Abstract | The trained parser produces a full syntactic parse of any sentence, while simultaneously producing logical forms for portions of the sentence that have a semantic representation within the parser’s predicate vocabulary. |
Introduction | Integrating syntactic parsing with semantics has long been a goal of natural language processing and is expected to improve both syntactic and semantic processing. |
Introduction | For example, semantics could help predict the differing prepositional phrase attachments in “I caught the butterfly with the net” and “I caught the butterfly with the spots A joint analysis could also avoid propagating syntactic parsing errors into semantic processing, thereby improving performance. |
Introduction | ideally improve the parser’s ability to solve difficult syntactic parsing problems, as in the examples above. |
Prior Work | This paper combines two lines of prior work: broad coverage syntactic parsing with CCG and semantic parsing. |
Prior Work | Broad coverage syntactic parsing with CCG has produced both resources and successful parsers. |
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 | We present a novel technique for semantic frame identification using distributed representations of predicates and their syntactic context; this technique leverages automatic syntactic parses and a generic set of word embeddings. |
Discussion | combination of two syntactic parsers as input. |
Frame Identification with Embeddings | Formally, let cc represent the actual sentence with a marked predicate, along with the associated syntactic parse tree; let our initial representation of the predicate context be Suppose that the word embeddings we start with are of dimension n. Then 9 is a function from a parsed sentence cc to Rm“, where k is the number of possible syntactic context types. |
Overview | We could represent the syntactic context of runs as a vector with blocks for all the possible dependents warranted by a syntactic parser ; for example, we could assume that positions 0 . |
Add arc <eC,ej> to GC with | The other two types of features which are related to length and syntactic parsing , only promote the performance slightly. |
Add arc <eC,ej> to GC with | Since the RST tree is similar to the constituency based syntactic tree except that the constituent nodes are different, the syntactic parsing techniques have been borrowed for discourse parsing (Soricut and Marcu, 2003; Baldridge and Lascarides, 2005; Sagae, 2009; Hernault et al., 2010b; Feng and Hirst, 2012). |
Introduction | Since such a hierarchical discourse tree is analogous to a constituency based syntactic tree except that the constituents in the discourse trees are text spans, previous researches have explored different constituency based syntactic parsing techniques (eg. |
Introduction | First, it is difficult to design a set of production rules as in syntactic parsing , since there are no determinate generative rules for the interior text spans. |
Experiments | To obtain syntactic parse trees and semantic roles on the tuning and test datasets, we first parse the source sentences with the Berkeley Parser (Petrov and Klein, 2007), trained on the Chinese Treebank 7.0 (Xue et al., 2005). |
Experiments | Since the syntactic parses of the tuning and test data contain 29 types of constituent labels and 35 types of POS tags, we have 29 types of XP+ features and 64 types of XP= features. |
Related Work | The reordering rules were either manually designed (Collins et al., 2005; Wang et al., 2007; Xu et al., 2009; Lee et al., 2010) or automatically learned (Xia and McCord, 2004; Gen-zel, 2010; Visweswariah et al., 2010; Khalilov and Sima’an, 2011; Lerner and Petrov, 2013), using syntactic parses . |
Related Work | (2012) obtained word order by using a reranking approach to reposition nodes in syntactic parse trees. |
Character-Level Dependency Tree | A transition-based framework with global learning and beam search decoding (Zhang and Clark, 2011) has been applied to a number of natural language processing tasks, including word segmentation, PCS-tagging and syntactic parsing (Zhang and Clark, 2010; Huang and Sagae, 2010; Bohnet and Nivre, 2012; Zhang et al., 2013). |
Character-Level Dependency Tree | Both are crucial to well-established features for word segmentation, PCS-tagging and syntactic parsing . |
Character-Level Dependency Tree | (2013) was the first to perform Chinese syntactic parsing over characters. |
Introduction | Second, word internal structures can also be useful for syntactic parsing . |
Conclusions | Seeking alternatives to measuring syntactic complexity of spoken responses via syntactic parsers , we study a shallow-analysis based approach for use in automatic scoring. |
Related Work | Not surprisingly, Chen and Zechner (2011) studied measures of grammatical complexity via syntactic parsing and found that a Pearson’s correlation coefficient of 0.49 between syntactic complexity measures (derived from manual transcriptions) and proficiency scores, was drastically reduced to near nonexistence when the measures were applied to ASR word hypotheses. |
Shallow-analysis approach to measuring syntactic complexity | The measures of syntactic complexity in this approach are POS bigrams and are not obtained by a deep analysis ( syntactic parsing ) of the structure of the sentence. |
Approaches | In Section 3.1, we introduced pipeline-trained models for SRL, which used grammar induction to predict unlabeled syntactic parses . |
Related Work | In this simple pipeline, the first stage syntactically parses the corpus, and the second stage predicts semantic predicate-argument structure for each sentence using the labels of the first stage as features. |
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. |
Abstract | Experiment on the SANCL 2012 shared task show that our approach achieves 93.15% average tagging accuracy, which is the best accuracy reported so far on this data set, higher than those given by ensembled syntactic parsers . |
Conclusion | For future work, we would like to investigate the two-phase approach to more challenging tasks, such as web domain syntactic parsing . |
Introduction | set, higher than those given by ensembled syntactic parsers . |