Modeling Comparative Logical Relation with Contrastive Learning for Text Generation
Data-to-Text Generation (D2T), a classic natural language generation problem, aims at producing fluent descriptions for structured input data, such as a table. Existing D2T works mainly focus on describing the superficial associative relations among entities, while ignoring the deep comparative logical relations, such as A is better than B in a certain aspect with a corresponding opinion, which is quite common in our daily life. In this paper, we introduce a new D2T task named comparative logical relation generation (CLRG). Additionally, we propose a Comparative Logic (CoLo) based text generation method, which generates texts following specific comparative logical relations with contrastive learning. Specifically, we first construct various positive and negative samples by fine-grained perturbations in entities, aspects and opinions. Then, we perform contrastive learning in the encoder layer to have a better understanding of the comparative logical relations, and integrate it in the decoder layer to guide the model to correctly generate the relations. Noting the data scarcity problem, we construct a Chinese Comparative Logical Relation Dataset (CLRD), which is a high-quality human-annotated dataset and challenging for text generation with descriptions of multiple entities and annotations on their comparative logical relations. Extensive experiments show that our method achieves impressive performance in both automatic and human evaluations.
Code (0)
등록된 구현이 없습니다.
Tasks
Contrastive LearningData-to-Text GenerationDecoderRelationText GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
DeepCL: Deep Change Feature Learning on Remote Sensing Images in the Metric Space
Change detection (CD) is an important yet challenging task in the Earth observation field for monitoring Earth surface dynamics. The advent of deep learning techniques has recently propelled automatic CD into a technolog…
Change DetectionEarth ObservationMetric LearningMorphology-Aware Multimodal Representation Learning for Insect Phylogenetic Reconstruction
Morphological traits provide important evidence for phylogenetic reconstruction and evolutionary relationship analysis. Recent image-based approaches have introduced deep learning, particularly convolutional models, to d…
parameter-efficient fine-tuningRepresentation LearningContrastive LearningNeuro-Symbolic Contrastive Learning for Cross-domain Inference
Pre-trained language models (PLMs) have made significant advances in natural language inference (NLI) tasks, however their sensitivity to textual perturbations and dependence on large datasets indicate an over-reliance o…
Contrastive LearningInductive logic programmingNatural Language InferenceA Comparative Analysis of the Ensemble Methods for Drug Design
Quantitative structure-activity relationship (QSAR) is a computer modeling technique for identifying relationships between the structural properties of chemical compounds and biological activity. QSAR modeling is necessa…
Drug DesignDrug DiscoveryEnsemble LearningContrastive Learning Subspace for Text Clustering
Contrastive learning has been frequently investigated to learn effective representations for text clustering tasks. While existing contrastive learning-based text clustering methods only focus on modeling instance-wise s…
ClusteringContrastive LearningSemantic SimilaritySemantic Textual Similarity+1