Composing Structure-Aware Batches for Pairwise Sentence Classification
Identifying the relation between two sentences requires datasets with pairwise annotations. In many cases, these datasets contain instances that are annotated multiple times as part of different pairs. They constitute a structure that contains additional helpful information about the inter-relatedness of the text instances based on the annotations. This paper investigates how this kind of structural dataset information can be exploited during training. We propose three batch composition strategies to incorporate such information and measure their performance over 14 heterogeneous pairwise sentence classification tasks. Our results show statistically significant improvements (up to 3.9%) - independent of the pre-trained language model - for most tasks compared to baselines that follow a standard training procedure. Further, we see that even this baseline procedure can profit from having such structural information in a low-resource setting.
Code (0)
등록된 구현이 없습니다.
Tasks
ClassificationLanguage ModelingLanguage ModellingSentenceSentence ClassificationSimilar Papers 제목 키워드 기반
Composing Structure-Aware Batches for Pairwise Sentence Classification
Identifying the relation between two sentences requires datasets with pairwise annotations. In many cases, these datasets contain instances that are annotated multiple times as part of different pairs. They constitute a …
ClassificationLanguage ModelingLanguage ModellingSentence+1iDiff: Interpretable Difference-aware Framework for Pairwise Image Quality Assessment
Pairwise image quality assessment (IQA) in professional photography requires a model not only to identify the preferred image between two candidates, but also to provide convincing and image-grounded reasoning. In the NT…
Image Quality AssessmentMultimodal ReasoningDecision MakingInstance-aware Image and Sentence Matching with Selective Multimodal LSTM
Effective image and sentence matching depends on how to well measure their global visual-semantic similarity. Based on the observation that such a global similarity arises from a complex aggregation of multiple local sim…
Semantic SimilaritySemantic Textual SimilaritySentenceTowards Structure-aware Paraphrase Identification with Phrase Alignment Using Sentence Encoders
Previous works have demonstrated the effectiveness of utilising pre-trained sentence encoders based on their sentence representations for meaning comparison tasks. Though such representations are shown to capture hidden …
Paraphrase IdentificationSensitivitySentenceConsistency-aware Shading Orders Selective Fusion for Intrinsic Image Decomposition
We address the problem of decomposing a single image into reflectance and shading. The difficulty comes from the fact that the components of image---the surface albedo, the direct illumination, and the ambient illuminati…
Intrinsic Image Decomposition