Three Generative, Lexicalised Models for Statistical Parsing

By Michael Collins. 1997

In this paper we first propose a new statistical parsing model, which is a generative model of lexicalised context-free grammar. We then extend the model to include a probabilistic treatment of both subcategorisation and wh-movement. Results on Wall Street Journal text show that the parser performs at 88.1/87.5% constituent precision/recall, an average improvement of 2.3% over (Collins 96).

Subfields: Natural Language Processing

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

Citations in the corpus

Grammar as a Foreign Language (2014, background): “The focus in these approaches is on devising appropriate smoothing techniques for highly lexicalized and thus rare events (Collins, 1997) or ca efully crafting the model structure (Klein & Manning, 2003).”
Statistical Phrase-Based Translation (2003, methodology): “We then parse both sides of the corpus with syntactic parsers [ Collins, 1997; Schmidt and Schulte im Walde, 2000].”
An Empirical Study of Smoothing Techniques for Language Modeling (1996, neutral): “ing (Magerman, 1994; Collins, 1997; Goodman, 1997).”
Evaluating the State-of-the-Art of End-to-End Natural Language Generation: The E2E NLG Challenge (2019, methodology): “We used the syntactic constituency parser of Collins (1997) to preprocess the sentences for the DLevel Analyser.11 The D-Level scale has eight levels of syntactic complexity, where levels 0 and 1 include simple or incomplete sentences and higher levels include sentences with more complex…”
LexRank: Graph-based Lexical Centrality as Salience in Text Summarization (2004, background): “Many problems in NLP, e.g., parsing (Collins, 1997), word sense disambiguation (Yarowsky, 1995), and automatic paraphrasing (Barzilay & Lee, 2003) have beneﬁted signiﬁcantly by the introduction of robust statistical techniques.”
Hedge Trimmer: A Parse-and-Trim Approach to Headline Generation (2003, methodology): “As described in Miller et al. (1998), the BBN parser builds augmented parse trees according to a process similar to that described in Collins (1997).”
Head-Driven Statistical Models for Natural Language Parsing (2003, methodology): “In particular, the model in Collins (1997) failed to generate punctuation, a deﬁciency of the model.”
Modeling Local Coherence: An Entity-Based Approach (2005, methodology): “We employ a robust statistical parser (Collins, 1997) to determine the constituent structure for each sentence, from which subjects (s), objects (o), and relations other than subject or object (x) are identified.”
Unbounded Dependency Recovery for Parser Evaluation (2009, background): “The Stanford parser is representative of a large number of PTB parsers, exempliﬁed by Collins (1997) and Charniak (2000).”
Recognizing Contextual Polarity in Phrase-Level Sentiment Analysis (2005, methodology): “Themodifyfeatures involve the dependency parse tree for the sentence, obtained by first parsing the sentence (Collins, 1997) and then converting the tree into its dependency representation (Xia and Palmer, 2001).”
Measuring the Evolution of a Scientific Field through Citation Frames (2018, background): “, (Collins, 1999; Buchholz et al., 1999; Collins, 1997), with a much sharper (lower entropy)”
11,001 New Features for Statistical Machine Translation (2009, methodology): “…Model 4 word alignments, and then the link deletion algorithm (Fossum et al., 2008) the syntax-based system, we ran a reimplementation of the Collins parser (Collins, 1997) on the English half of the bitext to produce parse trees, then restructured and relabeled them as described in Section 3.2.”
Easy-First Dependency Parsing with Hierarchical Tree LSTMs (2016, background): “ve to work better. We leave this line of inquiry to future work. The head-outward modiﬁer generation approach has a long history in the parsing literature, and goes back to at least Eisner (1996) and Collins (1997). In contrast to previous work in which each modiﬁer could condition only on a ﬁxed sm”
Bootstrapping language acquisition. (2017, background): “While naive PCFGs impose conditional independence assumptions that are too strong to characterize natural language, they can be augmented to overcome this problem (Charniak, 1997; Collins, 1997).”
Comparing and Combining Finite-State and Context-Free Parsers (2005, methodology): “The output of a context-free parser, such as that of Collins (1997) or Char-niak (2000), can be transformed into a sequence of shallow constituents for comparison with the output of a shallow parser.”
From TreeBank to PropBank (2002, background): “…of the Penn TreeBanks (Marcus, Santorini, & Marcinkiewicz 1993; Marcus 1994) enabled the development of extremely powerful new syntactic analyzers (Collins 1997, 2000), moving to the stage of accurate predicate argument analysis will require a body of publicly available training data that…”