Skip to content

Latest commit

 

History

History
83 lines (63 loc) · 8.29 KB

dependency_parsing.md

File metadata and controls

83 lines (63 loc) · 8.29 KB
Raw

Dependency parsing

Dependency parsing is the task of extracting a dependency parse of a sentence that represents its grammatical structure and defines the relationships between "head" words and words, which modify those heads.

Example:

     root
      |
      | +-------dobj---------+
      | |                    |
nsubj | |   +------det-----+ | +-----nmod------+
+--+  | |   |              | | |               |
|  |  | |   |      +-nmod-+| | |      +-case-+ |
+  |  + |   +      +      || + |      +      | |
I  prefer  the  morning   flight  through  Denver

Relations among the words are illustrated above the sentence with directed, labeled arcs from heads to dependents (+ indicates the dependent).

Penn Treebank

Models are evaluated on the Stanford Dependency conversion (v3.3.0) of the Penn Treebank with predicted POS-tags. Punctuation symbols are excluded from the evaluation. Evaluation metrics are unlabeled attachment score (UAS) and labeled attachment score (LAS). UAS does not consider the semantic relation (e.g. Subj) used to label the attachment between the head and the child, while LAS requires a semantic correct label for each attachment.Here, we also mention the predicted POS tagging accuracy.

Model POS UAS LAS Paper / Source Code
CVT + Multi-Task (Clark et al., 2018) 97.74 96.61 95.02 Semi-Supervised Sequence Modeling with Cross-View Training Official
Deep Biaffine (Dozat and Manning, 2017) 97.3 95.74 94.08 Deep Biaffine Attention for Neural Dependency Parsing Official
jPTDP (Nguyen and Verspoor, 2018) 97.97 94.51 92.87 An improved neural network model for joint POS tagging and dependency parsing Official
Andor et al. (2016) 97.44 94.61 92.79 Globally Normalized Transition-Based Neural Networks
Distilled neural FOG (Kuncoro et al., 2016) 97.3 94.26 92.06 Distilling an Ensemble of Greedy Dependency Parsers into One MST Parser
Distilled transition-based parser (Liu et al., 2018) 97.3 94.05 92.14 Distilling Knowledge for Search-based Structured Prediction Official
Weiss et al. (2015) 97.44 93.99 92.05 Structured Training for Neural Network Transition-Based Parsing
BIST transition-based parser (Kiperwasser and Goldberg, 2016) 97.3 93.9 91.9 Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations Official
Arc-hybrid (Ballesteros et al., 2016) 97.3 93.56 91.42 Training with Exploration Improves a Greedy Stack-LSTM Parser
BIST graph-based parser (Kiperwasser and Goldberg, 2016) 97.3 93.1 91.0 Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations Official

The following results are just for references:

Model UAS LAS Note Paper / Source
Stack-only RNNG (Kuncoro et al., 2017) 95.8 94.6 Constituent parser What Do Recurrent Neural Network Grammars Learn About Syntax?
Deep Biaffine (Dozat and Manning, 2017) 95.75 94.22 Stanford conversion v3.5.0 Deep Biaffine Attention for Neural Dependency Parsing
Semi-supervised LSTM-LM (Choe and Charniak, 2016) (Constituent parser) 95.9 94.1 Constituent parser Parsing as Language Modeling

Cross-lingual zero-shot dependency parsing

Cross-lingual zero-shot parsing is the task of inferring the dependency parse of sentences from one language without any labeled training trees for that language.

Universal Dependency Treebank

Models are evaluated against the Universal Dependency Treebank v2.0. For each of the 6 target languages, models can use the trees of all other languages and English and are evaluated by the UAS and LAS on the target. The final score is the average score across the 6 target languages. The most common evaluation setup is to use gold POS-tags.

Model UAS LAS Paper / Source Code
Cross-Lingual ELMo (Schuster et al., 2019) 84.2 77.3 Cross-Lingual Alignment of Contextual Word Embeddings, with Applications to Zero-shot Dependency Parsing Official
MALOPA (Ammar et al., 2016) 70.5 Many Languages, One Parser Official
Guo et al. (2016) 76.7 69.9 A representation learning framework for multi-source transfer parsing

Unsupervised dependency parsing

Unsupervised dependency parsing is the task of inferring the dependency parse of sentences without any labeled training data.

Penn Treebank

As with supervised parsing, models are evaluated against the Penn Treebank. The most common evaluation setup is to use gold POS-tags as input and to evaluate systems using the unlabeled attachment score (also called 'directed dependency accuracy').

Model UAS Paper / Source
Iterative reranking (Le & Zuidema, 2015) 66.2 Unsupervised Dependency Parsing - Let’s Use Supervised Parsers
Combined System (Spitkovsky et al., 2013) 64.4 Breaking Out of Local Optima with Count Transforms and Model Recombination - A Study in Grammar Induction
Tree Substitution Grammar DMV (Blunsom & Cohn, 2010) 55.7 Unsupervised Induction of Tree Substitution Grammars for Dependency Parsing
Shared Logistic Normal DMV (Cohen & Smith, 2009) 41.4 Shared Logistic Normal Distributions for Soft Parameter Tying in Unsupervised Grammar Induction
DMV (Klein & Manning, 2004) 35.9 Corpus-Based Induction of Syntactic Structure - Models of Dependency and Constituency

Go back to the README