A Maximum-Entropy-Inspired Parser

By Eugene Charniak. 2000

1,863 citations recorded by the source corpus.

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

Recurrent Neural Network Grammars (2016, background): “Modeling generation top-down as a rooted branching process that recursively rewrites nonterminals has been explored by Charniak (2000) and Roark (2001).”
Natural Language Processing (Almost) from Scratch (2011, methodology): “, 2005), related to CHUNK tags, and built using POS tags (Charniak, 2000; Collins, 1999).”
Accurate Unlexicalized Parsing (2003, methodology): “12This is part of the explanation of why (Charniak, 2000) finds that early generation of head tags as in (Collins, 1999) is so beneficial.”
Generating Typed Dependency Parses from Phrase Structure Parses (2006, background): “Recent years have seen the introduction of a number of treebank-trained statistical parsers [Collins (Collins, 1999), Charniak (Charniak, 2000), Stanford (Klein and Manning, 2003)] capable of generating parses with high accuracy.”
Direct Output Connection for a High-Rank Language Model (2018, methodology): “com/cdg720/emnlp2016 F1 Model Base Rerank Reranking with single model Choe and Charniak (2016) 89.7 92.6 AWD-LSTM 89.7 93.2 AWD-LSTM-MoS 89.7 93.2 AWD-LSTM-DOC 89.7 93.3 Reranking with model ensemble AWD-LSTM × 5 (ensemble) 89.7 93.4 AWD-LSTM-MoS × 5 (ensemble) 89.7 93.4 AWD-LSTM-DOC × 5 (ensemble) ”
End-to-end learning of semantic role labeling using recurrent neural networks (2015, methodology): “Moreover, in order to catch up with the performance of traditional methods, they had to incorporate the syntactic features by using parse trees of Charniak parser (Charniak, 2000) which still provides the major contribution.”
Structured Generative Models of Natural Source Code (2014, background): “…expression nodes with type information led to worse log probabilities of generating held out data: while the cost of generating tokens decreased because the model had access to type information, the increased cost of generating type annotations along with nodetypes outweighed the improvement.”
Deep Semantic Role Labeling: What Works and What’s Next (2017, critical): “and Charniak, 2016) provides smaller gains, while using the Charniak parser (Charniak, 2000) hurts performance if the model places too much trust in it.”
Head-Driven Statistical Models for Natural Language Parsing (2003, methodology): “Finally, Bod (2001) describes a very different approach (a DOP approach to parsing) that gives excellent results on treebank parsing, comparable to the results of Charniak (2000) and Collins (2000).”
Modeling Local Coherence: An Entity-Based Approach (2005, background): “It records that trial is present in sentences 1 and 6 (as O and X respectively) but is absent from the rest of the sentences.”
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).”
Discriminative Training of a Neural Network Statistical Parser (2004, methodology): “As with many previous statistical parsers (Rat-naparkhi, 1999; Collins, 1999; Charniak, 2000), we use a history-based model of parsing.”
Self-Training PCFG Grammars with Latent Annotations Across Languages (2009, background): “There is an extensive research literature on building high quality parsers for English (Collins, 1999; Charniak, 2000; Charniak and Johnson, 2005; Petrov et al., 2006), however, models for parsing other languages are less well developed.”
The Proposition Bank: An Annotated Corpus of Semantic Roles (2005, neutral): “Robust syntactic parsers, made possible by new statistical techniques (Ratnaparkhi 1997; Collins 1999, 2000; Bangalore and Joshi 1999; Charniak 2000) and by the availability of large, hand-annotated training corpora (Marcus, Santorini, and Marcinkiewicz 1993; Abeille´ 2003), have had a major impact…”
Learning Accurate, Compact, and Interpretable Tree Annotation (2006, background): “Probabilistic context-free grammars (PCFGs) underlie most high-performance parsers in one way or another (Collins, 1999; Charniak, 2000; Charniak and Johnson, 2005).”
Introduction to the CoNLL-2005 Shared Task: Semantic Role Labeling (2005, background): “• Full parser of Charniak (2000).”
Parsing as Language Modeling (2016, background): “(Charniak, 2000) performed better when trained on all of 24 million trees than when trained on resampled two million trees.”
Deep Learning for Efficient Discriminative Parsing (2011, background): “Since the introduction of lexicalized 1 probabilistic context-free grammar (PCFGs) parsers (Mager-man, 1995; Collins, 1996), improvements have been achieved over the years, but generative PCFGs parsers of the last decade from Collins (1999) and Charniak (2000) still remain standard benchmarks.”