Sparse Fuzzy Attention for Structured Sentiment Analysis

• URL: http://arxiv.org/abs/2109.06719v2
• Date: Wed, 15 Sep 2021 08:38:33 GMT
• Title: Sparse Fuzzy Attention for Structured Sentiment Analysis
• Authors: Letain Peng, Zuchao Li and Hai Zhao
• Abstract summary: 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.
• Score: 48.69930912510414
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Attention scorers have achieved success in parsing tasks like semantic and syntactic dependency parsing. However, in tasks modeled into parsing, like structured sentiment analysis, "dependency edges" are very sparse which hinders parser performance. Thus we propose a sparse and fuzzy attention scorer with pooling layers which improves parser 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.

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)
• Unsupervised Chunking with Hierarchical RNN [62.15060807493364]
  This paper introduces an unsupervised approach to chunking, a syntactic task that involves grouping words in a non-hierarchical manner. We present a two-layer Hierarchical Recurrent Neural Network (HRNN) designed to model word-to-chunk and chunk-to-sentence compositions. Experiments on the CoNLL-2000 dataset reveal a notable improvement over existing unsupervised methods, enhancing phrase F1 score by up to 6 percentage points.
  arXiv  Detail & Related papers  (2023-09-10T02:55:12Z)
• Topic-driven Distant Supervision Framework for Macro-level Discourse Parsing [72.14449502499535]
  The task of analyzing the internal rhetorical structure of texts is a challenging problem in natural language processing. Despite the recent advances in neural models, the lack of large-scale, high-quality corpora for training remains a major obstacle. Recent studies have attempted to overcome this limitation by using distant supervision.
  arXiv  Detail & Related papers  (2023-05-23T07:13:51Z)
• X2Parser: Cross-Lingual and Cross-Domain Framework for Task-Oriented Compositional Semantic Parsing [51.81533991497547]
  Task-oriented compositional semantic parsing (TCSP) handles complex nested user queries. We present X2 compared a transferable Cross-lingual and Cross-domain for TCSP. We propose to predict flattened intents and slots representations separately and cast both prediction tasks into sequence labeling problems.
  arXiv  Detail & Related papers  (2021-06-07T16:40:05Z)
• Structured Sentiment Analysis as Dependency Graph Parsing [5.174808367448261]
  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.
  arXiv  Detail & Related papers  (2021-05-30T11:19:46Z)
• On Robustness of Neural Semantic Parsers [9.176739484385932]
  We provide the empirical study on the robustness of semantics in the presence of adversarial attacks. Formally, adversaries of semantic parsing are considered to be the perturbed utterance-LF pairs. Our results answered five research questions in measuring the sate-of-the-arts' performance on test sets, and evaluating the effect of data augmentation.
  arXiv  Detail & Related papers  (2021-02-02T15:41:28Z)
• From Sentiment Annotations to Sentiment Prediction through Discourse Augmentation [30.615883375573432]
  We propose a novel framework to exploit task-related discourse for the task of sentiment analysis. More specifically, we are combining the large-scale, sentiment-dependent MEGA-DT treebank with a novel neural architecture for sentiment prediction. Experiments show that our framework using sentiment-related discourse augmentations for sentiment prediction enhances the overall performance for long documents.
  arXiv  Detail & Related papers  (2020-11-05T18:28:13Z)
• Weakly-Supervised Aspect-Based Sentiment Analysis via Joint Aspect-Sentiment Topic Embedding [71.2260967797055]
  We propose a weakly-supervised approach for aspect-based sentiment analysis. We learn sentiment, aspect> joint topic embeddings in the word embedding space. We then use neural models to generalize the word-level discriminative information.
  arXiv  Detail & Related papers  (2020-10-13T21:33:24Z)
• Fast semantic parsing with well-typedness guarantees [78.76675218975768]
  AM dependency parsing is a principled method for neural semantic parsing with high accuracy across multiple graphbanks. We describe an A* and a transition-based for AM dependency parsing which guarantee well-typedness and improve parsing speed by up to 3 orders of magnitude.
  arXiv  Detail & Related papers  (2020-09-15T21:54:01Z)
• A Survey of Syntactic-Semantic Parsing Based on Constituent and Dependency Structures [14.714725860010724]
  We focus on two of the most popular formalizations of parsing: constituent parsing and dependency parsing. This article briefly reviews the representative models of constituent parsing and dependency parsing, and also dependency parsing with rich semantics.
  arXiv  Detail & Related papers  (2020-06-19T10:21:17Z)

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.