A survey of graphs in natural language processing*

@article{Nastase2015ASO,
  title={A survey of graphs in natural language processing*},
  author={Vivi Nastase and Rada Mihalcea and Dragomir R. Radev},
  journal={Natural Language Engineering},
  year={2015},
  volume={21},
  pages={665 - 698}
}
Abstract Graphs are a powerful representation formalism that can be applied to a variety of aspects related to language processing. We provide an overview of how Natural Language Processing problems have been projected into the graph framework, focusing in particular on graph construction – a crucial step in modeling the data to emphasize the phenomena targeted. 
Graph-Based Annotation Engineering: Towards a Gold Corpus for Role and Reference Grammar
TLDR
While RRG annotations cannot be easily derived from any single treebank in existence, it is suggested that they can be reliably inferred from the intersection of syntactic and semantic annotations as represented by, for example, the Universal Dependencies and PropBank.
Similarity-Driven Semantic Role Induction via Graph Partitioning
TLDR
The working hypothesis of this article is that semantic roles can be induced without human supervision from a corpus of syntactically parsed sentences based on three linguistic principles, and a method is presented that implements these principles and formalizes the task as a graph partitioning problem.
Generating and applying textual entailment graphs for relation extraction and email categorization
TLDR
Investigating how entailment graphs can be generated and used for addressing two specific NLP tasks: First, the task of validating automatically derived relation extraction patterns and, second, thetask of automatically categorizing German customer emails show that both tasks can benefit from the integration of semantic knowledge, as expressed by entailment graph.
Modeling the Evolution of Word Senses with Force-Directed Layouts of Co-occurrence Networks
TLDR
A novel force-directed graph layout algorithm is proposed to draw a network of frequently co-occurring words to visualize the evolution of word senses and it is hoped that jointly modeling semantic change and multiple senses of words results in improvements for the individual tasks.
Named Entity Recognition based on a Graph Structure
TLDR
In this work, a graph structure for storage and enrichment of named entities is proposed that makes use of synonyms and domain-specic ontologies in the area of computing.
An Analysis of Euclidean vs. Graph-Based Framing for Bilingual Lexicon Induction from Word Embedding Spaces
TLDR
This work study the behavior of Euclidean versus graph-based approaches to BLI under differing data conditions and show that they complement each other when combined.
Random Walks for Knowledge-Based Word Sense Disambiguation
TLDR
This article presents a WSD algorithm based on random walks over large Lexical Knowledge Bases (LKB) that performs better than other graph-based methods when run on a graph built from WordNet and eXtended WordNet.
Edge-based sequential graph generation with recurrent neural networks
Revealing Semantic Structures of Texts: Multi-grained Framework for Automatic Mind-map Generation
TLDR
A novel neural network is taken to detect the relations at first, which employs multi-hop self-attention and gated recurrence network to reveal the directed semantic relations via sentences to create a human-like mind-map.
...
...

References

SHOWING 1-10 OF 171 REFERENCES
Networks and Natural Language Processing
TLDR
This paper presents some of the most successful graph-based representations and algorithms used in language processing and tries to explain how and why they work.
Graph-Based Clustering for Computational Linguistics: A Survey
TLDR
This survey overviews graph-based clustering and its applications in computational linguistics as a five-part story: hypothesis, modeling, measure, algorithm and evaluation, and envision that graph- based clustering is a promising solution for some emerging NLP problems.
A Graph-Theoretic Algorithm for Automatic Extension of Translation Lexicons
TLDR
A graph-theoretic approach to the identification of yet-unknown word translations based on the recursive Sim-Rank algorithm and relies on the intuition that two words are similar if they establish similar grammatical relationships with similar other words.
A Graph Model for Unsupervised Lexical Acquisition
TLDR
This paper presents an unsupervised method for assembling semantic knowledge from a part-of-speech tagged corpus using graph algorithms and focuses on the symmetric relationship between pairs of nouns which occur together in lists.
Inducing Temporal Graphs
TLDR
This work considers the problem of constructing a directed acyclic graph that encodes temporal relations found in a text and achieves 83% F-measure in temporal segmentation and 84% accuracy in inferring temporal relations between two segments.
Integrating Graph-Based and Transition-Based Dependency Parsers
TLDR
This paper shows how the distribution of parsing errors are correlated with theoretical properties of the models used for learning and inference can be exploited to improve parsing accuracy by integrating a graph-based and a transition-based model.
Robust Textual Inference via Graph Matching
TLDR
A learned graph matching approach to approximate entailment using the amount of the sentence's semantic content which is contained in the text, which outperforms Bag-Of-Words and TF-IDF models.
Global Learning of Focused Entailment Graphs
TLDR
A graph structure over predicates is defined that represents entailment relations as directed edges, and a global transitivity constraint on the graph is used to learn the optimal set of edges, by formulating the optimization problem as an Integer Linear Program.
TextRank: Bringing Order into Text
TLDR
TextRank, a graph-based ranking model for text processing, is introduced and it is shown how this model can be successfully used in natural language applications.
Chinese Whispers - an Efficient Graph Clustering Algorithm and its Application to Natural Language Processing Problems
TLDR
The performance of Chinese Whispers is measured on Natural Language Processing (NLP) problems as diverse as language separation, acquisition of syntactic word classes and word sense disambiguation.
...
...