paper-with-me

홈 › Papers

Semantic-aware Contrastive Learning for More Accurate Semantic Parsing

2023-01-19 · Shan Wu, Chunlei Xin, Bo Chen, Xianpei Han, Le Sun

Since the meaning representations are detailed and accurate annotations which express fine-grained sequence-level semtantics, it is usually hard to train discriminative semantic parsers via Maximum Likelihood Estimation (MLE) in an autoregressive fashion. In this paper, we propose a semantic-aware contrastive learning algorithm, which can learn to distinguish fine-grained meaning representations and take the overall sequence-level semantic into consideration. Specifically, a multi-level online sampling algorithm is proposed to sample confusing and diverse instances. Three semantic-aware similarity functions are designed to accurately measure the distance between meaning representations as a whole. And a ranked contrastive loss is proposed to pull the representations of the semantic-identical instances together and push negative instances away. Experiments on two standard datasets show that our approach achieves significant improvements over MLE baselines and gets state-of-the-art performances by simply applying semantic-aware contrastive learning on a vanilla Seq2Seq model.

📄 PDF Abstract BibTeX arXiv:2301.07919

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive LearningSemantic Parsing

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
Contrastive Learning 설명 없음
Tanh Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…
Seq2Seq Seq2Seq, or Sequence To Sequence, is a model used in sequence prediction tasks, such as language modelling and machine translation. The idea is to use one…

Similar Papers 제목 키워드 기반

Semantic-Aware Dual Contrastive Learning for Multi-label Image Classification

2023-07-19 · Leilei Ma, Dengdi Sun, Lei Wang, Haifeng Zhao 외

Extracting image semantics effectively and assigning corresponding labels to multiple objects or attributes for natural images is challenging due to the complex scene contents and confusing label dependencies. Recent wor…

Contrastive Learningimage-classificationImage ClassificationMulti-Label Image Classification+2

KAAE: Numerical Reasoning for Knowledge Graphs via Knowledge-aware Attributes Learning

2024-11-20 · Ming Yin, Qiang Zhou, Zongsheng Cao, Mei Li

Numerical reasoning is pivotal in various artificial intelligence applications, such as natural language processing and recommender systems, where it involves using entities, relations, and attribute values (e.g., weight…

AttributeContrastive LearningKnowledge Graph EmbeddingsKnowledge Graphs+2

Keyword-Based Diverse Image Retrieval by Semantics-aware Contrastive Learning and Transformer

2023-05-06 · Minyi Zhao, Jinpeng Wang, Dongliang Liao, Yiru Wang 외

In addition to relevance, diversity is an important yet less studied performance metric of cross-modal image retrieval systems, which is critical to user experience. Existing solutions for diversity-aware image retrieval…

Contrastive LearningDiversityImage RetrievalRetrieval

HC$^2$L: Hybrid and Cooperative Contrastive Learning for Cross-lingual Spoken Language Understanding

2024-05-10 · Bowen Xing, Ivor W. Tsang

State-of-the-art model for zero-shot cross-lingual spoken language understanding performs cross-lingual unsupervised contrastive learning to achieve the label-agnostic semantic alignment between each utterance and its co…

Contrastive LearningSpoken Language Understanding

DAPO: Design Structure-Aware Pass Ordering in High-Level Synthesis with Graph Contrastive and Reinforcement Learning

2025-12-12 · Jinming Ge, Linfeng Du, Likith Anaparty, Shangkun Li 외 arxiv

High-Level Synthesis (HLS) tools are widely adopted in FPGA-based domain-specific accelerator design. However, existing tools rely on fixed optimization strategies inherited from software compilations, limiting their eff…

Reinforcement LearningContrastive Learning