Improving Aspect Sentiment Quad Prediction via Template-Order Data Augmentation

• URL: http://arxiv.org/abs/2210.10291v1
• Date: Wed, 19 Oct 2022 04:31:08 GMT
• Title: Improving Aspect Sentiment Quad Prediction via Template-Order Data Augmentation
• Authors: Mengting Hu, Yike Wu, Hang Gao, Yinhao Bai, Shiwan Zhao
• Abstract summary: aspect sentiment quad prediction (ASQP) has become a popular task in the field of aspect-level sentiment analysis. Previous work utilizes a predefined template to paraphrase the original sentence into a structure target sequence. We study the effects of template orders and find that some orders help the generative model achieve better performance.
• Score: 14.962445913454747
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recently, aspect sentiment quad prediction (ASQP) has become a popular task in the field of aspect-level sentiment analysis. Previous work utilizes a predefined template to paraphrase the original sentence into a structure target sequence, which can be easily decoded as quadruplets of the form (aspect category, aspect term, opinion term, sentiment polarity). The template involves the four elements in a fixed order. However, we observe that this solution contradicts with the order-free property of the ASQP task, since there is no need to fix the template order as long as the quadruplet is extracted correctly. Inspired by the observation, we study the effects of template orders and find that some orders help the generative model achieve better performance. It is hypothesized that different orders provide various views of the quadruplet. Therefore, we propose a simple but effective method to identify the most proper orders, and further combine multiple proper templates as data augmentation to improve the ASQP task. Specifically, we use the pre-trained language model to select the orders with minimal entropy. By fine-tuning the pre-trained language model with these template orders, our approach improves the performance of quad prediction, and outperforms state-of-the-art methods significantly in low-resource settings.

Related papers

• BvSP: Broad-view Soft Prompting for Few-Shot Aspect Sentiment Quad Prediction [10.313467662221319]
  Aspect sentiment quad prediction (ASQP) aims to predict four aspect-based elements, including aspect term, opinion term, aspect category, and sentiment polarity. This work formulates ASQP into the few-shot scenario, which aims for fast adaptation in real applications.
  arXiv  Detail & Related papers  (2024-06-11T15:32:32Z)
• Mind Your Format: Towards Consistent Evaluation of In-Context Learning Improvements [10.687101698324897]
  Large language models demonstrate a remarkable capability for learning to solve new tasks from a few examples. The prompt template, or the way the input examples are formatted to obtain the prompt, is an important yet often overlooked aspect of in-context learning. We show that a poor choice of the template can reduce the performance of the strongest models and inference methods to a random guess level.
  arXiv  Detail & Related papers  (2024-01-12T18:58:26Z)
• Prompt Algebra for Task Composition [131.97623832435812]
  We consider Visual Language Models with prompt tuning as our base classifier. We propose constrained prompt tuning to improve performance of the composite classifier. On UTZappos it improves classification accuracy over the best base model by 8.45% on average.
  arXiv  Detail & Related papers  (2023-06-01T03:20:54Z)
• Conditional set generation using Seq2seq models [52.516563721766445]
  Conditional set generation learns a mapping from an input sequence of tokens to a set. Sequence-to-sequence(Seq2seq) models are a popular choice to model set generation. We propose a novel algorithm for effectively sampling informative orders over the space of label orders.
  arXiv  Detail & Related papers  (2022-05-25T04:17:50Z)
• Learning and Analyzing Generation Order for Undirected Sequence Models [86.10875837475783]
  We train a policy that learns the generation order for a pre-trained, undirected translation model via reinforcement learning. We show that the translations by our learned orders achieve higher BLEU scores than the outputs decoded from left to right or decoded by the learned order from Mansimov et al. Our findings could provide more insights on the mechanism of undirected generation models and encourage further research in this direction.
  arXiv  Detail & Related papers  (2021-12-16T18:29:07Z)
• The Power of Prompt Tuning for Low-Resource Semantic Parsing [10.37371743879877]
  We investigate prompt tuning for semantic parsing. For large T5 models we find (i.e. that prompt tuning significantly outperforms fine-tuning in the low data regime) This last result is surprising as it suggests that large T5 models can be modulated to generate sequences far from the pre-training distribution.
  arXiv  Detail & Related papers  (2021-10-16T09:33:09Z)
• Improving Graph-based Sentence Ordering with Iteratively Predicted Pairwise Orderings [38.91604447717656]
  We propose a novel sentence ordering framework which introduces two classifiers to make better use of pairwise orderings for graph-based sentence ordering. Our model achieves state-of-the-art performance when equipped with BERT and FHDecoder.
  arXiv  Detail & Related papers  (2021-10-13T02:18:16Z)
• Template-free Prompt Tuning for Few-shot NER [46.59447116255979]
  We propose a more elegant method to reformulate NER tasks as LM problems without any templates. Specifically, we discard the template construction process while maintaining the word prediction paradigm of pre-training models. Experimental results demonstrate the effectiveness of the proposed method over bert-tagger and template-based method under few-shot setting.
  arXiv  Detail & Related papers  (2021-09-28T07:19:24Z)
• Automated Concatenation of Embeddings for Structured Prediction [75.44925576268052]
  We propose Automated Concatenation of Embeddings (ACE) to automate the process of finding better concatenations of embeddings for structured prediction tasks. We follow strategies in reinforcement learning to optimize the parameters of the controller and compute the reward based on the accuracy of a task model.
  arXiv  Detail & Related papers  (2020-10-10T14:03:20Z)
• Pre-training Is (Almost) All You Need: An Application to Commonsense Reasoning [61.32992639292889]
  Fine-tuning of pre-trained transformer models has become the standard approach for solving common NLP tasks. We introduce a new scoring method that casts a plausibility ranking task in a full-text format. We show that our method provides a much more stable training phase across random restarts.
  arXiv  Detail & Related papers  (2020-04-29T10:54:40Z)

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.