Linguistically Motivated Large-Scale NLP with C&C and Boxer

By James Richard Curran, Stephen Clark, Johan Bos. Annual Meeting of the Association for Computational Linguistics, 2007

344 citations recorded by the source corpus.

The statistical modelling of language, together with advances in wide-coverage grammar development, have led to high levels of robustness and efficiency in NLP systems and made linguistically motivated large-scale language processing a possibility (Matsuzaki et al., 2007; Kaplan et al., 2004). This paper describes an NLP system which is based on syntactic and semantic formalisms from theoretical linguistics, and which we have used to analyse the entire Gigaword corpus (1 billion words) in less than 5 days using only 18 processors. This combination of detail and speed of analysis represents a break-through in NLP technology.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/dcceb47a102bb1a634a494e43030364e7f8e7533

How researchers see this paper

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

In Artificial Intelligence

Citations in the corpus

Book Reviews: Ontology-Based Interpretation of Natural Language by Philipp Cimiano, Christina Unger and John McCrae (2014, background): “Boxer [Curran et al., 2007], one of the most sophisticated such tools, limits itself to computing one logical form that mirrors the syntactic dependencies in the original sentence.”
Evaluating Entity Linking with Wikipedia (2013, methodology): “In our implementation, we ﬁrst use the C&C ner tagger (Curran et al., 2007) to extract named entity mentions from the text.”
Category-theoretic quantitative compositional distributional models of natural language semantics (2013, methodology): “For my evaluation, the corpus was lemmatised using Carroll’s Morpha [62], which was applied as a by-product of my parsing of the BNC with the C&Ctools parser of [20].”
The Meaning Factory: Formal Semantics for Recognizing Textual Entailment and Determining Semantic Similarity (2014, methodology): “It is the last component in the pipeline of the C&C tools (Curran et al., 2007), comprising a tokenizer, POS-tagger, lemmatizer (Minnen et al., 2001), and a robust parser for CCG (Steed-man, 2001).”
A Natural Proof System for Natural Language (2017, methodology): “The RTE system UTexas (Beltagy et al., 2014) also uses FOL representations obtained from Boxer but compared to Nutcracker it employs probabilistic FOL with Markov Logic Networks (MLN).”
The Role of Syntax in Vector Space Models of Compositional Semantics (2013, methodology): “While one could debate the relative merits of various linguistic formalisms the existence of mature tools and resources, such as the CCGBank (Hockenmaier and Steedman, 2007), the Groningen Meaning Bank (Basile et al., 2012) and the C&C Tools (Curran et al., 2007) is another big advantage for CCG. CC”
Every Picture Tells a Story: Generating Sentences from Images (2010, positive): “We used the Curran & Clark parser [22] to generate a dependency parse for each sentence.”
Developing a large semantically annotated corpus (2012, methodology): “The pipeline used for constructing meaning representations is a cascade of various components, most of them provided by the C&C tools and Boxer (Curran et al., 2007).”
Grounding language acquisition by training semantic parsers using captioned videos (2018, methodology): “Following Zettlemoyer and Collins (2005) and Curran et al. (2007), we adopt a weighted linear semantic parser.”
Asiya: An Open Toolkit for Automatic Machine Translation (Meta-)Evaluation (2010, methodology): “For the discursive analysis of texts, DR measures rely on the C&C Tools (Curran et al., 2007).”
Split and Rephrase (2017, methodology): “Our second contribution is to provide ﬁve models to understand the difﬁculty of the proposed Split-and-Rephrase task: (i) A basic encoder-decoder taking as input only the complex sentence; (ii) A hybrid probabilistic-SMT model taking as input a deep semantic representation (Discourse representation ”