Deep dependencies from context-free statistical parsers: correcting the surface dependency approximation (original) (raw)

Deep dependencies from context-free statistical parsers

Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics - ACL '04, 2004

We present a linguistically-motivated algorithm for reconstructing nonlocal dependency in broad-coverage context-free parse trees derived from treebanks. We use an algorithm based on loglinear classifiers to augment and reshape context-free trees so as to reintroduce underlying nonlocal dependencies lost in the context-free approximation. We find that our algorithm compares favorably with prior work on English using an existing evaluation metric, and also introduce and argue for a new dependency-based evaluation metric. By this new evaluation metric our algorithm achieves 60% error reduction on gold-standard input trees and 5% error reduction on state-ofthe-art machine-parsed input trees, when compared with the best previous work. We also present the first results on nonlocal dependency reconstruction for a language other than English, comparing performance on English and German. Our new evaluation metric quantitatively corroborates the intuition that in a language with freer word order, the surface dependencies in context-free parse trees are a poorer approximation to underlying dependency structure.

Parser evaluation over local and non-local deep dependencies in a large corpus

2011

In order to obtain a fine-grained evaluation of parser accuracy over naturally occurring text, we study 100 examples each of ten reasonably frequent linguistic phenomena, randomly selected from a parsed version of the English Wikipedia. We construct a corresponding set of gold-standard target dependencies for these 1000 sentences, operationalize mappings to these targets from seven state-of-theart parsers, and evaluate the parsers against this data to measure their level of success in identifying these dependencies.

Wide-Coverage Deep Statistical Parsing Using Automatic Dependency Structure Annotation

Computational Linguistics, 2008

A number of researchers have recently conducted experiments comparing "deep" hand-crafted wide-coverage with "shallow" treebank-and machine-learning-based parsers at the level of dependencies, using simple and automatic methods to convert tree output generated by the shallow parsers into dependencies. In this article, we revisit such experiments, this time using sophisticated automatic LFG f-structure annotation methodologies with surprising results. We compare various PCFG and history-based parsers to find a baseline parsing system that fits best into our automatic dependency structure annotation technique. This combined system of syntactic parser and dependency structure annotation is compared to two hand-crafted, deep constraint-based parsers, RASP and XLE. We evaluate using dependency-based gold standards Computational Linguistics Volume 34, Number 1 and use the Approximate Randomization Test to test the statistical significance of the results. Our experiments show that machine-learning-based shallow grammars augmented with sophisticated automatic dependency annotation technology outperform hand-crafted, deep, widecoverage constraint grammars. Currently our best system achieves an f-score of 82.73% against the PARC 700 Dependency Bank, a statistically significant improvement of 2.18% over the most recent results of 80.55% for the hand-crafted LFG grammar and XLE parsing system and an f-score of 80.23% against the CBS 500 Dependency Bank, a statistically significant 3.66% improvement over the 76.57% achieved by the hand-crafted RASP grammar and parsing system.

Deriving Enhanced Universal Dependencies from a Hybrid Dependency-Constituency Treebank

Text, Speech, and Dialogue, 2018

The treebanks provided by the Universal Dependencies (UD) initiative are a state-of-the-art resource for cross-lingual and monolingual syntax-based linguistic studies, as well as for multilingual dependency parsing. Creating a UD treebank for a language helps further the UD initiative by providing an important dataset for research and natural language processing in that language. In this paper, we describe how we created a UD treebank for Latvian, and how we obtained both the basic and enhanced UD representations from the data in Latvian Treebank which is annotated according to a hybrid dependency-constituency grammar model. The hybrid model was inspired by Lucien Tesnière's dependency grammar theory and its notion of a syntactic nucleus. While the basic UD representation is already a de facto standard in NLP, the enhanced UD representation is just emerging, and the treebank described here is among the first to provide both representations.

The CoNLL 2007 shared task on dependency parsing

2007

The Conference on Computational Natural Language Learning features a shared task, in which participants train and test their learning systems on the same data sets. In 2007, as in 2006, the shared task has been devoted to dependency parsing, this year with both a multilingual track and a domain adaptation track. In this paper, we define the tasks of the different tracks and describe how the data sets were created from existing treebanks for ten languages. In addition, we characterize the different approaches of the participating systems, report the test results, and provide a first analysis of these results. 2 Task Definition In this section, we provide the task definitions that were used in the two tracks of the CoNLL 2007 Shard Task, the multilingual track and the domain adaptation track, together with some background and motivation for the design choices made. First of all, we give a brief description of the data format and evaluation metrics, which were common to the two tracks. 2.1 Data Format and Evaluation Metrics

Please Mind the Root: Decoding Arborescences for Dependency Parsing

2020

The connection between dependency trees and spanning trees is exploited by the NLP community to train and to decode graph-based dependency parsers. However, the NLP literature has missed an important difference between the two structures: only one edge may emanate from the root in a dependency tree. We analyzed the output of state-of-the-art parsers on many languages from the Universal Dependency Treebank: although these parsers are often able to learn that trees which violate the constraint should be assigned lower probabilities, their ability to do so unsurprisingly degrades as the size of the training set decreases. In fact, the worst constraint-violation rate we observe is 24%. Prior work has proposed an inefficient algorithm to enforce the constraint, which adds a factor of n to the decoding runtime. We adapt an algorithm due to Gabow and Tarjan (1984) to dependency parsing, which satisfies the constraint without compromising the original runtime. 1 (2005)) opt for the simpler CLE algorithm (Chu and Liu, 1965; Bock, 1971; Edmonds, 1967), which has a worst-case bound of O(n 3), but is often fast in practice. 3 A notable exception is the Prague Dependency Treebank (Bejček et al., 2013), which allows for multi-rooted trees.

82 Treebanks, 34 Models: Universal Dependency Parsing with Multi-Treebank Models

Proceedings of the, 2018

We present the Uppsala system for the CoNLL 2018 Shared Task on universal dependency parsing. Our system is a pipeline consisting of three components: the first performs joint word and sentence segmentation; the second predicts part-ofspeech tags and morphological features; the third predicts dependency trees from words and tags. Instead of training a single parsing model for each treebank, we trained models with multiple treebanks for one language or closely related languages, greatly reducing the number of models. On the official test run, we ranked 7th of 27 teams for the LAS and MLAS metrics. Our system obtained the best scores overall for word segmentation, universal POS tagging, and morphological features. 2 Resources All three components of our system were trained principally on the training sets of Universal Dependencies v2.2 released to coincide with the shared task (Nivre et al., 2018). The tagger and parser also make use of the pre-trained word

A high-throughput dependency parser

2017

Dependency parsing is an important task in NLP, and it is used in many downstream tasks for analyzing the semantic structure of sentences. Analyzing very large corpora in a reasonable amount of time, however, requires a fast parser. In this thesis we develop a transitionbased dependency parser with a neural-network decision function which outperforms spaCy, Stanford CoreNLP, and MALTParser in terms of speed while having a comparable, and in some cases better, accuracy. We also develop several variations of our model to investigate the trade-off between accuracy and speed. This leads to a model with a greatly reduced feature set which is much faster but less accurate, as well as a more complex model involving a BiLSTM simultaneously trained to produce POS tags which is more accurate, but much slower. We compare the accuracy and speed of our different parser models against the three mentioned parsers on the Penn Treebank, Universal Dependencies English, and Ontonotes datasets using tw...

A Neural Network Model for Low-Resource Universal Dependency Parsing

Accurate dependency parsing requires large treebanks, which are only available for a few languages. We propose a method that takes advantage of shared structure across languages to build a mature parser using less training data. We propose a model for learning a shared "universal" parser that operates over an interlingual continuous representation of language, along with language-specific mapping components. Compared with supervised learning, our methods give a consistent 8-10% improvement across several treebanks in low-resource simulations.

LingPars, a Linguistically Inspired, Language-Independent Machine Learner for Dependency Treebanks

This paper presents a Constraint Grammar-inspired machine learner and parser, Ling­ Pars, that assigns dependencies to morpho­ logically annotated treebanks in a function-centred way. The system not only bases at­ tachment probabilities for PoS, case, mood, lemma on those features' function probabil­ ities, but also uses topological features like function/PoS n-grams, barrier tags and daughter-sequences. In the CoNLL shared task, performance was below average on attachment scores, but a relatively higher score for function tags/deprels in isolation suggests that the system's strengths were not fully exploited in the current architec­ ture.