Abstract | In this paper, we show how these results can be exploited to improve parsing accuracy by integrating a graph-based and a transition-based model. |
Integrated Models | For the graph-based model, X is the set of possible dependency arcs (2,7,1); for the transition-based model, X is the set of possible configuration-transition pairs (0,75). |
Integrated Models | 3.2 The Guided Graph-Based Model |
Introduction | Practically all data-driven models that have been proposed for dependency parsing in recent years can be described as either graph-based or transition-based (McDonald and Nivre, 2007). |
Introduction | In graph-based parsing, we learn a model for scoring possible dependency graphs for a given sentence, typically by factoring the graphs into their component arcs, and perform parsing by searching for the highest-scoring graph. |
Introduction | The graph-based models are globally trained and use exact inference algorithms, but define features over a limited history of parsing decisions. |
Two Models for Dependency Parsing | 2.2 Graph-Based Models |
Two Models for Dependency Parsing | Graph-based dependency parsers parameterize a model over smaller substructures in order to search the space of valid dependency graphs and produce the most likely one. |
Two Models for Dependency Parsing | An advantage of graph-based methods is that tractable inference enables the use of standard structured learning techniques that globally set parameters to maximize parsing performance on the training set (McDonald et al., 2005a). |
Abstract | This paper introduces a graph-based semi-supervised joint model of Chinese word segmentation and part-of-speech tagging. |
Abstract | The proposed approach is based on a graph-based label propagation technique. |
Background | 3.2 Graph-based Label Propagation |
Background | Graph-based label propagation, a critical subclass of semi-supervised learning (SSL), has been widely used and shown to outperform other SSL methods (Chapelle et al., 2006). |
Background | Typically, graph-based label propagation algorithms are run in two main steps: graph construction and label propagation. |
Introduction | This study focuses on using a graph-based label propagation method to build a semi-supervised joint S&T model. |
Introduction | Graph-based label propagation methods have recently shown they can outperform the state-of-the-art in several natural language processing (NLP) tasks, e.g., POS tagging (Subramanya et al., 2010), knowledge acquisition (Talukdar et al., 2008), shallow semantic parsing for unknown predicate (Das and Smith, 2011). |
Introduction | Motivated by the works in (Subramanya et al., 2010; Das and Smith, 2011), for structured problems, graph-based label propagation can be employed to infer valuable syntactic information (n-gram-level label distributions) from labeled data to unlabeled data. |
Method | The proposed approach employs a transductive graph-based label propagation method to acquire such gainful information, i.e., label distributions from a similarity graph constructed over labeled and unlabeled data. |
Related Work | (2010) proposed a graph-based self-train style semi-supervised CRFs algorithm. |
Abstract | We propose a computationally efficient graph-based approach for local coherence modeling. |
Experiments | We evaluate the ability of our graph-based model to estimate the local coherence of a textual document with three different experiments. |
Experiments | 3Our graph-based model obtains for the discrimination task an accuracy of 0.846 and 0.635 on the ACCIDENTS and EARTHQUAKES datasets, respectively, compared to 0.904 and 0.872 as reported by Barzilay and Lapata (2008). |
Experiments | Table 3: Discrimination, reproduced baselines (B&L: Barzilay and Lapata (2008); E&C Elsner and Charniak (2011)) vs. graph-based |
Introduction | Similar to the application of graph-based methods in other areas of NLP (e.g. |
Introduction | work on word sense disambiguation by Navigli and Lapata (2010); for an overview over graph-based methods in NLP see Mihalcea and Radev (2011)) we model local coherence by relying only on centrality measures applied to the nodes in the graph. |
Introduction | We apply our graph-based model to the three tasks handled by Barzilay and Lapata (2008) to show that it provides the same flexibility over disparate tasks as the entity grid model: sentence ordering (Section 4.1), summary coherence ranking (Section 4.2), and readability assessment (Section 4.3). |
Method | In contrast to Barzilay and Lapata’s entity grid that contains information about absent entities, our graph-based representation only contains “positive” information. |
Method | From this graph-based representation, the local coherence of a text T can be measured by computing the average outdegree of a projection graph P. This centrality measure was chosen for two main reasons. |
Experiments and Analysis | McDonald and Pereira (2006) propose a second-order graph-based parser, but use a smaller feature set than our work. |
Experiments and Analysis | K00 and Collins (2010) propose a third-order graph-based parser. |
Introduction | For example, Koo and Collins (2010) and Zhang and McDonald (2012) show that incorporating higher-order features into a graph-based parser only leads to modest increase in parsing accuracy. |
Introduction | To construct parse forest on unlabeled data, we employ three supervised parsers based on different paradigms, including our baseline graph-based dependency parser, a transition-based dependency parser (Zhang and Nivre, 2011), and a generative constituent parser (Petrov and Klein, 2007). |
Supervised Dependency Parsing | The graph-based method views the problem as finding an optimal tree from a fully-connected directed graph (McDonald et al., 2005; McDonald and Pereira, 2006; Carreras, 2007; K00 and Collins, 2010), while the transition-based method tries to find a highest-scoring transition sequence that leads to a legal dependency tree (Yamada and Matsumoto, 2003; Nivre, 2003; Zhang and Nivre, 2011). |
Supervised Dependency Parsing | 2.1 Graph-based Dependency Parser (GParser) |
Supervised Dependency Parsing | In this work, we adopt the graph-based paradigm because it allows us to naturally derive conditional probability of a dependency tree (1 given a sentence X, which is required to compute likelihood of both labeled and unlabeled data. |
Abstract | We convert such graph-based translation consensus from similar source strings into useful features both for n-best output re-ranking and for decoding algorithm. |
Graph-based Structured Learning | In general, a graph-based model assigns labels to instances by considering the labels of similar instances. |
Graph-based Structured Learning | The gist of graph-based model is that, if two instances are connected by a strong edge, then their labels tend to be the same (Zhu, 2005). |
Graph-based Structured Learning | This scenario differs from the general case of graph-based model in two aspects. |
Graph-based Translation Consensus | Our MT system with graph-based translation consensus adopts the conventional log-linear model. |
Graph-based Translation Consensus | Based on the commonly used features, two kinds of feature are added to equation (1), one is graph-based consensus features, which are about consensus among the translations of similar sentences/spans; the other is local consensus features, which are about consensus among the translations of the same sentence/span. |
Introduction | Alexandrescu and Kirchhoff (2009) proposed a graph-based semi-supervised model to re-rank n-best translation output. |
Introduction | In this paper, we attempt to leverage translation consensus among similar (spans of) source sentences in bilingual training data, by a novel graph-based model of translation consensus. |
Abstract | We compare two parsing models for temporal dependency structures, and show that a deterministic non-projective dependency parser outperforms a graph-based maximum spanning tree parser, achieving labeled attachment accuracy of 0.647 and labeled tree edit distance of 0.596. |
Discussion and Conclusions | Comparing the two dependency parsing models, we have found that a shift-reduce parser, which more closely mirrors the incremental processing of our human annotators, outperforms a graph-based maximum spanning tree parser. |
Evaluations | Table 2: Features for the shift-reduce parser (SRP) and the graph-based maximum spanning tree (MST) parser. |
Evaluations | The Shift-Reduce parser (SRP; Section 4.1) and the graph-based , maximum spanning tree parser (MST; Section 4.2) are compared to these baselines. |
Evaluations | It has been argued that graph-based models like the maximum spanning tree parser should be able to produce more globally consistent and correct dependency trees, yet we do not observe that here. |
Feature Design | The shift-reduce parser (SRP) trains a machine learning classifier as the oracle 0 E (C —> T) to predict a transition 75 from a parser configuration 0 2 (L1, L2, Q, E), using node features such as the heads of L1, L2 and Q, and edge features from the already predicted temporal relations in E. The graph-based maximum spanning tree (MST) parser trains a machine learning model to predict SCORE(e) for an edge e = (107;, rj, wk), using features of the nodes w, and wk. |
Parsing Models | We consider two different approaches to learning a temporal dependency parser: a shift-reduce model (Nivre, 2008) and a graph-based model (McDonald et al., 2005). |
Parsing Models | 4.2 Graph-Based Parsing Model |
Parsing Models | Graph-based models are an alternative dependency parsing model, which assembles a graph with weighted edges between all pairs of words, and selects the tree-shaped subset of this graph that gives the highest total score (Fig. |
Abstract | 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. |
Cross-lingual Annotation Projection for Relation Extraction | To solve both of these problems at once, we propose a graph-based projection approach for relation extraction. |
Graph Construction | The most crucial factor in the success of graph-based learning approaches is how to construct a graph that is appropriate for the target task. |
Graph Construction | Das and Petrov (Das and Petrov, 2011) proposed a graph-based bilingual projection of part-of-speech tagging by considering the tagged words in the source language as labeled examples and connecting them to the unlabeled words in the target language, while referring to the word alignments. |
Graph Construction | The graph for our graph-based projection is constructed by connecting related vertex pairs by weighted edges. |
Implementation | To demonstrate the effectiveness of the graph-based projection approach for relation extraction, we developed a Korean relation extraction system that was trained with projected annotations from English resources. |
Implementation | Table 1: Comparison between direct and graph-based projection approaches to extract semantic relationships for four relation types |
Implementation | The graph-based projection was performed by the Junto toolkit 4 with the maximum number of iterations of 10 for each execution. |
Introduction | In this paper, we propose a graph-based projection approach for weakly supervised relation extraction. |
Introduction | The goal of our graph-based approach is to improve the robustness of the extractor with respect to errors that are generated and accumulated by preprocessors. |
Label Propagation | To induce labels for all of the unlabeled vertices on the graph constructed in Section 3, we utilize the label propagation algorithm (Zhu and Ghahramani, 2002), which is a graph-based semi-supervised learning algorithm. |
Abstract | Most previous graph-based parsing models increase decoding complexity when they use high-order features due to exact-inference decoding. |
Abstract | In this paper, we present an approach to enriching high—order feature representations for graph-based dependency parsing models using a dependency language model and beam search. |
Experiments | Table 7 shows the performance of the graph-based systems that were compared, where McDonald06 refers to the second-order parser of McDonald |
Implementation Details | We implement our parsers based on the MSTParserl, a freely available implementation of the graph-based model proposed by (McDonald and Pereira, 2006). |
Introduction | Among them, graph-based dependency parsing models have achieved state-of-the-art performance for a wide range of Ian-guages as shown in recent CoNLL shared tasks |
Introduction | In the graph-based models, dependency parsing is treated as a structured prediction problem in which the graphs are usually represented as factored structures. |
Introduction | How to enrich high-order feature representations without increasing the decoding complexity for graph-based models becomes a very challenging problem in the dependency parsing task. |
Parsing with dependency language model | 3.1 Graph-based parsing model |
Parsing with dependency language model | The graph-based parsing model aims to search for the maximum spanning tree (MST) in a graph (McDonald et al., 2005). |
Abstract | The second one is a graph-based method, which incorporates topic and sentiment information, as well as additional information about sentence-to-sentence relations extracted based on dialogue structure. |
Abstract | In particular, we find that incorporating dialogue structure in the graph-based method contributes to the improved system performance. |
Experiments | In the graph-based method, the best parameters are Asim = 0,)\adj = 0.3,Arel = 0.4,Asent = 0.3. |
Experiments | This is different from graph-based summarization systems for text domains. |
Experiments | When compared to abstractive reference summaries, the graph-based method is slightly better. |
Introduction | widely used in extractive summarization: sentence-ranking and graph-based methods. |
Introduction | Furthermore, in the graph-based method, we propose to better incorporate the dialogue structure information in the graph in order to select salient summary utterances. |
Opinion Summarization Methods | The second one is a graph-based method, which incorporates the dialogue structure in ranking. |
Opinion Summarization Methods | 4.2 Graph-based Summarization |
Opinion Summarization Methods | Graph-based methods have been widely used in document summarization. |
Abstract | We present a graph-based semi-supervised learning for the question-answering (QA) task for ranking candidate sentences. |
Abstract | With a new representation of graph-based SSL on QA datasets using only a handful of features, and under limited amounts of labeled data, we show improvement in generalization performance over state-of-the-art QA models. |
Conclusions and Discussions | In this paper, we applied a graph-based SSL algorithm to improve the performance of QA task by exploiting unlabeled entailment relations between affirmed question and candidate sentence pairs. |
Conclusions and Discussions | We demonstrated that summarization on graph-based SSL can improve the QA task performance when more unlabeled data is used to learn the classifier model. |
Experiments | We evaluated the performance of graph-based QA system using a set of 202 questions from the TREC04 as testing dataset (Voorhees, 2003), (Prager et al., 2000). |
Graph Based Semi-Supervised Learning for Entailment Ranking | In general graph-based SSL, a function over the graph is estimated such that it satisfies two conditions: 1) close to the observed labels , and 2) be smooth on the whole graph by: |
Graph Based Semi-Supervised Learning for Entailment Ranking | Most graph-based SSLs are transductive, i.e., not easily expendable to new test points outside L U U. |
Graph Summarization | Research on graph-based SSL algorithms point out their effectiveness on real applications, e.g., (Zhu et al., 2003), (Zhou and Scholkopf, 2004), (Sindhwani et al., 2007). |
Graph Summarization | Using graph-based SSL method on the new representative dataset, X’ = X U XTe, which is comprised of summarized dataset, X = {Xifizy as labeled data points, and the testing dataset, XTe as unlabeled data points. |
Introduction | Recent research indicates that using labeled and unlabeled data in semi-supervised learning (SSL) environment, with an emphasis on graph-based methods, can improve the performance of information extraction from data for tasks such as question classification (Tri et al., 2006), web classification (Liu et al., 2006), relation extraction (Chen et al., 2006), passage-retrieval (Otterbacher et al., 2009), various natural language processing tasks such as part-of-speech tagging, and named-entity recognition (Suzuki and Isozaki, 2008), word-sense disam- |
Introduction | We construct a textual entailment (TE) module by extracting features from each paired question and answer sentence and designing a classifier with a novel yet feasible graph-based SSL method. |
Approach Overview | Graph-based optimization as the third step to further boost the performance by taking the related tweets into consideration. |
Conclusions and Future Work | In addition, different from previous work using only information on the current tweet for sentiment classification, we propose to take the related tweets of the current tweet into consideration by utilizing graph-based optimization. |
Conclusions and Future Work | According to the experimental results, the graph-based optimization significantly improves the performance. |
Experiments | 6.4 Evaluation of Graph-based Optimization |
Experiments | For these tweets, our graph-based optimization approach will have no effect. |
Experiments | Target-dependent sentiment classifier +Graph-based optimization |
Graph-based Sentiment Optimization | If we consider that the sentiment of a tweet only depends on its content and immediate neighbors, we can leverage a graph-based method for sentiment classification of tweets. |
Experiments | * SSL-Graph: A SSL model presented in (Subramanya et al., 2010) that uses graph-based leam-ing as posterior tag smoother for CRF model using Eq. |
Experiments | For graph-based learning, we implemented the algorithm presented in (Subramanya et al., 2010) and used the same hyper-parameters and features. |
Related Work and Motivation | Recent adaptation methods for SSL use: expectation minimization (Daumé-III, 2010) graph-based learning (Chapelle et al., 2006; Zhu, 2005), etc. |
Related Work and Motivation | In (Subramanya et al., 2010) an efficient iterative SSL method is described for syntactic tagging, using graph-based learning to smooth POS tag posteriors. |
Semi-Supervised Semantic Labeling | The unlabeled POS tag posteriors are then smoothed using a graph-based learning algorithm. |
Semi-Supervised Semantic Labeling | Graph-based SSL defines a new CRF objective function: |
Semi-Supervised Semantic Labeling | smoothing model, instead of a graph-based model, as follows: |
Abstract | We use graph-based label propagation for cross-lingual knowledge transfer and use the projected labels as features in an unsupervised model (Berg—Kirkpatrick et al., 2010). |
Conclusion | We have shown the efficacy of graph-based label propagation for projecting part-of-speech information across languages. |
Experiments and Results | To provide a thorough analysis, we evaluated three baselines and two oracles in addition to two variants of our graph-based approach. |
Experiments and Results | We tried two versions of our graph-based approach: |
Graph Construction | In graph-based learning approaches one constructs a graph whose vertices are labeled and unlabeled examples, and whose weighted edges encode the degree to which the examples they link have the same label (Zhu et al., 2003). |
Graph Construction | Note, however, that it would be possible to use our graph-based framework also for completely unsupervised POS induction in both languages, similar to Snyder et al. |
Introduction | First, we use a novel graph-based framework for projecting syntactic information across language boundaries. |
Dependency Parsing | There has been much recent work on dependency parsing using graph-based , transition-based, and hybrid methods; see Nivre and McDonald (2008) for an overview. |
Dependency Parsing | Typical graph-based methods consider linear classifiers of the form |
Dependency Parsing as an ILP | Our approach will build a graph-based parser without the drawback of a restriction to local features. |
Experiments | baselines, all of them state-of-the-art parsers based on non-arc-factored models: the second order model of McDonald and Pereira (2006), the hybrid model of Nivre and McDonald (2008), which combines a (labeled) transition-based and a graph-based parser, and a refinement of the latter, due to Martins et al. |
Experiments | Comparing with the baselines, we observe that our full model outperforms that of McDonald and Pereira (2006), and is in line with the most accurate dependency parsers (Nivre and McDonald, 2008; Martins et al., 2008), obtained by combining transition-based and graph-based parsers.14 Notice that our model, compared with these hybrid parsers, has the advantage of not requiring an ensemble configuration (eliminating, for example, the need to tune two parsers). |
Experiments | 13Unlike our model, the hybrid models used here as baselines make use of the dependency labels at training time; indeed, the transition-based parser is trained to predict a labeled dependency parse tree, and the graph-based parser use these predicted labels as input features. |
Introduction | In order to address these unique challenges for wikification for the short tweets, we employ graph-based semi-supervised learning algorithms (Zhu et al., 2003; Smola and Kondor, 2003; Blum et al., 2004; Zhou et al., 2004; Talukdar and Crammer, 2009) for collective inference by exploiting the manifold (cluster) structure in both unlabeled and labeled data. |
Introduction | effort to explore graph-based semi-supervised learning algorithms for the wikification task. |
Related Work | Non-collective methods usually rely on prior popularity and context similarity with supervised models (Mihalcea and Csomai, 2007; Milne and Witten, 2008b; Han and Sun, 2011), while collective approaches further leverage the global coherence between concepts normally through supervised or graph-based re-ranking models (Cucerzan, 2007; Milne and Witten, 2008b; Han and Zhao, 2009; Kulkarni et al., 2009; Pennacchiotti and Pantel, 2009; Ferragina and Scaiella, 2010; Fernandez et al., 2010; Radford et al., 2010; Cucerzan, 2011; Guo et al., 2011; Han and Sun, 2011; Han et al., 2011; Ratinov et al., 2011; Chen and Ji, 2011; Kozareva et al., 2011; Cassidy et al., 2012; Shen et al., 2013; Liu et al., 2013). |
Related Work | This work is also related to graph-based semi-supervised learning (Zhu et al., 2003; Smola and Kondor, 2003; Zhou et al., 2004; Talukdar and Crammer, 2009), which has been successfully applied in many Natural Language Processing tasks (Niu et al., 2005; Chen et al., 2006). |
Relational Graph Construction | Compared to the referent graph which considers each mention or concept as a node in previous graph-based re-ranking approaches (Han et al., 2011; Shen et al., 2013), our |
Relational Graph Construction | (ii) It is more appropriate for our graph-based semi-supervised model since it is difficult to assign labels to a pair of mention and concept in the referent graph. |
Semi-supervised Graph Regularization | We propose a novel semi-supervised graph regularization framework based on the graph-based semi-supervised learning algorithm (Zhu et al., 2003): |
Analysis | (Grineva et al., 2009) [X] News Graph-based ranking (DUC for extended neighborhood 28.8 35.4 31.7 -2001) (Wan and Xiao, 2008b) [><] Papers Statistical, semantic, and |
Keyphrase Extraction Approaches | 3.3.1 Graph-Based Ranking |
Keyphrase Extraction Approaches | The basic idea behind a graph-based approach is to build a graph from the input document and rank its nodes according to their importance using a graph-based ranking method (e.g., Erin and Page (1998)). |
Keyphrase Extraction Approaches | TextRank (Mihalcea and Tarau, 2004) is one of the most well-known graph-based approaches to keyphrase extraction. |
Experiments & Results 4.1 Experimental Setup | For evaluating our baseline as well as graph-based approaches, we use both intrinsic and extrinsic evaluations. |
Experiments & Results 4.1 Experimental Setup | 4.3.1 Graph-based Results |
Graph-based Lexicon Induction | Graph-based approaches can easily become com-putationally very expensive as the number of nodes grow. |
Related work | (2010) used linguistic analysis in the form of graph-based models instead of a vector space. |
Related work | Graph-based semi-supervised methods have been shown to be useful for domain adaptation in MT as well. |
Related work | Alexandrescu and Kirchhoff (2009) applied a graph-based method to determine similarities between sentences and use these similarities to promote similar translations for similar sentences. |
Introduction | In recent years, graph-based methods have attracted considerable attentions (Mihalcea, 2005; Navigli and Lapata, 2007; Agirre and Soroa, 2009). |
Introduction | On the graph structure of lexical knowledge base (LKB), random-walk or other well-known graph-based techniques have been applied to find mutually related senses among target words. |
Introduction | Unlike earlier studies disambiguating word-by-word, the graph-based methods obtain sense-interdependent solution for target words. |
Related Work | As described in Section 1, graph-based WSD has been extensively studied, since graphs are favorable structure to deal with interactions of data on vertices. |
Related Work | Our method can be viewed as one of graph-based methods, but it regards input-t0-class mapping as vertices, and the edges represent the relations both together in context and in sense. |
Related Work | Mihalcea (2005) proposed graph-based methods, whose vertices are sense label hypotheses on word sequence. |
Abstract | In this work, we present a semi-supervised graph-based approach for generating new translation rules that leverages bilingual and monolingual data. |
Generation & Propagation | Otherwise it is called an unlabeled phrase, and our algorithm finds labels (translations) for these unlabeled phrases, with the help of the graph-based representation. |
Introduction | Our work introduces a new take on the problem using graph-based semi-supervised learning to acquire translation rules and probabilities by leveraging both monolingual and parallel data resources. |
Related Work | Recent improvements to BLI (Tamura et al., 2012; Irvine and Callison-Burch, 2013b) have contained a graph-based flavor by presenting label propagation-based approaches using a seed lexicon, but evaluation is once again done on top-1 or top-3 accuracy, and the focus is on unigrams. |
Related Work | (2013) and Irvine and Callison-Burch (2013a) conduct a more extensive evaluation of their graph-based BLI techniques, where the emphasis and end-to-end BLEU evaluations concentrated on OOVs, i.e., unigrams, and not on enriching the entire translation model. |
Related Work | aged to have similar target language translations, has also been explored via a graph-based approach (Alexandrescu and Kirchhoff, 2009). |
Related Works | Both the graph-based (McDonald et al., 2005a; McDonald and Pereira, 2006; Carreras et al., 2006) and the transition-based (Yamada and Matsumoto, 2003; Nivre et al., 2006) parsing algorithms are related to our word-pair classification model. |
Related Works | Similar to the graph-based method, our model is factored on dependency edges, and its decoding procedure also aims to find a maximum spanning tree in a fully connected directed graph. |
Related Works | From this point, our model can be classified into the graph-based category. |
Word-Pair Classification Model | Previous graph-based dependency models usually use the index distance of word 7' and word j |
A Multigraph Model | Work on graph-based models similar to ours report robustness with regard to the amount of training data used (Cai et al., 2011b; Cai et al., 2011a; Martschat et al., 2012). |
Conclusions and Future Work | We presented an unsupervised graph-based model for coreference resolution. |
Introduction | In this paper we present a graph-based approach for coreference resolution that models a document to be processed as a graph. |
Related Work | Graph-based coreference resolution. |
Related Work | While not developed within a graph-based framework, factor-based approaches for pronoun resolution (Mitkov, 1998) can be regarded as greedy clustering in a multigraph, where edges representing factors for pronoun resolution have negative or positive weight. |
Experiments | DWSA stands for Dijkstra-WSA, the state-of-the-art graph-based alignment approach of Matuschek and Gurevych (2013). |
Introduction | However, not all lexical resources provide explicit semantic relations between concepts and, hence, machine-readable dictionaries like Wiktionary have first to be transformed into semantic graphs before such graph-based approaches can be applied to them. |
Related Work | Last year Matuschek and Gurevych (2013) proposed Dijkstra-WSA, a graph-based approach relying on shortest paths between two concepts when the two corresponding resources graphs were combined by leveraging monosemous linking. |
Resource Alignment | The structural similarity component, instead, is a novel graph-based similarity measurement technique which calculates the similarity between a pair of concepts across the semantic networks of the two resources by leveraging the semantic |
Abstract | Second, we use two graph-based summarization approaches, Generalized ClueWordSummarizer and Page-Rank, to extract sentences as summaries. |
Abstract | Third, we propose a summarization approach based on subjective opinions and integrate it with the graph-based ones. |
Related Work | Finally, we did not compared CWS to other possible graph-based approaches as we propose in this paper. |
Summarization with Subjective Opinions | Other than the conversation structure, the measures of cohesion and the graph-based summarization methods we have proposed, the importance of a sentence in emails can be captured from other aspects. |
Abstract | We develop graph-based ranking models that automatically select the best output from multiple redundant versions of translations and edits, and improves translation quality closer to professionals. |
Evaluation | Using the raw translations without post-editing, our graph-based ranking method achieves a BLEU score of 38.89, compared to Zaidan and Callison-Burch (2011)’ s reported score of 28.13, which they achieved using a linear feature-based classification. |
Evaluation | In contrast, our proposed graph-based ranking framework achieves a score of 41.43 when using the same information. |
Introduction | 0 A new graph-based algorithm for selecting the best translation among multiple translations of the same input. |
Connotation Induction Algorithms | Limitations of Graph-based Algorithms |
Connotation Induction Algorithms | Although graph-based algorithms (§2.l, §2.2) provide an intuitive framework to incorporate various lexical relations, limitations include: |
Connotation Induction Algorithms | Addressing limitations of graph-based algorithms (§2.2), we propose an induction algorithm based on Integer Linear Programming (ILP). |
Experimental Result I | The [OVERLAY], which is based on both Pred-Arg and Arg-Arg subgraphs (§2.2), achieves the best performance among graph-based algorithms, significantly improving the precision over all other baselines. |
MUSE — MUltilingual Sentence Extractor | In contrast, representation used by the graph-based methods (except for TextRank) is based on the word-based graph representation models described in (Schenker et al., 2004). |
Related Work | Today, graph-based text representations are becoming increasingly popular, due to their ability to enrich the document model with syntactic and semantic relations. |
Related Work | (1997) were among the first to make an attempt at using graph-based ranking methods in single document extractive summarization, generating similarity links between document paragraphs and using degree scores in order to extract the important paragraphs from the text. |
Related Work | Erkan and Radev (2004) and Mihalcea (2005) introduced algorithms for unsupervised extractive summarization that rely on the application of iterative graph-based ranking algorithms, such as PageRank (Erin and Page, 1998) and HITS (Kleinberg, 1999). |
Related Work | There were also many works employed graph-based method (Li et al., 2012; Zhang et al., 2010; Hassan and Radev, 2010; Liu et al., 2012), but none of previous works considered confidence of patterns in the graph. |
The First Stage: Sentiment Graph Walking Algorithm | In the first stage, we propose a graph-based algorithm called Sentiment Graph Walking to mine opinion words and opinion targets from reviews. |
The First Stage: Sentiment Graph Walking Algorithm | We can see that our graph-based methods (Ours-Bigraph and 0urs-Stage1 ) achieve higher recall than Zhang. |
Experiments | In such situation, the graph-based ranking algorithm in the second component will be apt to be affected by the frequency information, so the final performance could not be sensitive to the performance of opinion relations iden- |
Opinion Target Extraction Methodology | To extract opinion targets from reviews, we adopt the framework proposed by (Liu et al., 2012), which is a graph-based extraction framework and |
Opinion Target Extraction Methodology | In the second component, we adopt a graph-based algorithm used in (Liu et al., 2012) to compute the confidence of each opinion target candidate, and the candidates with higher confidence than the threshold will be extracted as the opinion targets. |
Conclusions | We introduced a new general-purpose graph-based summarization framework that combines a submodular coverage function with a non-submodular dispersion function. |
Introduction | We propose a very general graph-based summarization framework that combines a submodular function with a non-submodular dispersion function. |
Related Work | Graph-based methods have been used for summarization (Ganesan et al., 2010), but in a different context—using paths in graphs to produce very short abstractive summaries. |
Experiments | The second block shows results from other kinds of parsing approaches (e.g., graph-based parsing, ensemble parsing, linear programming, dual decomposition). |
Experiments | Our parser gives a comparative accuracy to Koo and Collins (2010) that is a 3rd-order graph-based parsing approach. |
Experiments | Nivre and McDonald (2008) uses an ensemble model between transition-based and graph-based parsing approaches. |
Abstract | We present a novel, graph-based approach using SimRank, a well-established vertex similarity algorithm to transfer sentiment information between a source language and a target language graph. |
Bilingual Lexicon Induction | Two examples of such methods are a graph-based approach by Dorow et al. |
Bilingual Lexicon Induction | In this paper, we will employ the graph-based method. |
Dependency parsing | For dependency parsing, there are two main types of parsing models (Nivre and McDonald, 2008; Nivre and Kubler, 2006): transition-based (Nivre, 2003; Yamada and Matsumoto, 2003) and graph-based (McDonald et al., 2005; Carreras, 2007). |
Dependency parsing | In this paper, we employ the graph-based MST parsing model proposed by McDonald and Pereira |
Dependency parsing | In the graph-based parsing model, features are represented for all the possible relations on single edges (two words) or adjacent edges (three words). |