | Distant supervision is provided by the following constraint: every relation instance 7“(€1,€2) E K must be expressed by at least one sentence in 8031,62), the set of sentences that mention both 61 and 62 (Hoffmann et al., 2011). |
Parameter Estimation | tures of the best set of parses that satisfy the distant supervision constraint. |
Parameter Estimation | This maximization is intractable due to the coupling between logical forms in E caused by enforcing the distant supervision constraint. |
Prior Work | The parser presented in this paper can be viewed as a combination of both a broad coverage syntactic parser and a semantic parser trained using distant supervision . |
Abstract | In addition to traditional linguistic features used in distant supervision for information extraction, our approach also takes into account network information, a unique opportunity offered by social media. |
Conclusion and Future Work | We construct the publicly available dataset based on distant supervision and experiment our model on three useful user profile attributes, i.e., Education, Job and Spouse. |
Introduction | Inspired by the concept of distant supervision , we collect training tweets by matching attribute ground truth from an outside “knowledge base” such as Facebook or Google Plus. |
Model | The distant supervision assumes that if entity 6 corresponds to an attribute for user i, at least one posting from user i’s Twitter stream containing a mention of 6 might express that attribute. |
Related Work | Distant Supervision Distant supervision , also known as weak supervision, is a method for leam-ing to extract relations from text using ground truth from an existing database as a source of supervision. |
Related Work | 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). |
Related Work | 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 |
Conclusions | We have also studied the limits of the distant supervision approach to relation extraction, showing empirically that its performance depends not only on the nature of reference knowledge base and document corpus (Riedel et al., 2010), but also on the relation to be extracted. |
Conclusions | Given a relation between two arguments, if it is not dominant among textual expressions of those arguments, the distant supervision assumption will be more often violated. |
Distant Supervised Relation Extraction | 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). |
Distant Supervised Relation Extraction | Our document-level distant supervision assumption is that if entity and value are found in a document graph (see section 3), and there is a path connecting them, then the document expresses the relation. |
Evaluation | Second, the distant supervision assumption underlying our approach is that for a seed relation instance (entity, relation, value), any textual mention of entity and value expresses the relation. |
Introduction | Our system (see Figure l) extracts relational facts from text using distant supervision (Mintz et al., 2009) and then anchors the relation to an interval of temporal validity. |
Discussion | We have mentioned that the basic alignment assumption of distant supervision (Mintz et al., 2009) tends to generate noisy (noisy features and |
Introduction | Therefore, the distant supervision paradigm may generate incomplete labeling corpora. |
Introduction | To the best of our knowledge, we are the first to apply this technique on relation extraction with distant supervision . |
Related Work | The idea of distant supervision was firstly proposed in the field of bioinformatics (Craven and Kumlien, 1999). |
Related Work | 11It is the abbreviation for Distant supervision for Relation extraction with Matrix Completion |
Related Work | However, they did not concern about the data noise brought by the basic assumption of distant supervision . |
Abstract | We leverage distant supervision using relations from the knowledge base FreeBase, but do not require any manual heuristic nor manual seed list selections. |
Conclusions | We have described a new distant supervision model with which to learn patterns for relation extraction with no manual intervention. |
Introduction | 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. |
Unsupervised relational pattern learning | Similar to other distant supervision methods, our approach takes as input an existing knowledge base containing entities and relations, and a textual corpus. |
Unsupervised relational pattern learning | One of the most important problems to solve in distant supervision approaches is to be able to distinguish which of the textual examples that include two related entities, 67; and 63-, are supporting the relation. |
Abstract | 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. |
Abstract | We present a novel generative model that directly models the heuristic labeling process of distant supervision . |
Introduction | A particularly attractive approach, called distant supervision (DS), creates labeled data by heuristically aligning entities in text with those in a knowledge base, such as Freebase (Mintz et al., 2009). |
Introduction | Figure 1: Automatic labeling by distant supervision . |
Related Work | The increasingly popular approach, called distant supervision (DS), or weak supervision, utilizes a knowledge base to heuristically label a corpus (Wu and Weld, 2007; Bellare and McCallum, 2007; Pal |
Experiments | We also use two distant supervision approaches for the comparison. |
Related Work | Distant supervision (DS) is a semi-supervised RE framework and has attracted many attentions (Bunescu, 2007; Mintz et al., 2009; Yao et al., 2010; Surdeanu et al., 2010; Hoffmann et al., 2011; Surdeanu et al., 2012). |
Related Work | (2013) utilize relation cardinality to create negative samples for distant supervision while we use both implicit type clues and relation cardinality expectations to discover possible inconsistencies among local predictions. |
The Framework | 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. |
Evaluation Setup | While it is possible to train these parameters via direct annotation of messages with label sequences, we opted instead to use a simple approach where message tokens from the training weekend are labeled via their intersection with gold records, often called “distant supervision” (Mintz et al., 2009b). |
Model | The weights of the CRF component of our model, QSEQ, are the only weights learned at training time, using a distant supervision process described in Section 6. |
Related Work | Our work also relates to recent approaches for relation extraction with distant supervision (Mintz et al., 2009b; Bunescu and Mooney, 2007; Yao et al., 2010a). |
Abstract | We test the DCNN in four experiments: small scale binary and multi-class sentiment prediction, six-way question classification and Twitter sentiment prediction by distant supervision . |
Experiments | 5.4 TWitter Sentiment Prediction with Distant Supervision |
Introduction | The fourth experiment involves predicting the sentiment of Twitter posts using distant supervision (Go et al., 2009). |
Abstract | Annotation errors can significantly hurt classifier performance, yet datasets are only growing noisier with the increased use of Amazon Mechanical Turk and techniques like distant supervision that automatically generate labels. |
Introduction | Low-quality annotations have become even more common in recent years with the rise of Amazon Mechanical Turk, as well as methods like distant supervision and co-training that involve automatically generating training data. |
Introduction | Although small amounts of noise may not be detrimental, in some applications the level can be high: upon manually inspecting a relation extraction corpus commonly used in distant supervision , Riedel et al. |
Background | Recently, “distant supervision” has emerged to be a popular choice for training relation extractors without using manually labeled data (Mintz et al., 2009; J iang, 2009; Chan and Roth, 2010; Wang et al., 2011; Riedel et al., 2010; Ji et al., 2011; Hoffmann et al., 2011; Sur-deanu et al., 2012; Takamatsu et al., 2012; Min et al., 2013). |
Identifying Key Medical Relations | This ( distant supervision ) approach resulted in a huge amount of sentences that contain the desired relations, but also brought in a lot of noise in the form of false positives. |
Relation Extraction with Manifold Models | This feature is useful when the training data comes from “crowdsourcing” or “distant supervision” . |