An Improved Non-monotonic Transition System for Dependency Parsing

By Matthew Honnibal, Mark Johnson. 2015

648 citations recorded by the source corpus.

Transition-based dependency parsers usually use transition systems that monotonically extend partial parse states until they identify a complete parse tree. Honnibal et al. (2013) showed that greedy onebest parsing accuracy can be improved by adding additional non-monotonic transitions that permit the parser to “repair” earlier parsing mistakes by “over-writing” earlier parsing decisions. This increases the size of the set of complete parse trees that each partial parse state can derive, enabling such a parser to escape the “garden paths” that can trap monotonic greedy transition-based dependency parsers. We describe a new set of non-monotonic transitions that permits a partial parse state to derive a larger set of completed parse trees than previous work, which allows our parser to escape from a larger set of garden paths. A parser with our new nonmonotonic transition system has 91.85% directed attachment accuracy, an improvement of 0.6% over a comparable parser using the standard monotonic arc-eager transitions.

Subfields: Artificial Intelligence, Information Systems, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems

In Natural Language Processing

Citations in the corpus

End-to-End Learning of Visual Representations From Uncurated Instructional Videos (2019, methodology): “We used spaCy [14] to parse every sentence classified as describing one of the 13 actions and get every subject for each action verb.”
A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents (2018, methodology): “We lowercase all tokens and perform sentence and word tokenization using spaCy (Honnibal and Johnson, 2015).”
Question Answering as an Automatic Evaluation Metric for News Article Summarization (2019, methodology): “, Name, Nationality, Organization, Geopolitical Entity or Facility) using an NER system (Honnibal and Johnson, 2015) and we create fill-in-the-blank type questions where the answers are these entities.”
Question Relevance in VQA: Identifying Non-Visual And False-Premise Questions (2016, positive): “We use spaCy POS tagger (Honnibal and Johnson, 2015).”
Evidence Sentence Extraction for Machine Reading Comprehension (2019, methodology): “We use spaCy (Honnibal and Johnson, 2015) for tokenization and named entity tagging.”
Slice-based Learning: A Programming Model for Residual Learning in Critical Data Slices (2019, methodology): “We consider two text-based relation extraction datasets: Chemical-Disease Relations (CDR),[41], in which we identify causal links between chemical and disease entities in a dataset of PubMed abstracts, and Spouses [9], in which we identify mentions of spousal relationships using preprocessed pairs o”
Does BERT Make Any Sense? Interpretable Word Sense Disambiguation with Contextualized Embeddings (2019, methodology): “We use spaCy1 (Honnibal and Johnson, 2015) for pre-processing and the lemma of a word as the target word representation, e.”
Combining Similarity and Transformer Methods for Case Law Entailment (2019, methodology): “Similarly, we also extracted the noun-phrases of the text fragments using spaCy [16].”
Comparison of Transfer-Learning Approaches for Response Selection in Multi-Turn Conversations (2018, methodology): “We used the spaCy tokenizer (Honnibal and Johnson 2015) and additionally split words on boundaries between alpha and numeric characters.”
GraphRel: Modeling Text as Relational Graphs for Joint Entity and Relation Extraction (2019, methodology): “The POS tag for each word and the dependency tree for whole sentences was retrieved from spaCy (Honnibal and Johnson, 2015).”
Predictive Embeddings for Hate Speech Detection on Twitter (2018, neutral): “We tokenize the data using Spacy (Honnibal and Johnson, 2015).”
Unsupervised Distillation of Syntactic Information from Contextualized Word Representations (2020, methodology): “Corpus For training the transformation f , we rely on 150,000 sentences from Wikipedia, tokenized and POS-tagged by spaCy (Honnibal and Johnson, 2015; Honnibal and Montani, 2017).”