Abstract | In this paper, we propose to use deep syntactic information for obtaining fine-grained translation rules. |
Abstract | A head-driven phrase structure grammar (HPSG) parser is used to obtain the deep syntactic information, which includes a fine-grained description of the syntactic property and a semantic representation of a sentence. |
Abstract | We extract fine-grained rules from aligned HPSG tree/forest-string pairs and use them in our tree-to-string and string-to-tree systems. |
Introduction | But, “VBN(killed)” is indeed separable into two fine-grained tree fragments of “VBN(killedzactive)” and “VBN(killed:passive)”1. |
Introduction | This motivates our proposal of using deep syntactic information to obtain a fine-grained translation rule set. |
Introduction | deep syntactic information of an English sentence, which includes a fine-grained description of the syntactic property and a semantic representation of the sentence. |
Related Work | Before describing our approaches of applying deep syntactic information yielded by an HPSG parser for fine-grained rule extraction, we would like to briefly review what kinds of deep syntactic information have been employed for SMT. |
Related Work | fine-grained tree-to-string rule extraction, rather than string-to-string translation (Hassan et al., 2007; Birch et al., 2007). |
Divergent (Re)Categorization | To find the stable properties that can underpin a meaningful fine-grained category for cowboy, we must seek out the properties that are so often presupposed to be salient of all cowboys that one can use them to anchor a simile, such as "swaggering like a cowboy” or “as grizzled as a cowboy”. |
Divergent (Re)Categorization | Since each hit will also yield a value for S via the wildcard *, and a fine-grained category PS for C, we use this approach here to harvest fine-grained categories from the web from most of our similes. |
Divergent (Re)Categorization | After 2 cycles we acquire 43 categories; after 3 cycles, 72; after 4 cycles, 93; and after 5 cycles, we acquire 102 fine-grained perspectives on cola, such as stimu-lating-drink and corrosive-substance. |
Measuring and Creating Similarity | We also want any fine-grained perspective M-H to influence our similarity metric, provided it can be coherently tied into WordNet as a shared hypemym of the two lexical concepts being compared. |
Measuring and Creating Similarity | The denominator in (2) denotes the sum total of the size of all fine-grained categories that can be coherently added to WordNet for any term. |
Measuring and Creating Similarity | For a shared dimension H in the feature vectors of concepts C1 and C2, if at least one fine-grained perspective M-H has been added to WordNet between H and C1 and between H and C2, then the value of dimension H for C1 and for C2 is given by (4): |
Related Work and Ideas | A fine-grained category hierarchy permits fine-grained similarity judgments, and though WordNet is useful, its sense hierarchies are not especially fine-grained . |
Related Work and Ideas | However, we can automatically make WordNet subtler and more discerning, by adding new fine-grained categories to unite lexical concepts whose similarity is not reflected by any existing categories. |
Related Work and Ideas | Veale (2003) shows how a property that is found in the glosses of two lexical concepts, of the same depth, can be combined with their LCS to yield a new fine-grained parent category, so e.g. |
Abstract | The proposed models are tested on three different tasks: coarse-grained word sense disambiguation, fine-grained word sense disambiguation, and detection of literal vs. nonliteral usages of potentially idiomatic expressions. |
Experimental Setup | We evaluate our models on three different tasks: coarse-grained WSD, fine-grained WSD and literal vs. nonliteral sense detection. |
Experimental Setup | To determine whether our model is also suitable for fine-grained WSD, we test on the data provided by Pradhan et al. |
Experimental Setup | (2009) for the Semeval-2007 Task-l7 (English fine-grained all-words task). |
Experiments | Table 4: Model performance (F-score) for the fine-grained word sense disambiguation task. |
Experiments | 5.2 Fine-grained WSD |
Experiments | Fine-grained WSD, however, is a more difficult task. |
Introduction | We apply these models to coarse- and fine-grained WSD and find that they outperform comparable systems for both tasks. |
Discussion: a Multilingual FrameNet | Also, fine-grained sense and frame distinctions may be more relevant in one language than in another language. |
Discussion: a Multilingual FrameNet | We however find lower performance for verbs in a fine-grained setting. |
Discussion: a Multilingual FrameNet | We argue that an improved alignment algorithm, for instance taking subcategorization information into account, can identify the fine-grained distinctions. |
FrameNet — Wiktionary Alignment | The verb senses are very fine-grained and thus present a difficult alignment task. |
FrameNet — Wiktionary Alignment | A number of false positives occur because the gold standard was developed in a very fine-grained manner: distinctions such as causative vs. inchoa-tive (enlarge: become large vs. enlarge: make large) were explicitly stressed in the definitions and thus annotated as different senses by the annotators. |
Intermediate Resource FNWKxx | Because sense granularity was an issue in the error analysis, we considered two alignment decisions: (a) fine-grained alignment: the two glosses describe the same sense; (b) coarse-grained alignment. |
Intermediate Resource FNWKxx | The precision for the fine-grained (a) is lower than the allover precision on the gold standard. |
Evaluation | HYENA (Hierarchical tYpe classification for Entity NAmes), the method of (Yosef 2012), based on a feature-rich classifier for fine-grained , hierarchical type tagging. |
Introduction | Our aim is for all recognized and newly discovered entities to be semantically interpretable by having fine-grained types that connect them to KB classes. |
Introduction | For informative knowledge, new entities must be typed in a fine-grained manner (e.g., guitar player, blues band, concert, as opposed to crude types like person, organization, event). |
Introduction | Therefore, our setting resembles the established task of fine-grained typing for noun phrases (Fleis-chmann 2002), with the difference being that we disregard common nouns and phrases for prominent in-KB entities and instead exclusively focus on the difficult case of phrases that likely denote new entities. |
Related Work | There is fairly little work on fine-grained typing, notable results being (Fleischmann 2002; Rahman 2010; Ling 2012; Yosef 2012). |
Related Work | These methods consider type taxonomies similar to the one used for PEARL, consisting of several hundreds of fine-grained types. |
Abstract | The model uses a minimal set of domain-independent seed words as prior knowledge to discover a domain-specific lexicon, learning a fine-grained emotion lexicon much richer and adaptive to a specific domain. |
Abstract | By comprehensive experiments, we show that our model can generate a high-quality fine-grained domain-specific emotion lexicon. |
Conclusions and Future Work | In this paper, we have presented a novel emotion-aware LDA model that is able to quickly build a fine-grained domain-specific emotion lexicon for languages without many manually constructed resources. |
Experiments | The experimental results show that our algorithm can successfully construct a fine-grained domain-specific emotion lexicon for this corpus that is able to understand the connotation of the words that may not be obvious without the context. |
Introduction | As the fine-grained annotated data are expensive to get, the unsupervised approaches are preferred and more used in reality. |
Introduction | Usually, a high quality emotion lexicon play a significant role when apply the unsupervised approaches for fine-grained emotion classification. |
Introduction | The results demonstrate that our EaLDA model improves the quality and the coverage of state-of-the-art fine-grained lexicon. |
Experiments | Out of these, 4,011 are positive relation examples annotated with 6 coarse-grained relation types and 22 fine-grained relation types5 . |
Experiments | We similarly build a fine-grained classifier to disambiguate between 45 relation labels. |
Experiments | We built one binary, one coarse-grained, and one fine-grained classifier for each fold. |
Add arc <eC,ej> to GC with | One is composed of 19 coarse-grained relations and the other 111 fine-grained relations6. |
Add arc <eC,ej> to GC with | From Table 3 and Table 4, we can see that the addition of more feature types, except the 6th feature type (semantic similarity), can promote the performance of relation labeling, whether using the coarse-grained 19 relations and the fine-grained 111 relations. |
Add arc <eC,ej> to GC with | Table 5 selects 10 features with the highest weights in absolute value for the parser which uses the coarse-grained relations, while Table 6 selects the top 10 features for the parser using the fine-grained relations. |
Discourse Dependency Structure and Tree Bank | A total of 110 fine-grained relations (e.g. |
Abstract | To tackle these challenges, we propose a novel semi-supervised graph regularization model to incorporate both local and global evidence from multiple tweets through three fine-grained relations. |
Conclusions | By studying three novel fine-grained relations, detecting semantically-related information with semantic meta paths, and exploiting the data manifolds in both unlabeled and labeled data for collective inference, our work can dramatically save annotation cost and achieve better performance, thus shed light on the challenging wikification task for tweets. |
Experiments | Our full model SSRegulgg achieves significant improvement over the supervised baseline (5% absolute Fl gain with 95.0% confidence level by the Wilcoxon Matched-Pairs Signed-Ranks Test), showing that incorporating global evidence from multiple tweets with fine-grained relations is beneficial. |
Introduction | In order to construct a semantic-rich graph capturing the similarity between mentions and concepts for the model, we introduce three novel fine-grained relations based on a set of local features, social networks and meta paths. |
Related Work | Our method is a collective approach with the following novel advancements: (i) A novel graph representation with fine-grained relations, (ii) A unified framework based on meta paths to explore richer relevant context, (iii) Joint identification and linking of mentions under semi-supervised setting. |
Related Work | We introduce a novel graph that incorporates three fine-grained relations. |
Abstract | This paper addresses the task of fine-grained opinion extraction — the identification of opinion-related entities: the opinion expressions, the opinion holders, and the targets of the opinions, and the relations between opinion expressions and their targets and holders. |
Experiments | For evaluation, we used version 2.0 of the MPQA corpus (Wiebe et al., 2005; Wilson, 2008), a widely used data set for fine-grained opinion analysis.6 We considered the subset of 482 documents7 that contain attitude and target annotations. |
Introduction | Fine-grained opinion analysis is concerned with identifying opinions in text at the expression level; this includes identifying the subjective (i.e., opinion) expression itself, the opinion holder and the target of the opinion (Wiebe et al., 2005). |
Introduction | Not surprisingly, fine-grained opinion extraction is a challenging task due to the complexity and variety of the language used to express opinions and their components (Pang and Lee, 2008). |
Introduction | We evaluate our approach using a standard corpus for fine-grained opinion analysis (the MPQA corpus (Wiebe et al., 2005)) and demonstrate that our model outperforms by a significant margin traditional baselines that do not employ joint inference for extracting opinion entities and different types of opinion relations. |
Related Work | Significant research effort has been invested into fine-grained opinion extraction for open-domain text such as news articles (Wiebe et al., 2005; Wilson et al., 2009). |
Evaluations | Since our system predicts fine-grained clusters comparing against Freebase relations, the measure of recall is underestimated. |
Evaluations | Since our systems predict more fine-grained clusters than |
Introduction | fine-grained entity types of two arguments, to handle polysemy. |
Introduction | It is difficult to discover a high-quality set of fine-grained entity types due to unknown criteria for developing such a set. |
Introduction | In this paper we address the problem of polysemy, while we circumvent the problem of finding fine-grained entity types. |
Related Work | They cluster arguments to fine-grained entity types and rank the associations of a relation with these entity types to discover selectional preferences. |
Abstract | The second measures the similarity between the source query and each target query, and then combines these fine-grained similarity values for its importance estimation. |
Conclusion | The second measures the similarity between a source query and each target query, and then combine the fine-grained similarity values to estimate its importance to target domain. |
Evaluation | By contrast, more accurate query weights can be achieved by the more fine-grained similarity measure between the source query and all target queries in algorithm 2. |
Evaluation | fine-grained similarity values. |
Query Weighting | more precise measures of query similarity by utilizing the more fine-grained classification hyperplane for separating the queries of two domains. |
Evaluation | Note that the information gain agent starts dialogs with the top-level and appropriate subcategory questions, so it is only for longer dialogs that the fine-grained aspects boost performance. |
Generating Questions from Reviews | To identify these subcategories, we run Latent Dirichlet Analysis (LDA) (Blei et al., 2003) on the reviews of each set of businesses in the twenty most common top-level categories, using 10 topics and concatenating all of a business’s reviews into one document.2 Several researchers have used sentence-level documents to model topics in reviews, but these tend to generate topics about fine-grained aspects of the sort we discuss in Section 2.2 (Jo and Oh, 2011; Brody and Elhadad, 2010). |
Generating Questions from Reviews | 2.2 Questions from Fine-Grained Aspects |
Introduction | The framework makes use of techniques from topic modeling and sentiment-based aspect extraction to identify fine-grained attributes for each business. |
Introduction | However, recent work has shown that parsing results can be greatly improved by defining more fine-grained syntactic |
Introduction | This gives a fine-grained notion of semantic similarity, which is useful for tackling problems like ambiguous attachment decisions. |
Introduction | The former can capture the discrete categorization of phrases into NP or PP while the latter can capture fine-grained syntactic and compositional-semantic information on phrases and words. |
Application to Essay Scoring | This fine-grained scale resulted in higher mean pairwise inter-rater correlations than the traditional integer-only scale (r=0.79 vs around r=0.70 for the operational scoring). |
Application to Essay Scoring | This dataset provides a very fine-grained ranking of the essays, with almost no two essays getting exactly the same score. |
Application to Essay Scoring | This is a very competitive baseline, as e-rater features explain more than 70% of the variation in essay scores on a relatively coarse scale (setA) and more than 80% of the variation in scores on a fine-grained scale (setB). |
Methodology | We chose a relatively fine-grained binning and performed no optimization for grid selection; for more sophisticated gridding approaches to study nonlinear relationships in the data, see Reshef et al. |
A Class-based Model of Agreement | After segmentation, we tag each segment with a fine-grained morpho-syntactic class. |
Discussion of Translation Results | Finally, +POS+Agr shows the class-based model with the fine-grained classes (e. g., “Noun+Fem+S g”). |
Experiments | For training the tagger, we automatically converted the ATE morphological analyses to the fine-grained class set. |
Introduction | We address this shortcoming with an agreement model that scores sequences of fine-grained morpho-syntactic classes. |
Experiments and Results | Not surprisingly, the fine-grained performance is quite a bit lower than the core relations. |
Learning Time Constraints | We also experiment with 7 fine-grained relations: |
Learning Time Constraints | Obviously the more fine-grained a relation, the better it can inform a classifier. |
Learning Time Constraints | We use a similar function for the seven fine-grained relations. |
Abstract | The KNN based classifier conducts pre-labeling to collect global coarse evidence across tweets while the CRF model conducts sequential labeling to capture fine-grained information encoded in a tweet. |
Introduction | Following the two-stage prediction aggregation methods (Krishnan and Manning, 2006), such pre-labeled results, together with other conventional features used by the state-of-the-art NER systems, are fed into a linear Conditional Random Fields (CRF) (Lafferty et al., 2001) model, which conducts fine-grained tweet level NER. |
Our Method | Our model is hybrid in the sense that a KNN classifier and a CRF model are sequentially applied to the target tweet, with the goal that the KNN classifier captures global coarse evidence while the CRF model fine-grained information encoded in a single tweet and in the gazetteers. |
Our Method | model, which is good at encoding the subtle interactions between words and their labels, compensates for KNN’s incapability to capture fine-grained evidence involving multiple decision points. |
Background | Such hierarchies have good structures and high accuracy, but their coverage is limited to fine-grained concepts (e.g., “Ranunculaceae” is not included in WordNet.). |
Conclusion and Future Work | Further improvements are made using a cluster-based approach in order to model the more fine-grained relations. |
Method | hyponym word pairs in our training data and visualize them.2 Figure 2 shows that the relations are adequately distributed in the clusters, which implies that hypernym—hyponym relations indeed can be decomposed into more fine-grained relations. |
Results and Analysis 5.1 Varying the Amount of Clusters | Some fine-grained relations exist in Wikipedia, but the coverage is limited. |
Experiments | Classifier Fine-grained (%) Binary (%) |
Experiments | Likewise, in the fine-grained case, we use the standard 8544/1101/2210 splits. |
Experiments | The DCNN for the fine-grained result has the same architecture, but the filters have size 10 and 7, the top pooling parameter k is 5 and the number of maps is, respectively, 6 and 12. |
Properties of the Sentence Model | For most applications and in order to learn fine-grained feature detectors, it is beneficial for a model to be able to discriminate whether a specific n-gram occurs in the input. |
Approach | The differences are: (l) we encode the coreference relations as soft constraints during learning instead of applying them as hard constraints during inference time; (2) our constraints can apply to both polar and non-polar sentences; (3) our identification of coreference relations is automatic without any fine-grained annotations for opinion targets. |
Introduction | Accordingly, extracting sentiment at the fine-grained level (e. g. at the sentence- or phrase-level) has received increasing attention recently due to its challenging nature and its importance in supporting these opinion analysis tasks (Pang and Lee, 2008). |
Introduction | However, the discourse relations were obtained from fine-grained annotations and implemented as hard constraints on polarity. |
Introduction | Obtaining sentiment labels at the fine-grained level is costly. |
Experimental setting | We experiment with both full synsets and SFs as instances of fine-grained and coarse-grained semantic representation, respectively. |
Integrating Semantics into Parsing | The more fine-grained our semantic representation, the higher the average polysemy and the greater the need to distinguish between these senses. |
Integrating Semantics into Parsing | Disambiguating each word relative to its context of use becomes increasingly difficult for fine-grained representations (Palmer et al., 2006). |
Results | We hypothesise that this is due to the avoidance of excessive fragmentation, as occurs with fine-grained senses. |
Experiments | We posit that EDUs are too fine-grained for sentiment analysis. |
Introduction | However, these changes can be successfully exploited for inferring fine-grained sentiments. |
Introduction | Segments can be shorter than sentences and therefore help capture fine-grained sentiments. |
Introduction | In our approach, we classify sentences as S-(non)relevant because this is the most fine-grained level at which S-relevance manifests itself; at the word or phrase level, S-relevance classification is not possible because of scope and context effects. |
Related Work | Our work is most closely related to (Taboada et al., 2009) who define a fine-grained classification that is similar to sentiment relevance on the highest level. |
Related Work | Tackstro'm and McDonald (2011) develop a fine-grained annotation scheme that includes S-nonrelevance as one of five categories. |
Towards A Universal Treebank | This mainly consisted in relabeling dependency relations and, due to the fine-grained label set used in the Swedish Treebank (Teleman, 1974), this could be done with high precision. |
Towards A Universal Treebank | Making fine-grained label distinctions was discouraged. |
Towards A Universal Treebank | Such a reduction may ultimately be necessary also in the case of dependency relations, but since most of our data sets were created through manual annotation, we could afford to retain a fine-grained analysis, knowing that it is always possible to map from finer to coarser distinctions, but not vice versa.4 |
Introduction | Specifically, we are interested in identifying fine-grained product properties across reviews (e.g., battery life for electronics or pizza for restaurants) as well as capturing attributes of these properties, namely aggregate user sentiment. |
Problem Formulation | Property: A property corresponds to some fine-grained aspect of a product. |
Related Work | While our model captures similar high-level intuition, it analyzes fine-grained properties expressed at the snippet level, rather than document-level sentiment. |
Experiments | We use standard classification accuracy (Acc) on the most fine-grained level of target categories in the genre hierarchy. |
Introduction | This paper explores a way of using information on the hierarchy of labels for improving fine-grained genre classification. |
Structural SVMs | Let x be a document and wm a weight vector associated with the genre class m in a corpus with k genres at the most fine-grained level. |
Conclusion | In this paper, we present a novel, fine-grained taxonomy of 43 noun-noun semantic relations, the largest annotated noun compound dataset yet created, and a supervised classification method for automatic noun compound interpretation. |
Evaluation | The .57-.67 H figures achieved by the Voted annotations compare well with previously reported inter-annotator agreement figures for noun compounds using fine-grained taxonomies. |
Introduction | In this paper, we present a large, fine-grained taxonomy of 43 noun compound relations, a dataset annotated according to this taxonomy, and a supervised, automatic classification method for determining the relation between the head and modifier words in a noun compound. |
A Latent Variable CCG Parser | The Petrov parser uses latent variables to refine a coarse-grained grammar extracted from a training corpus to a grammar which makes much more fine-grained syntactic distinctions. |
A Latent Variable CCG Parser | in Petrov’s experiments on the Penn treebank, the syntactic category NP was refined to the more fine-grained N P1 and N P2 roughly corresponding to N Ps in subject and object positions. |
A Latent Variable CCG Parser | However, this fine-grained control is exactly what the Petrov parser does automatically. |
Abstract | But word appears to be too fine-grained in some cases such as non-compositional phrasal equivalences, where no clear word alignments exist. |
Conclusion | It is proposed to replace too fine-grained word as basic translational unit. |
Introduction | But there is a deficiency in such manner that word is too fine-grained in some cases such as non-compositional phrasal equivalences, where clear word alignments do not exist. |
Human Language Project | We postulate that interlinear glossed text is sufficiently fine-grained to serve our purposes. |
Human Language Project | All documents will be included in primary form, but the percentage of documents with manual annotation, or manually corrected annotation, decreases at increasingly fine-grained levels of annotation. |
Human Language Project | Where manual fine-grained annotation is unavailable, automatic methods for creating it (at a lower quality) are desirable. |
Data and Evaluation | Since Sundance clauses are also too fine-grained for our purposes, we use a few simple rules to collapse clauses that are unlikely to meet our definition of EDU. |
Data and Evaluation | A clearer example that illustrates the pitfalls of fine-grained discourse segmenting is shown in the following output from SPADE: |
Introduction* | The segments produced by a parser, however, are too fine-grained for discourse purposes, breaking off complement and other clauses that are not in a discourse relation to any other segment. |
Conclusion and Future work | We also tried to map the fine-grained VerbNet roles into coarser roles, but it did not yield better results than the mapping from PropBank roles. |
Mapping into VerbNet Thematic Roles | But if we compare them to the results of the PropBank to VerbNet mapping, where we simply substitute the fine-grained roles by their corresponding groups, we see that they still lag behind (second row in Table 6). |
On the Generalization of Role Sets | In the case of VerbNet, the more fine-grained distinction among roles seems to depend more on the meaning of the predicate. |
Related Work | On the one hand, their model is asymmetric, thus not giving the same interpretation power to verbs and arguments; on the other hand, the model provides a more fine-grained clustering for nouns, in the form of an additional hierarchical structure of the noun clusters. |
Verb Class Model 2.1 Probabilistic Model | A model with a large number of fine-grained concepts as selectional preferences assigns a higher likelihood to the data than a model with a small number of general concepts, because in general a larger number of parameters is better in describing training data. |
Verb Class Model 2.1 Probabilistic Model | Consequently, the EM algorithm a priori prefers fine-grained concepts but — due to sparse data problems — tends to overfit the training data. |