Shallow Semantic Parsing using Support Vector Machines

By Sameer Pradhan, Wayne H. Ward, Kadri Hacioglu, James H. Martin, Dan Jurafsky. 2004

449 citations recorded by the source corpus.

Subfields: Natural Language Processing, Information Extraction

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

In Information Extraction

Citations in the corpus

Natural Language Processing (Almost) from Scratch (2011, methodology): “Pradhan et al. (2004) take these base features and define additional features, notably the part-of-speech tag of the head word, the predicted named entity class of the argument, features providing word sense disambiguation for the verb (they add 25 variants of 12 new feature types overall).”
SPICE: Semantic Propositional Image Caption Evaluation (2016, methodology): “In the MEANT metric [21], SRLs are used to try to capture the basic event structure of sentences – ‘ who did what to whom , when , where and why ’ [22].”
Deep learning via semi-supervised embedding (2008, methodology): “SRL is a Semantic Role Labeling task (Pradhan et al., 2004) with one million labeled training examples and 631 million unlabeled examples. data set classes dims points labeled g50c 2 50 500 50 Text 2 7511 1946 50 Uspst 10 256 2007 50 Mnist1h 10 784 70k 100 Mnist6h 10 784 70k 600 Mnist1k 10 784…”
When does a compliment become sexist? Analysis and classification of ambivalent sexism using twitter data (2017, methodology): “After this, we used the Stanford Shallow Parser (Pradhan et al., 2004) to chunk tweets and get all the phrases.”
Semantic Role Chunking Combining Complementary Syntactic Views (2005, methodology): “…use features based on syntactic constituents produced by a Charniak parser (Pradhan et al., 2003; Pradhan et al., 2004) and others use only a ﬂat syntactic representation produced by a syntactic chun-ker (Hacioglu et al., 2003; Hacioglu and Ward, 2003; Hacioglu, 2004; Hacioglu et al., 2004).”
Inferring Robot Task Plans from Human Team Meetings: A Generative Modeling Approach with Logic-Based Prior (2013, background): “Processing human dialogue into more machine understandable forms is an important research area (Kruijff, Janıcek, and Lison 2010; Tellex et al. 2011; Koomen et al. 2005; Palmer, Gildea, and Xue 2010; Pradhan et al. 2004), but we view this as a separate problem and do not focus on it in this paper.”
Rank learning for factoid question answering with linguistic and semantic constraints (2010, methodology): “The baseline passage retrieval approach in our QA system consists of bag-of-words Indri2 queries with named entity placeholders to represent the expected answer type.”
Calibrating Features for Semantic Role Labeling (2004, methodology): “As far as we know the best results so far are reported by (Pradhan et al., 2004), where a wide range of features, including features extracted from named entities, verb clusters and verb senses, temporal cue words, dynamic context, are tested with an SVM classifier.”
A Model of Zero-Shot Learning of Spoken Language Understanding (2015, methodology): “Statistical SLU models are usually trained on the data obtained from a speciﬁc domain and location, using a structured output classiﬁer that can be discriminative (Pradhan et al., 2004; Kate and Mooney, 2006; Henderson et al., 2012) or generative (Schwartz et al., 1996; He and Young, 2005).”
Exploiting Semantic Role Labeling, WordNet and Wikipedia for Coreference Resolution (2006, methodology): “In our experiments we use the ASSERT parser (Pradhan et al., 2004), an SVM based semantic role tagger which uses a full syntactic analysis to automatically identify all verb predicates in a sentence together with their semantic arguments, which are output as Prop-Bank arguments (Palmer et al.,…”
MASC: the Manually Annotated Sub-Corpus of American English (2008, methodology): “Despite the difficulty, and thanks largely to the impetus of two separate competitions concerned with frame semantic annotation, at Senseval-3 (Litkowski et al. 2004) and Semeval-4 (Baker et al. 2006), there are currently three publicly available systems for automatically recognizing frames and assi”
Using Semantic Roles to Improve Question Answering (2007, methodology): “They use ASSERT (Pradhan et al., 2004), a publicly available shallow semantic parser trained on PropBank, to generate predicate-argument structures which subsequently form the basis of comparison between question and answer sentences.”
Tree Kernels for Semantic Role Labeling (2008, methodology): “In the next sections, we brieﬂy introduce the kernel trick and describe the subtree (ST) kernel devised in Vishwanathan and Smola (2002), the subset tree (SST) kernel deﬁned in Collins and Duffy (2002), and the partial tree (PT) kernel proposed in Moschitti (2006a).”
Inferring Team Task Plans from Human Meetings: A Generative Modeling Approach with Logic-Based Prior (2015, unknown): “…(Kruijﬀ, Janıcek, & Lison, 2010; Tellex, Kollar, Dick-erson, Walter, Banerjee, Teller, & Roy, 2011; Koomen, Punyakanok, Roth, & Yih, 2005; Palmer, Gildea, & Xue, 2010; Pradhan, Ward, Hacioglu, Martin, & Jurafsky, 2004), but we view this as a separate problem and do not focus on it in this paper.”
A unified architecture for natural language processing: deep neural networks with multitask learning (2008, methodology): “54% for a state-of-the-art method based on parse trees (Pradhan et al., 2004) 1 .”
Support Vector Learning for Semantic Argument Classification (2005, methodology): “We formulate the parsing problem as a multi-class classification problem and use a Support Vector Machine (SVM) classifier (Hacioglu et al., 2003; Pradhan et al., 2003).”