[PDF] CLOSURE: Assessing Systematic Generalization of CLEVR Models | Semantic Scholar

[PDF] CLOSURE: Assessing Systematic Generalization of CLEVR Models | Semantic Scholar

The CLEVR dataset of natural-looking questions about 3D-rendered scenes has recently received much attention from the research community. A number of models have been proposed for this task, many of which achieved very high accuracies of around 97-99%. In this work, we study how systematic the generalization of such models is, that is to which extent they are capable of handling novel combinations of known linguistic constructs. To this end, we define 7 additional question families which test models’ understanding of similarity-based references (such as e.g. “the object that has the same size as ...”) in novel contexts. Our experiments on the thereby constructed CLOSURE benchmark show that state-of-the-art models often do not exhibit systematicity after being trained on CLEVR. Surprisingly, we find that the explicitly compositional Neural Module Network model also generalizes badly on CLOSURE, even when it has access to the ground-truth programs at test time. We improve the NMN’s syste

1 mentions: @nlpmattg
Date: 2020/01/15 17:21

Referring Tweets

@nlpmattg A follow-on to this paper by most of the same folks: t.co/gJFLRtFGXU t.co/t6qlqrhubl

Related Entries

Read more 109 - What Does Your Model Know About Language, with Ellie Pavlick by NLP Highlights | Free Listenin...
0 users, 1 mentions 2020/03/30 18:52
Read more GitHub - keunwoochoi/openmic-2018-tfrecord
0 users, 1 mentions 2020/04/16 21:51
Read more [1910.13069] Disentangling Timbre and Singing Style with Multi-singer Singing Synthesis Systemopen s...
0 users, 1 mentions 2020/05/18 02:21
Read more [2002.07016] Meta-learning Extractors for Music Source Separationopen searchopen navigation menucont...
0 users, 1 mentions 2020/05/18 02:21
Read more 集団スポーツの選手軌道予測
0 users, 1 mentions 2020/07/18 05:21