Structured Sentiment Analysis as Dependency Graph Parsing

• URL: http://arxiv.org/abs/2105.14504v1
• Date: Sun, 30 May 2021 11:19:46 GMT
• Title: Structured Sentiment Analysis as Dependency Graph Parsing
• Authors: Jeremy Barnes, Robin Kurtz, Stephan Oepen, Lilja {\O}vrelid, Erik Velldal
• Abstract summary: We argue that this division has become counterproductive and propose a new unified framework to remedy the situation. We cast the structured sentiment problem as dependency graph parsing, where the nodes are spans of sentiment holders, targets and expressions, and the arcs are the relations between them.
• Score: 5.174808367448261
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Structured sentiment analysis attempts to extract full opinion tuples from a text, but over time this task has been subdivided into smaller and smaller sub-tasks, e,g,, target extraction or targeted polarity classification. We argue that this division has become counterproductive and propose a new unified framework to remedy the situation. We cast the structured sentiment problem as dependency graph parsing, where the nodes are spans of sentiment holders, targets and expressions, and the arcs are the relations between them. We perform experiments on five datasets in four languages (English, Norwegian, Basque, and Catalan) and show that this approach leads to strong improvements over state-of-the-art baselines. Our analysis shows that refining the sentiment graphs with syntactic dependency information further improves results.

Related papers

• Revisiting Structured Sentiment Analysis as Latent Dependency Graph Parsing [38.27437431585664]
  Internal structures of spans are neglected, thus only the boundary tokens of spans are used for relation prediction and span recognition. Long spans occupy a significant proportion in the SSA datasets, which further exacerbates the problem of internal structure neglect. We propose a two-stage parsing method and leverage TreeCRFs with a novel constrained inside algorithm to model latent structures explicitly.
  arXiv  Detail & Related papers  (2024-07-05T18:18:50Z)
• USA: Universal Sentiment Analysis Model & Construction of Japanese Sentiment Text Classification and Part of Speech Dataset [0.0]
  This paper proposes enhancing performance by leveraging the Mutual Reinforcement Effect(MRE) between individual words and the overall text. To support our research, we annotated four novel Sentiment Text Classification and Part of Speech(SCPOS) datasets. Furthermore, we developed a Universal Sentiment Analysis(USA) model, with a 7-billion parameter size.
  arXiv  Detail & Related papers  (2023-09-07T15:35:00Z)
• Variational Cross-Graph Reasoning and Adaptive Structured Semantics Learning for Compositional Temporal Grounding [143.5927158318524]
  Temporal grounding is the task of locating a specific segment from an untrimmed video according to a query sentence. We introduce a new Compositional Temporal Grounding task and construct two new dataset splits. We argue that the inherent structured semantics inside the videos and language is the crucial factor to achieve compositional generalization.
  arXiv  Detail & Related papers  (2023-01-22T08:02:23Z)
• Learn from Structural Scope: Improving Aspect-Level Sentiment Analysis with Hybrid Graph Convolutional Networks [6.116341682577877]
  Aspect-level sentiment analysis aims to determine the sentiment polarity towards a specific target in a sentence. We introduce the concept of Scope, which outlines a structural text region related to a specific target. We propose a hybrid graph convolutional network (HGCN) to synthesize information from constituency tree and dependency tree.
  arXiv  Detail & Related papers  (2022-04-27T09:10:22Z)
• Dependency Induction Through the Lens of Visual Perception [81.91502968815746]
  We propose an unsupervised grammar induction model that leverages word concreteness and a structural vision-based to jointly learn constituency-structure and dependency-structure grammars. Our experiments show that the proposed extension outperforms the current state-of-the-art visually grounded models in constituency parsing even with a smaller grammar size.
  arXiv  Detail & Related papers  (2021-09-20T18:40:37Z)
• Sparse Fuzzy Attention for Structured Sentiment Analysis [48.69930912510414]
  We propose a sparse and fuzzy attention scorer with pooling layers which improves performance and sets the new state-of-the-art on structured sentiment analysis. We further explore the parsing modeling on structured sentiment analysis with second-order parsing and introduce a novel sparse second-order edge building procedure that leads to significant improvement in parsing performance.
  arXiv  Detail & Related papers  (2021-09-14T14:37:56Z)
• GATE: Graph Attention Transformer Encoder for Cross-lingual Relation and Event Extraction [107.8262586956778]
  We introduce graph convolutional networks (GCNs) with universal dependency parses to learn language-agnostic sentence representations. GCNs struggle to model words with long-range dependencies or are not directly connected in the dependency tree. We propose to utilize the self-attention mechanism to learn the dependencies between words with different syntactic distances.
  arXiv  Detail & Related papers  (2020-10-06T20:30:35Z)
• Relational Graph Attention Network for Aspect-based Sentiment Analysis [35.342467338880546]
  Aspect-based sentiment analysis aims to determine the sentiment polarity towards a specific aspect in online reviews. We propose a relational graph attention network (R-GAT) to encode the new tree structure for sentiment prediction. Experiments are conducted on the SemEval 2014 and Twitter datasets.
  arXiv  Detail & Related papers  (2020-04-26T12:21:04Z)
• Extractive Summarization as Text Matching [123.09816729675838]
  This paper creates a paradigm shift with regard to the way we build neural extractive summarization systems. We formulate the extractive summarization task as a semantic text matching problem. We have driven the state-of-the-art extractive result on CNN/DailyMail to a new level (44.41 in ROUGE-1)
  arXiv  Detail & Related papers  (2020-04-19T08:27:57Z)
• A Deep Neural Framework for Contextual Affect Detection [51.378225388679425]
  A short and simple text carrying no emotion can represent some strong emotions when reading along with its context. We propose a Contextual Affect Detection framework which learns the inter-dependence of words in a sentence.
  arXiv  Detail & Related papers  (2020-01-28T05:03:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.