Index of papers in Proc. ACL that mention
  • constituent parsing
Wang, Zhiguo and Xue, Nianwen
Abstract
We propose three improvements to address the drawbacks of state-of-the-art transition-based constituent parsers .
Introduction
Constituent parsing is one of the most fundamental tasks in Natural Language Processing (NLP).
Introduction
Transition-based constituent parsing (Sagae and Lavie, 2005; Wang et al., 2006; Zhang and Clark, 2009) is an attractive alternative.
Introduction
However, there is still room for improvement for these state-of-the-art transition-based constituent parsers .
Transition-based Constituent Parsing
This section describes the transition-based constituent parsing model, which is the basis of Section 3 and the baseline model in Section 4.
Transition-based Constituent Parsing
2.1 Transition-based Constituent Parsing Model
Transition-based Constituent Parsing
A transition-based constituent parsing model is a quadruple C = (S, T, 30, St), where S is a set of parser states (sometimes called configurations), T is a finite set of actions, so is an initialization function to map each input sentence into a unique initial state, and St E S is a set of terminal states.
constituent parsing is mentioned in 30 sentences in this paper.
Topics mentioned in this paper:
Cai, Jingsheng and Utiyama, Masao and Sumita, Eiichiro and Zhang, Yujie
Dependency-based Pre-ordering Rule Set
Figure 1 shows a constituent parse tree and its Stanford typed dependency parse tree for the same
Dependency-based Pre-ordering Rule Set
9) is much fewer than that in its corresponding constituent parse tree (i.e.
Experiments
First, we converted the constituent parse trees in the results of the Berkeley Parser into dependency parse trees by employing a tool in the Stanford Parser (Klein and Manning, 2003).
Experiments
In our opinion, the reason for the great decrease was that the dependency parse trees were more concise than the constituent parse trees in describing sentences and they could also describe the reordering at the sentence level in a finer way.
Experiments
In contrast, the constituent parse trees were more redundant and they needed more nodes to conduct long-distance reordering.
Introduction
Syntax-based pre-ordering by employing constituent parsing have demonstrated effectiveness in many language pairs, such as English-French (Xia and McCord, 2004), German-English (Collins et al., 2005), Chinese-English (Wang et al., 2007; Zhang et al., 2008), and English-Japanese (Lee et al., 2010).
Introduction
Since dependency parsing is more concise than constituent parsing in describing sentences, some research has used dependency parsing in pre-ordering approaches for language pairs such as Arabic-English (Habash, 2007), and English-SOV languages (Xu et al., 2009; Katz-Brown et al., 2011).
Introduction
They created a set of pre-ordering rules for constituent parsers for Chinese-English PBSMT.
constituent parsing is mentioned in 12 sentences in this paper.
Topics mentioned in this paper:
Bansal, Mohit and Klein, Dan
Abstract
We then integrate our features into full-scale dependency and constituent parsers .
Abstract
We show relative error reductions of 7.0% over the second-order dependency parser of McDonald and Pereira (2006), 9.2% over the constituent parser of Petrov et al.
Analysis
We next investigate the features that were given high weight by our learning algorithm (in the constituent parsing case).
Introduction
For constituent parsing , we rerank the output of the Berkeley parser (Petrov et al., 2006).
Introduction
To show end-to-end effectiveness, we incorporate our features into state-of-the-art dependency and constituent parsers .
Introduction
For constituent parsing , we use a reranking framework (Charniak and Johnson, 2005; Collins and Koo, 2005; Collins, 2000) and show 9.2% relative error reduction over the Berkeley parser baseline.
Parsing Experiments
We then add them to a constituent parser in a reranking approach.
Parsing Experiments
4.2 Constituent Parsing
Parsing Experiments
We also evaluate the utility of web-scale features on top of a state-of—the-art constituent parser — the Berkeley parser (Petrov et al., 2006), an unlexical-ized phrase-structure parser.
Web-count Features
1For constituent parsers , there can be minor tree variations which can result in the same set of induced dependencies, but these are rare in comparison.
constituent parsing is mentioned in 10 sentences in this paper.
Topics mentioned in this paper:
Rastrow, Ariya and Dredze, Mark and Khudanpur, Sanjeev
Experiments
The dependency parser and POS tagger are trained on supervised data and up-trained on data labeled by the CKY—style bottom-up constituent parser of Huang et al.
Experiments
Therefore, we could not use the constituent parser for ASR rescoring since utterances can be very long, although the shorter up-training text data was not a problem.7 We evaluate both unlabeled (UAS) and labeled dependency accuracy (LAS).
Experiments
Figure 3 shows improvements to parser accuracy through up-training for different amount of (randomly selected) data, where the last column indicates constituent parser score (91.4% UAS).
Incorporating Syntactic Structures
4We note that while we have demonstrated substructure sharing for dependency parsing, the same improvements can be made to a shift—reduce constituent parser (Sagae and Lavie, 2006).
Up-Training
(2010) used up-training as a domain adaptation technique: a constituent parser —which is more robust to domain changes — was used to label a new domain, and a fast dependency parser
Up-Training
We parse a large corpus of text with a very accurate but very slow constituent parser and use the resulting data to up-train our tools.
constituent parsing is mentioned in 9 sentences in this paper.
Topics mentioned in this paper:
Zhang, Meishan and Zhang, Yue and Che, Wanxiang and Liu, Ting
Character-based Chinese Parsing
Our character-based Chinese parsing model is based on the work of Zhang and Clark (2009), which is a transition-based model for lexicalized constituent parsing .
Character-based Chinese Parsing
In summary, our character-based parser contains the word-based features of constituent parser presented in Zhang and Clark (2009), the word-based and shallow character-based features of joint word segmentation and POS tagging presented in Zhang and Clark (2010), and additionally the deep character-based features that encode word structure information, which are the first presented by this paper.
Experiments
(a) Joint segmentation and (b) Joint constituent parsing POS tagging F—scores.
Experiments
Our final performance on constituent parsing is by far the best that we are aware of for the Chinese data, and even better than some state-of-the-art models with gold segmentation.
Experiments
(2007) achieves 83.45%5 in parsing accuracy on the test corpus, and our pipeline constituent parsing model achieves 83.55% with gold segmentation.
Related Work
Our character-level parsing model is inspired by the work of Zhang and Clark (2009), which is a transition-based model with a beam-search decoder for word-based constituent parsing .
Related Work
In addition, we propose novel features related to word structures and interactions between word segmentation, POS tagging and word-based constituent parsing .
Related Work
They exploit a generative maximum entropy model for character-based constituent parsing , and find that POS information is very useful for Chinese word segmentation, but high-level syntactic information seems to have little effect on segmentation.
constituent parsing is mentioned in 9 sentences in this paper.
Topics mentioned in this paper:
Li, Zhenghua and Zhang, Min and Chen, Wenliang
Ambiguity-aware Ensemble Training
To construct parse forests for unlabeled data, we employ three diverse parsers, i.e., our baseline GParser, a transition-based parser (ZPar3) (Zhang and Nivre, 2011), and a generative constituent parser (Berkeley Parser4) (Petrov and Klein, 2007).
Conclusions
For future work, among other possible extensions, we would like to see how our approach performs when employing more diverse parsers to compose the parse forest of higher quality for the unlabeled data, such as the easy-first nondirectional dependency parser (Goldberg and Elhadad, 2010) and other constituent parsers (Collins and Koo, 2005; Charniak and Johnson, 2005; Finkel et al., 2008).
Experiments and Analysis
We believe the reason is that being a generative model designed for constituent parsing , Berkeley Parser is more different from discriminative dependency parsers, and therefore can provide more divergent syntactic structures.
Introduction
Although working well on constituent parsing (McClosky et al., 2006; Huang and Harper, 2009), self-training is shown unsuccessful for dependency parsing (Spreyer and Kuhn, 2009).
Introduction
To construct parse forest on unlabeled data, we employ three supervised parsers based on different paradigms, including our baseline graph-based dependency parser, a transition-based dependency parser (Zhang and Nivre, 2011), and a generative constituent parser (Petrov and Klein, 2007).
Introduction
We first employ a generative constituent parser for semi-supervised dependency parsing.
Supervised Dependency Parsing
Instead, we build a log-linear CRF-based dependency parser, which is similar to the CRF-based constituent parser of Finkel et al.
constituent parsing is mentioned in 8 sentences in this paper.
Topics mentioned in this paper:
Chen, Xiao and Kit, Chunyu
Abstract
This paper presents a higher-order model for constituent parsing aimed at utilizing more local structural context to decide the score of a grammar rule instance in a parse tree.
Conclusion
This paper has presented a higher-order model for constituent parsing that factorizes a parse tree into larger parts than before, in hopes of increasing its power of discriminating the true parse from the others without losing tractability.
Conclusion
More importantly, it extends the existing works into a more general framework of constituent parsing to utilize more lexical and structural context and incorporate more strength of various parsing techniques.
Conclusion
However, higher-order constituent parsing inevitably leads to a high computational complexity.
Introduction
Similarly, we can define the order of constituent parsing in terms of the number of grammar rules in a part.
Introduction
Then, the previous discriminative constituent parsing models (Johnson, 2001; Henderson, 2004; Taskar et al., 2004; Petrov and Klein, 2008a;
Introduction
The discriminative re-scoring models (Collins, 2000; Collins and Duffy, 2002; Charniak and Johnson, 2005; Huang, 2008) can be viewed as previous attempts to higher-order constituent parsing , using some parts containing more than one grammar rule as nonlocal features.
constituent parsing is mentioned in 8 sentences in this paper.
Topics mentioned in this paper:
Andreas, Jacob and Klein, Dan
Abstract
Do continuous word embeddings encode any useful information for constituency parsing ?
Conclusion
It is important to emphasize that these results do not argue against the use of continuous representations in a parser’s state space, nor argue more generally that constituency parsers cannot possibly benefit from word embeddings.
Conclusion
Indeed, our results suggest a hypothesis that word embeddings are useful for dependency parsing (and perhaps other tasks) because they provide a level of syntactic abstraction which is explicitly annotated in constituency parses .
Introduction
This paper investigates a variety of ways in which word embeddings might augment a constituency parser with a discrete state space.
Introduction
It has been less clear how (and indeed whether) word embeddings in and of themselves are useful for constituency parsing .
Introduction
The fact that word embedding features result in nontrivial gains for discriminative dependency parsing (Bansal et al., 2014), but do not appear to be effective for constituency parsing , points to an interesting structural difference between the two tasks.
Three possible benefits of word embeddings
We are interested in the question of whether a state-of-the-art discrete-variable constituency parser can be improved with word embeddings, and, more precisely, what aspect (or aspects) of the parser can be altered to make effective use of embeddings.
constituent parsing is mentioned in 8 sentences in this paper.
Topics mentioned in this paper:
Parikh, Ankur P. and Cohen, Shay B. and Xing, Eric P.
Abstract
We propose a spectral approach for unsupervised constituent parsing that comes with theoretical guarantees on latent structure recovery.
Abstract
More specifically, we approach unsupervised constituent parsing from the perspective of structure learning as opposed to parameter learning.
Abstract
This undirected latent tree is then directed via a direction mapping to give the final constituent parse .
constituent parsing is mentioned in 7 sentences in this paper.
Topics mentioned in this paper:
Gómez-Rodr'iguez, Carlos and Carroll, John and Weir, David
Abstract
We define a new formalism, based on Sikkel’s parsing schemata for constituency parsers , that can be used to describe, analyze and compare dependency parsing algorithms.
Dependency parsing schemata
Therefore, as items for constituency parsers are defined as sets of partial constituency trees, it is tempting to define items for dependency parsers as sets of partial dependency graphs.
Dependency parsing schemata
Once we have this definition of an item set for dependency parsing, the remaining definitions are analogous to those in Sikkel’s theory of constituency parsing (Sikkel, 1997), so we will not include them here in full detail.
Dependency parsing schemata
However, when executing this schema with a deductive engine, we can recover the parse forest by following back pointers in the same way as is done with constituency parsers (Billot and Lang, 1989).
Introduction
This is an alternative to constituency parsing , which tries to find a division of the sentence into segments (constituents) which are then broken up into smaller constituents.
Introduction
The formalism of parsing schemata (Sikkel, 1997) is a useful tool for the study of constituency parsers since it provides formal, high-level descriptions of parsing algorithms that can be used to prove their formal properties (such as correctness), establish relations between them, derive new parsers from existing ones and obtain efficient implementations automatically (Gomez-Rodriguez et al., 2007).
constituent parsing is mentioned in 6 sentences in this paper.
Topics mentioned in this paper:
Bodenstab, Nathan and Dunlop, Aaron and Hall, Keith and Roark, Brian
Introduction
Statistical constituent parsers have gradually increased in accuracy over the past ten years.
Introduction
Although syntax is becoming increasingly important for large-scale NLP applications, constituent parsing is slow—too slow to scale to the size of many potential consumer applications.
Introduction
Deterministic algorithms for dependency parsing exist that can extract syntactic dependency structure very quickly (Nivre, 2008), but this approach is often undesirable as constituent parsers are more accurate and more adaptable to new domains (Petrov et al., 2010).
constituent parsing is mentioned in 5 sentences in this paper.
Topics mentioned in this paper:
Ponvert, Elias and Baldridge, Jason and Erk, Katrin
CD
5 Constituent parsing with a cascade of chunkers
CD
We use cascades of chunkers for full constituent parsing , building hierarchical constituents bottom-up.
Data
We use the standard data sets for unsupervised constituency parsing research: for English, the Wall Street Journal subset of the Penn Treebank-3 (WSJ, Marcus et al.
Introduction
This result suggests that improvements to low-level constituent prediction will ultimately lead to further gains in overall constituent parsing .
Tasks and Benchmark
portantly, until recently it was the only unsupervised raw text constituent parser to produce results competitive with systems which use gold POS tags (Klein and Manning, 2002; Klein and Manning, 2004; Bod, 2006) — and the recent improved raw-text parsing results of Reichart and Rappoport (2010) make direct use of CCL without modification.
constituent parsing is mentioned in 5 sentences in this paper.
Topics mentioned in this paper:
Zhu, Muhua and Zhang, Yue and Chen, Wenliang and Zhang, Min and Zhu, Jingbo
Abstract
Shift-reduce dependency parsers give comparable accuracies to their chart-based counterparts, yet the best shift-reduce constituent parsers still lag behind the state-of-the-art.
Improved hypotheses comparison
Unlike dependency parsing, constituent parse trees for the same sentence can have different numbers of nodes, mainly due to the existence of unary nodes.
Introduction
The best reported accuracies of transition-based constituent parsers still lag behind the state-of-the-art (Sagae and Lavie, 2006; Zhang and Clark, 2009).
Semi-supervised Parsing with Large Data
Based on the information, we propose a set of novel features specifically designed for shift-reduce constituent parsing .
Semi-supervised Parsing with Large Data
The idea of exploiting lexical dependency information from auto-parsed data has been explored before for dependency parsing (Chen et al., 2009) and constituent parsing (Zhu et al., 2012).
constituent parsing is mentioned in 5 sentences in this paper.
Topics mentioned in this paper:
Pauls, Adam and Klein, Dan
Scoring a Sentence
For machine translation, a model that builds target-side constituency parses , such as that of Galley et a1.
Tree Transformations
number of transformations of Treebank constituency parses that allow us to capture such dependencies.
Treelet Language Modeling
There is one additional hurdle in the estimation of our model: while there exist corpora with human-annotated constituency parses like the Penn Treebank (Marcus et al., 1993), these corpora are quite small — on the order of millions of tokens — and we cannot gather nearly as many counts as we can for 77.-grams, for which billions or even trillions (Brants et al., 2007) of tokens are available on the Web.
Treelet Language Modeling
However, we can use one of several high-quality constituency parsers (Collins, 1997; Charniak, 2000; Petrov et al., 2006) to automatically generate parses.
constituent parsing is mentioned in 4 sentences in this paper.
Topics mentioned in this paper:
Berg-Kirkpatrick, Taylor and Gillick, Dan and Klein, Dan
Experiments
Constituency parses were produced using the Berkeley parser (Petrov and Klein, 2007).
Joint Model
In our complete model, which jointly extracts and compresses sentences, we choose whether or not to cut individual subtrees in the constituency parses
Joint Model
Assume a constituency parse 758 for every sentence 3.
Joint Model
While we use constituency parses rather than dependency parses, this model has similarities with the vine-growth model of Daume III (2006).
constituent parsing is mentioned in 4 sentences in this paper.
Topics mentioned in this paper:
Niu, Zheng-Yu and Wang, Haifeng and Wu, Hua
Abstract
Evaluation on the Penn Chinese Treebank indicates that a converted dependency treebank helps constituency parsing and the use of unlabeled data by self-training further increases parsing f-score to 85.2%, resulting in 6% error reduction over the previous best result.
Conclusion
Moreover, experimental results on the Penn Chinese Treebank indicate that a converted dependency treebank helps constituency parsing , and it is better to exploit probability information produced by the parser through score interpolation than to prune low quality trees for the use of the converted treebank.
Our Two-Step Solution
We first train a constituency parser on CPS
Related Work
(1999) performed statistical constituency parsing of Czech on a treebank that was converted from the Prague Dependency Treebank under the guidance of conversion rules and heuristic rules, e.g., one level of projection for any category, minimal projection for any dependents, and fixed position of attachment.
constituent parsing is mentioned in 4 sentences in this paper.
Topics mentioned in this paper:
Sun, Weiwei and Uszkoreit, Hans
Abstract
Syntagmatic lexical relations are implicitly captured by constituent parsing and are utilized via system combination.
Capturing Syntagmatic Relations via Constituency Parsing
The majority of the state-of-the-art constituent parsers are based on generative PCFG learning, with lexicalized (Collins, 2003; Chamiak, 2000) or latent annotation (PCFG-LA) (Matsuzaki et al., 2005; Petrov et al., 2006; Petrov and Klein, 2007) refinements.
State-of-the-Art
Xu, 2011), POS tagging (Huang et al., 2007, 2009), constituency parsing (Zhang and Clark, 2009; Wang et al., 2006) and dependency parsing (Zhang and Clark, 2008; Huang and Sagae, 2010; Li et al., 2011).
constituent parsing is mentioned in 3 sentences in this paper.
Topics mentioned in this paper:
Li, Zhenghua and Liu, Ting and Che, Wanxiang
Experiments and Analysis
(2009) use the maximum entropy inspired generative parser (GP) of Charniak (2000) as their constituent parser .
Related Work
They automatically convert the dependency—structure CDT into the phrase—structure style of CTBS using a statistical constituency parser trained on CTBS.
Related Work
Their experiments show that the combined treebank can significantly improve the performance of constituency parsers .
constituent parsing is mentioned in 3 sentences in this paper.
Topics mentioned in this paper:
Feng, Vanessa Wei and Hirst, Graeme
Method
HILDA’s features: We incorporate the original features used in the HILDA discourse parser with slight modification, which include the following four types of features occurring in SL, SR, or both: (1) N-gram prefixes and suffixes; (2) syntactic tag prefixes and suffixes; (3) lexical heads in the constituent parse tree; and (4) PCS tag of the dominating nodes.
Related work
(2009) attempted to recognize implicit discourse relations (discourse relations which are not signaled by explicit connectives) in PDTB by using four classes of features — contextual features, constituent parse features, dependency parse features, and lexical features — and explored their individual influence on performance.
Related work
They showed that the production rules extracted from constituent parse trees are the most effective features, while contextual features are the weakest.
constituent parsing is mentioned in 3 sentences in this paper.
Topics mentioned in this paper:
Constant, Matthieu and Sigogne, Anthony and Watrin, Patrick
Abstract
This paper evaluates two empirical strategies to integrate multiword units in a real constituency parsing context and shows that the results are not as promising as has sometimes been suggested.
Introduction
view, their incorporation has also been considered such as in (Nivre and Nilsson, 2004) for dependency parsing and in (Arun and Keller, 2005) in constituency parsing .
Introduction
Our proposal is to evaluate two discriminative strategies in a real constituency parsing context: (a) pre-grouping MWE before parsing; this would be done with a state-of-the-art recognizer based on Conditional Random Fields; (b) parsing with a grammar including MWE identification and then reranking the output parses thanks to a Maximum Entropy model integrating MWE-dedicated features.
constituent parsing is mentioned in 3 sentences in this paper.
Topics mentioned in this paper:
Hall, David and Durrett, Greg and Klein, Dan
Abstract
On the SPMRL 2013 multilingual constituency parsing shared task (Seddah et al., 2013), our system outperforms the top single parser system of Bjorkelund et al.
Conclusion
To date, the most successful constituency parsers have largely been generative, and operate by refining the grammar either manually or automatically so that relevant information is available locally to each parsing decision.
Conclusion
We build up a small set of feature templates as part of a discriminative constituency parser and outperform the Berkeley parser on a wide range of languages.
constituent parsing is mentioned in 3 sentences in this paper.
Topics mentioned in this paper:
Snyder, Benjamin and Naseem, Tahira and Barzilay, Regina
Abstract
We investigate the task of unsupervised constituency parsing from bilingual parallel corpora.
Introduction
In this paper we investigate the task of unsupervised constituency parsing when bilingual parallel text is available.
Related Work
While PCFGs perform poorly on this task, the CCM model (Klein and Manning, 2002) has achieved large gains in performance and is among the state-of-the-art probabilistic models for unsupervised constituency parsing .
constituent parsing is mentioned in 3 sentences in this paper.
Topics mentioned in this paper: