English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

There has been great progress in unifying various table-to-text tasks using asingle encoder-decoder model trained via multi-task learning (Xie et al.,2022). However, existing methods typically encode task information with asimple dataset name as a prefix to the encoder. This not only limits theeffectiveness of multi-task learning, but also hinders the model's ability togeneralize to new domains or tasks that were not seen during training, which iscrucial for real-world applications. In this paper, we propose compositionaltask configurations, a set of prompts prepended to the encoder to improvecross-task generalization of unified models. We design the task configurationsto explicitly specify the task type, as well as its input and output types. Weshow that this not only allows the model to better learn shared knowledgeacross different tasks at training, but also allows us to control the model bycomposing new configurations that apply novel input-output combinations in azero-shot manner. We demonstrate via experiments over ten table-to-text tasksthat our method outperforms the UnifiedSKG baseline by noticeable margins inboth in-domain and zero-shot settings, with average improvements of +0.5 and+12.6 from using a T5-large backbone, respectively.

Improving Cross-task Generalization of Unified Table-to-text Models with Compositional Task Configurations