A Self-enhancement Multitask Framework for Unsupervised Aspect Category Detection

• URL: http://arxiv.org/abs/2311.09708v1
• Date: Thu, 16 Nov 2023 09:35:24 GMT
• Title: A Self-enhancement Multitask Framework for Unsupervised Aspect Category Detection
• Authors: Thi-Nhung Nguyen, Hoang Ngo, Kiem-Hieu Nguyen, Tuan-Dung Cao
• Abstract summary: This work addresses the problem of unsupervised Aspect Category Detection using a small set of seed words. We propose a framework that automatically enhances the quality of initial seed words and selects high-quality sentences for training. In addition, we jointly train Aspect Category Detection with Aspect Term Extraction and Aspect Term Polarity to further enhance performance.
• Score: 0.24578723416255754
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Our work addresses the problem of unsupervised Aspect Category Detection using a small set of seed words. Recent works have focused on learning embedding spaces for seed words and sentences to establish similarities between sentences and aspects. However, aspect representations are limited by the quality of initial seed words, and model performances are compromised by noise. To mitigate this limitation, we propose a simple framework that automatically enhances the quality of initial seed words and selects high-quality sentences for training instead of using the entire dataset. Our main concepts are to add a number of seed words to the initial set and to treat the task of noise resolution as a task of augmenting data for a low-resource task. In addition, we jointly train Aspect Category Detection with Aspect Term Extraction and Aspect Term Polarity to further enhance performance. This approach facilitates shared representation learning, allowing Aspect Category Detection to benefit from the additional guidance offered by other tasks. Extensive experiments demonstrate that our framework surpasses strong baselines on standard datasets.

Related papers

• Manual Verbalizer Enrichment for Few-Shot Text Classification [1.860409237919611]
  acrshortmave is an approach for verbalizer construction by enrichment of class labels. Our model achieves state-of-the-art results while using significantly fewer resources.
  arXiv  Detail & Related papers  (2024-10-08T16:16:47Z)
• Betrayed by Captions: Joint Caption Grounding and Generation for Open Vocabulary Instance Segmentation [80.48979302400868]
  We focus on open vocabulary instance segmentation to expand a segmentation model to classify and segment instance-level novel categories. Previous approaches have relied on massive caption datasets and complex pipelines to establish one-to-one mappings between image regions and captions in nouns. We devise a joint textbfCaption Grounding and Generation (CGG) framework, which incorporates a novel grounding loss that only focuses on matching object to improve learning efficiency.
  arXiv  Detail & Related papers  (2023-01-02T18:52:12Z)
• Fine-Grained Visual Entailment [51.66881737644983]
  We propose an extension of this task, where the goal is to predict the logical relationship of fine-grained knowledge elements within a piece of text to an image. Unlike prior work, our method is inherently explainable and makes logical predictions at different levels of granularity. We evaluate our method on a new dataset of manually annotated knowledge elements and show that our method achieves 68.18% accuracy at this challenging task.
  arXiv  Detail & Related papers  (2022-03-29T16:09:38Z)
• On Guiding Visual Attention with Language Specification [76.08326100891571]
  We use high-level language specification as advice for constraining the classification evidence to task-relevant features, instead of distractors. We show that supervising spatial attention in this way improves performance on classification tasks with biased and noisy data.
  arXiv  Detail & Related papers  (2022-02-17T22:40:19Z)
• Dense Contrastive Visual-Linguistic Pretraining [53.61233531733243]
  Several multimodal representation learning approaches have been proposed that jointly represent image and text. These approaches achieve superior performance by capturing high-level semantic information from large-scale multimodal pretraining. We propose unbiased Dense Contrastive Visual-Linguistic Pretraining to replace the region regression and classification with cross-modality region contrastive learning.
  arXiv  Detail & Related papers  (2021-09-24T07:20:13Z)
• The Single-Noun Prior for Image Clustering [34.97652735163338]
  Self-supervised clustering methods have achieved increasing accuracy in recent years but do not yet perform as well as supervised classification methods. We introduce the "single-noun" prior - which states that semantic clusters tend to correspond to concepts that humans label by a single-noun. We show that our formulation is a special case of the facility location problem, and introduce a simple-yet-effective approach for solving this optimization task at scale.
  arXiv  Detail & Related papers  (2021-04-08T17:54:37Z)
• 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)
• Dynamic Semantic Matching and Aggregation Network for Few-shot Intent Detection [69.2370349274216]
  Few-shot Intent Detection is challenging due to the scarcity of available annotated utterances. Semantic components are distilled from utterances via multi-head self-attention. Our method provides a comprehensive matching measure to enhance representations of both labeled and unlabeled instances.
  arXiv  Detail & Related papers  (2020-10-06T05:16:38Z)
• User-Guided Aspect Classification for Domain-Specific Texts [25.16272160909319]
  We study the problem of classifying aspects based on only a few user-provided seed words for pre-defined aspects. The major challenge lies in how to handle the noisy misc aspect, which is designed for texts without any pre-defined aspects. We propose a novel framework, ARYA, which enables mutual enhancements between pre-defined aspects and the misc aspect.
  arXiv  Detail & Related papers  (2020-04-30T03:14:16Z)

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.