• Documents
  • Authors
  • Tables
  • Log in
  • Sign up
  • MetaCart
  • DMCA
  • Donate

CiteSeerX logo

Advanced Search Include Citations
Advanced Search Include Citations

Statistical parsing with a context-free grammar and word statistics. (1997)

by E Charniak
Venue:In Proc. of the AAAI,
Add To MetaCart

Tools

Sorted by:
Results 1 - 10 of 414
Next 10 →

Head-Driven Statistical Models for Natural Language Parsing

by Michael Collins , 1999
"... ..."
Abstract - Cited by 1158 (15 self) - Add to MetaCart
Abstract not found
(Show Context)

Citation Context

...ameters.) 608 Model ≤ 40 Words (2,245 sentences) LR LP CBs 0 CBs ≤ 2 CBs Magerman 1995 84.6% 84.9% 1.26 56.6% 81.4% Collins 1996 85.8% 86.3% 1.14 59.9% 83.6% Goodman 1997 84.8% 85.3% 1.21 57.6% 81=-=.4% Charniak 1997-=- 87.5% 87.4% 1.00 62.1% 86.1% Model 1 87.9% 88.2% 0.95 65.8% 86.3% Model 2 88.5% 88.7% 0.92 66.7% 87.1% Model 3 88.6% 88.7% 0.90 67.1% 87.4% Charniak 2000 90.1% 90.1% 0.74 70.1% 89.6% Collins 2000 90....

Accurate Unlexicalized Parsing

by Dan Klein, Christopher D. Manning - IN PROCEEDINGS OF THE 41ST ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS , 2003
"... We demonstrate that an unlexicalized PCFG can parse much more accurately than previously shown, by making use of simple, linguistically motivated state splits, which break down false independence assumptions latent in a vanilla treebank grammar. Indeed, its ..."
Abstract - Cited by 1052 (70 self) - Add to MetaCart
We demonstrate that an unlexicalized PCFG can parse much more accurately than previously shown, by making use of simple, linguistically motivated state splits, which break down false independence assumptions latent in a vanilla treebank grammar. Indeed, its

A Maximum-Entropy-Inspired Parser

by Eugene Charniak , 1999
"... We present a new parser for parsing down to Penn tree-bank style parse trees that achieves 90.1% average precision/recall for sentences of length 40 and less, and 89.5% for sentences of length 100 and less when trained and tested on the previously established [5,9,10,15,17] "stan- dard" se ..."
Abstract - Cited by 971 (19 self) - Add to MetaCart
We present a new parser for parsing down to Penn tree-bank style parse trees that achieves 90.1% average precision/recall for sentences of length 40 and less, and 89.5% for sentences of length 100 and less when trained and tested on the previously established [5,9,10,15,17] "stan- dard" sections of the Wall Street Journal tree- bank. This represents a 13% decrease in error rate over the best single-parser results on this corpus [9]. The major technical innova- tion is the use of a "maximum-entropy-inspired" model for conditioning and smoothing that let us successfully to test and combine many different conditioning events. We also present some partial results showing the effects of different conditioning information, including a surprising 2% improvement due to guessing the lexical head's pre-terminal before guessing the lexical head.
(Show Context)

Citation Context

...style parse trees that achieves 90.1% average precision/recall for sentences of length 40 and less, and 89.5% for sentences of length 100 and less when trMned and tested on the previously established =-=[5,9,10,15,17] "sta-=-ndard" sections of the Wall Street Journal treebank. This represents a 13% decrease in error rate over the best single-parser results on this corpus [9]. The major technical innovation is tire us...

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 gram- mar. We then extend the model to in- clude a probabilistic treatment of both subcategorisation and wh~movement. Results on Wall Street Journal text show that the parse ..."
Abstract - Cited by 570 (8 self) - Add to MetaCart
In this paper we first propose a new statistical parsing model, which is a generative model of lexicalised context-free gram- mar. We then extend the model to in- clude 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).

Discriminative Reranking for Natural Language Parsing

by Michael Collins, Terry Koo , 2005
"... This article considers approaches which rerank the output of an existing probabilistic parser. The base parser produces a set of candidate parses for each input sentence, with associated probabilities that define an initial ranking of these parses. A second model then attempts to improve upon this i ..."
Abstract - Cited by 333 (9 self) - Add to MetaCart
This article considers approaches which rerank the output of an existing probabilistic parser. The base parser produces a set of candidate parses for each input sentence, with associated probabilities that define an initial ranking of these parses. A second model then attempts to improve upon this initial ranking, using additional features of the tree as evidence. The strength of our approach is that it allows a tree to be represented as an arbitrary set of features, without concerns about how these features interact or overlap and without the need to define a derivation or a generative model which takes these features into account. We introduce a new method for the reranking task, based on the boosting approach to ranking problems described in Freund et al. (1998). We apply the boosting method to parsing the Wall Street Journal treebank. The method combined the log-likelihood under a baseline model (that of Collins [1999]) with evidence from an additional 500,000 features over parse trees that were not included in the original model. The new model achieved 89.75 % F-measure, a 13 % relative decrease in F-measure error over the baseline model’s score of 88.2%. The article also introduces a new algorithm for the boosting approach which takes advantage of the sparsity of the feature space in the parsing data. Experiments show significant efficiency gains for the new algorithm over the obvious implementation of the boosting approach. We argue that the method is an appealing alternative—in terms of both simplicity and efficiency—to work on feature selection methods within log-linear (maximum-entropy) models. Although the experiments in this article are on natural language parsing (NLP), the approach should be applicable to many other NLP problems which are naturally framed as ranking tasks, for example, speech recognition, machine translation, or natural language generation.
(Show Context)

Citation Context

...nking approaches, we will describeshistory-based models (Black et al. 1992). They are important for a few reasons. First, at present the best performing parsers on the WSJ treebank (Ratnaparkhi 1997; =-=Charniak 1997-=-, 1999; Collins 1997, 1999) are all cases of history-based models. Many systems applied to part-ofspeech tagging, speech recognition and other language or speech tasks also fall into this class of mod...

From treebank to propbank

by Paul Kingsbury, Martha Palmer - In Language Resources and Evaluation , 2002
"... This paper describes our approach to the development of a Proposition Bank, which involves the addition of semantic information to the Penn English Treebank. Our primary goal is the labeling of syntactic nodes with specific argument labels that preserve the similarity of roles such as the window in ..."
Abstract - Cited by 265 (14 self) - Add to MetaCart
This paper describes our approach to the development of a Proposition Bank, which involves the addition of semantic information to the Penn English Treebank. Our primary goal is the labeling of syntactic nodes with specific argument labels that preserve the similarity of roles such as the window in John broke the window and the window broke. After motivating the need for explicit predicate argument structure labels, we briefly discuss the theoretical considerations of predicate argument structure and the need to maintain consistency across syntactic alternations. The issues of consistency of argument structure across both polysemous and synonymous verbs are also discussed and we present our actual guidelines for these types of phenomena, along with numerous examples of tagged sentences and verb frames. Metaframes are introduced as a technique for handling similar frames among near− synonymous verbs. We conclude with a summary of the current status of annotation process. 1.

PCFG Models of Linguistic Tree Representations

by Mark Johnson - Computational Linguistics , 1998
"... This paper points out that the Penn lI treebank representations are of the kind predicted to have such an effect, and describes a simple node relabeling transformation that improves a treebank PCFG-based parser's average precision and recall by around 8%, or approximately half of the performanc ..."
Abstract - Cited by 253 (9 self) - Add to MetaCart
This paper points out that the Penn lI treebank representations are of the kind predicted to have such an effect, and describes a simple node relabeling transformation that improves a treebank PCFG-based parser's average precision and recall by around 8%, or approximately half of the performance difference between a simple PCFG model and the best broad-coverage parsers available today. This performance variation comes about because any PCFG, and hence the corpus of trees from which the PCFG is induced, embodies independence assumptions about the distribution of words and phrases. The particular independence assumptions implicit in a tree representation can be studied theoretically and investigated empirically by means of a tree transformation / detransformation process
(Show Context)

Citation Context

...lins 1996), their simplicity makes them straightforward to analyze both theoretically and empirically. Moreover, since more sophisticated systems can be viewed as refinements of the basic PCFG model (=-=Charniak 1997-=-), it seems reasonable to first attempt to better understand the properties of PCFG models themselves. It is well known that natural language exhibits dependencies that context-free grammars (CFGs) ca...

Treebank Grammars

by Eugene Charniak - In Proc. of the 13th National Conference on Artificial Intelligence (AAAI-1996 , 1996
"... By a “tree-bank grammar ” we mean a context-free grammar created by reading the production rules directly from hand-parsed sentences in a tree bank. Common wisdom has it that such grammars do not perform we & though we know of no published data on the issue. The primary purpose of this paper is ..."
Abstract - Cited by 252 (4 self) - Add to MetaCart
By a “tree-bank grammar ” we mean a context-free grammar created by reading the production rules directly from hand-parsed sentences in a tree bank. Common wisdom has it that such grammars do not perform we & though we know of no published data on the issue. The primary purpose of this paper is to show that the common wisdom is wrong. In particular, we present results on a tree-bank grammar based on the Penn WaII Street Journal tree bank. To the best of our knowledge, this grammar outperforms ah other non-word-based statistical parsers/grammars on this corpus. That is, it outperforms parsers that consider the input as a string of tags and ignore the actual words of the corpus.
(Show Context)

Citation Context

...ull 78.8 80.4 87.7 Reduced 78.2 80.7 87.6 Figure 3: Parsing results for a reduced tree-bank grammar 10 15 20 25 85 90 95 100 4 4 4 4 4 4 fi fi fi 2 2 2 3 4--- The tree-bank grammar fi --- The PCFG of =-=[4]-=- 2 --- The transformation parser of [1] 3 --- The PCFG of [7] Figure 4: Accuracy vs. average sentence length for several parsers It seems clear that the tree-bank grammar outperforms the others, parti...

Maximum Entropy Models for Natural Language Ambiguity Resolution

by Adwait Ratnaparkhi , 1998
"... The best aspect of a research environment, in my opinion, is the abundance of bright people with whom you argue, discuss, and nurture your ideas. I thank all of the people at Penn and elsewhere who have given me the feedback that has helped me to separate the good ideas from the bad ideas. I hope th ..."
Abstract - Cited by 234 (1 self) - Add to MetaCart
The best aspect of a research environment, in my opinion, is the abundance of bright people with whom you argue, discuss, and nurture your ideas. I thank all of the people at Penn and elsewhere who have given me the feedback that has helped me to separate the good ideas from the bad ideas. I hope that Ihave kept the good ideas in this thesis, and left the bad ideas out! Iwould like toacknowledge the following people for their contribution to my education: I thank my advisor Mitch Marcus, who gave me the intellectual freedom to pursue what I believed to be the best way to approach natural language processing, and also gave me direction when necessary. I also thank Mitch for many fascinating conversations, both personal and professional, over the last four years at Penn. I thank all of my thesis committee members: John La erty from Carnegie Mellon University, Aravind Joshi, Lyle Ungar, and Mark Liberman, for their extremely valuable suggestions and comments about my thesis research. I thank Mike Collins, Jason Eisner, and Dan Melamed, with whom I've had many stimulating and impromptu discussions in the LINC lab. Iowe them much gratitude for their valuable feedback onnumerous rough drafts of papers and thesis chapters.

Expectation-based syntactic comprehension

by Roger Levy , 2006
"... This paper investigates the role of resource allocation as a source of processing difficulty in human sentence comprehension. The paper proposes a simple informationtheoretic characterization of processing difficulty as the work incurred by resource reallocation during parallel, incremental, probabi ..."
Abstract - Cited by 231 (18 self) - Add to MetaCart
This paper investigates the role of resource allocation as a source of processing difficulty in human sentence comprehension. The paper proposes a simple informationtheoretic characterization of processing difficulty as the work incurred by resource reallocation during parallel, incremental, probabilistic disambiguation in sentence comprehension, and demonstrates its equivalence to the theory of Hale (2001), in which the difficulty of a word is proportional to its surprisal (its negative log-probability) in the context within which it appears. This proposal subsumes and clarifies findings that high-constraint contexts can facilitate lexical processing, and connects these findings to well-known models of parallel constraint-based comprehension. In addition, the theory leads to a number of specific predictions about the role of expectation in syntactic comprehension, including the reversal of locality-based difficulty patterns in syntactically constrained contexts, and conditions under which increased ambiguity facilitates processing. The paper examines a range of established results bearing on these predictions, and shows that they are largely consistent with the surprisal theory.
(Show Context)

Citation Context

...n applied contexts been remarkably successful in reconciling the tension between broad coverage and ambiguity management that has traditionally plagued computational linguistics (see Collins 1999 and =-=Charniak 1997-=-, among many others). The availability of PCFG models that have the properties 1 and 2 from the beginning of this paper, of robustness to arbitrary input and accurate disambiguation, makes them partic...

Powered by: Apache Solr
  • About CiteSeerX
  • Submit and Index Documents
  • Privacy Policy
  • Help
  • Data
  • Source
  • Contact Us

Developed at and hosted by The College of Information Sciences and Technology

© 2007-2019 The Pennsylvania State University