Improving Encoder by Auxiliary Supervision Tasks for Table-to-Text Generation
Table-to-text generation aims at automatically generating natural text to help people conveniently obtain salient information in tables. Although neural models for table-to-text have achieved remarkable progress, some problems are still overlooked. Previous methods cannot deduce the factual results from the entity{'}s (player or team) performance and the relations between entities. To solve this issue, we first build an entity graph from the input tables and introduce a reasoning module to perform reasoning on the graph. Moreover, there are different relations (e.g., the numeric size relation and the importance relation) between records in different dimensions. And these relations may contribute to the data-to-text generation. However, it is hard for a vanilla encoder to capture these. Consequently, we propose to utilize two auxiliary tasks, Number Ranking (NR) and Importance Ranking (IR), to supervise the encoder to capture the different relations. Experimental results on ROTOWIRE and RW-FG show that our method not only has a good generalization but also outperforms previous methods on several metrics: BLEU, Content Selection, Content Ordering.
Code (1)
Tasks
Data-to-Text GenerationRelationTable-to-Text GenerationText GenerationSimilar Papers 제목 키워드 기반
Multitask Learning with Low-Level Auxiliary Tasks for Encoder-Decoder Based Speech Recognition
End-to-end training of deep learning-based models allows for implicit learning of intermediate representations based on the final task loss. However, the end-to-end approach ignores the useful domain knowledge encoded in…
DecoderPhoneme Recognitionspeech-recognitionSpeech RecognitionEvaluating Factor-Wise Auxiliary Dynamics Supervision for Latent Structure and Robustness in Simulated Humanoid Locomotion
We evaluate whether factor-wise auxiliary dynamics supervision produces useful latent structure or improved robustness in simulated humanoid locomotion. DynaMITE -- a transformer encoder with a factored 24-d latent train…
Alternating Weak Triphone/BPE Alignment Supervision from Hybrid Model Improves End-to-End ASR
In this paper, alternating weak triphone/BPE alignment supervision is proposed to improve end-to-end model training. Towards this end, triphone and BPE alignments are extracted using a pre-existing hybrid ASR system. The…
Towards Lifelong Self-Supervision For Unpaired Image-to-Image Translation
Unpaired Image-to-Image Translation (I2IT) tasks often suffer from lack of data, a problem which self-supervised learning (SSL) has recently been very popular and successful at tackling. Leveraging auxiliary tasks such a…
ColorizationContinual LearningImage-to-Image TranslationSelf-Supervised Learning+1Reference-based Variational Autoencoders
Learning disentangled representations from visual data, where different high-level generative factors are independently encoded, is of importance for many computer vision tasks. Solving this problem, however, typically r…
AttributeConditional Image GenerationImage Generation