IIE-NLP-Eyas at SemEval-2021 Task 4: Enhancing PLM for ReCAM with Special Tokens, Re-Ranking, Siamese Encoders and Back Translation

• URL: http://arxiv.org/abs/2102.12777v1
• Date: Thu, 25 Feb 2021 10:51:48 GMT
• Title: IIE-NLP-Eyas at SemEval-2021 Task 4: Enhancing PLM for ReCAM with Special Tokens, Re-Ranking, Siamese Encoders and Back Translation
• Authors: Yuqiang Xie, Luxi Xing, Wei Peng, Yue Hu
• Abstract summary: This paper introduces our systems for all three subtasks of SemEval-2021 Task 4: Reading of Abstract Meaning. We well-design many simple and effective approaches adapted to the backbone model (RoBERTa) Experimental results show that our approaches achieve significant performance compared with the baseline systems.
• Score: 8.971288666318719
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper introduces our systems for all three subtasks of SemEval-2021 Task 4: Reading Comprehension of Abstract Meaning. To help our model better represent and understand abstract concepts in natural language, we well-design many simple and effective approaches adapted to the backbone model (RoBERTa). Specifically, we formalize the subtasks into the multiple-choice question answering format and add special tokens to abstract concepts, then, the final prediction of question answering is considered as the result of subtasks. Additionally, we employ many finetuning tricks to improve the performance. Experimental results show that our approaches achieve significant performance compared with the baseline systems. Our approaches achieve eighth rank on subtask-1 and tenth rank on subtask-2.

Related papers

• Bag of Tricks for Effective Language Model Pretraining and Downstream Adaptation: A Case Study on GLUE [93.98660272309974]
  This report briefly describes our submission Vega v1 on the General Language Understanding Evaluation leaderboard. GLUE is a collection of nine natural language understanding tasks, including question answering, linguistic acceptability, sentiment analysis, text similarity, paraphrase detection, and natural language inference. With our optimized pretraining and fine-tuning strategies, our 1.3 billion model sets new state-of-the-art on 4/9 tasks, achieving the best average score of 91.3.
  arXiv  Detail & Related papers  (2023-02-18T09:26:35Z)
• Effective Cross-Task Transfer Learning for Explainable Natural Language Inference with T5 [50.574918785575655]
  We compare sequential fine-tuning with a model for multi-task learning in the context of boosting performance on two tasks. Our results show that while sequential multi-task learning can be tuned to be good at the first of two target tasks, it performs less well on the second and additionally struggles with overfitting.
  arXiv  Detail & Related papers  (2022-10-31T13:26:08Z)
• Instruction Tuning for Few-Shot Aspect-Based Sentiment Analysis [72.9124467710526]
  generative approaches have been proposed to extract all four elements as (one or more) quadruplets from text as a single task. We propose a unified framework for solving ABSA, and the associated sub-tasks to improve the performance in few-shot scenarios.
  arXiv  Detail & Related papers  (2022-10-12T23:38:57Z)
• COLO: A Contrastive Learning based Re-ranking Framework for One-Stage Summarization [84.70895015194188]
  We propose a Contrastive Learning based re-ranking framework for one-stage summarization called COLO. COLO boosts the extractive and abstractive results of one-stage systems on CNN/DailyMail benchmark to 44.58 and 46.33 ROUGE-1 score.
  arXiv  Detail & Related papers  (2022-09-29T06:11:21Z)
• SemEval-2021 Task 4: Reading Comprehension of Abstract Meaning [47.49596196559958]
  This paper introduces the SemEval-2021 shared task 4: Reading of Abstract Meaning (ReCAM) Given a passage and the corresponding question, a participating system is expected to choose the correct answer from five candidates of abstract concepts. Subtask 1 aims to evaluate how well a system can model concepts that cannot be directly perceived in the physical world. Subtask 2 focuses on models' ability in comprehending nonspecific concepts located high in a hypernym hierarchy. Subtask 3 aims to provide some insights into models' generalizability over the two types of abstractness.
  arXiv  Detail & Related papers  (2021-05-31T11:04:17Z)
• ReCAM@IITK at SemEval-2021 Task 4: BERT and ALBERT based Ensemble for Abstract Word Prediction [2.482368922343792]
  We fine-tuned the pre-trained masked language models namely BERT and ALBERT. We tried multiple approaches and found that Masked Language Modeling(MLM) based approach works the best.
  arXiv  Detail & Related papers  (2021-04-04T08:22:19Z)
• XRJL-HKUST at SemEval-2021 Task 4: WordNet-Enhanced Dual Multi-head Co-Attention for Reading Comprehension of Abstract Meaning [6.55600662108243]
  This paper presents our submitted system to SemEval 2021 Task 4: Reading of Abstract Meaning. Our system uses a large pre-trained language model as the encoder and an additional dual multi-head co-attention layer to strengthen the relationship between passages and question-answer pairs. Our system, called WordNet-enhanced DUal Multi-head Co-Attention (WN-DUMA), achieves 86.67% and 89.99% accuracy on the official blind test set of subtask 1 and subtask 2 respectively.
  arXiv  Detail & Related papers  (2021-03-30T06:22:58Z)
• ZJUKLAB at SemEval-2021 Task 4: Negative Augmentation with Language Model for Reading Comprehension of Abstract Meaning [16.151203366447962]
  We explain the algorithms used to learn our models and the process of tuning the algorithms and selecting the best model. Inspired by the similarity of the ReCAM task and the language pre-training, we propose a simple yet effective technology, namely, negative augmentation with language model. Our models achieve the 4th rank on both official test sets of Subtask 1 and Subtask 2 with an accuracy of 87.9% and an accuracy of 92.8%, respectively.
  arXiv  Detail & Related papers  (2021-02-25T13:03:05Z)
• IIE-NLP-NUT at SemEval-2020 Task 4: Guiding PLM with Prompt Template Reconstruction Strategy for ComVE [13.334749848189826]
  We formalize the subtasks into the multiple-choice question answering format and construct the input with the prompt templates. Experimental results show that our approaches achieve significant performance compared with the baseline systems. Our approaches secure the third rank on both official test sets of the first two subtasks with an accuracy of 96.4 and an accuracy of 94.3 respectively.
  arXiv  Detail & Related papers  (2020-07-02T06:59:53Z)
• Meta Reinforcement Learning with Autonomous Inference of Subtask Dependencies [57.27944046925876]
  We propose and address a novel few-shot RL problem, where a task is characterized by a subtask graph. Instead of directly learning a meta-policy, we develop a Meta-learner with Subtask Graph Inference. Our experiment results on two grid-world domains and StarCraft II environments show that the proposed method is able to accurately infer the latent task parameter.
  arXiv  Detail & Related papers  (2020-01-01T17:34:00Z)

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.