Evaluating the Impact of Model Scale for Compositional Generalization in Semantic Parsing Article Swipe

MAKE IMPACT

Linlu Qiu , Peter Shaw , Panupong Pasupat , Tianze Shi , Jonathan Herzig , Emily Pitler , Fei Sha , Kristina Toutanova · YOU? · · 2022 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2205.12253

Despite their strong performance on many tasks, pre-trained language models have been shown to struggle on out-of-distribution compositional generalization. Meanwhile, recent work has shown considerable improvements on many NLP tasks from model scaling. Can scaling up model size also improve compositional generalization in semantic parsing? We evaluate encoder-decoder models up to 11B parameters and decoder-only models up to 540B parameters, and compare model scaling curves for three different methods for applying a pre-trained language model to a new task: fine-tuning all parameters, prompt tuning, and in-context learning. We observe that fine-tuning generally has flat or negative scaling curves on out-of-distribution compositional generalization in semantic parsing evaluations. In-context learning has positive scaling curves, but is generally outperformed by much smaller fine-tuned models. Prompt-tuning can outperform fine-tuning, suggesting further potential improvements from scaling as it exhibits a more positive scaling curve. Additionally, we identify several error trends that vary with model scale. For example, larger models are generally better at modeling the syntax of the output space, but are also more prone to certain types of overfitting. Overall, our study highlights limitations of current techniques for effectively leveraging model scale for compositional generalization, while our analysis also suggests promising directions for future work.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2205.12253

PDF

https://arxiv.org/pdf/2205.12253

OA Status

green

Cited By

4

Related Works

10

OpenAlex ID

https://openalex.org/W4281566743

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4281566743

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2205.12253

Digital Object Identifier

Title

Evaluating the Impact of Model Scale for Compositional Generalization in Semantic Parsing

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2022

Year of publication

Publication date

2022-05-24

Full publication date if available

Authors

Linlu Qiu, Peter Shaw, Panupong Pasupat, Tianze Shi, Jonathan Herzig, Emily Pitler, Fei Sha, Kristina Toutanova

List of authors in order

Landing page

https://arxiv.org/abs/2205.12253

Publisher landing page

PDF URL

https://arxiv.org/pdf/2205.12253

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2205.12253

Direct OA link when available

Concepts

Generalization, Overfitting, Computer science, Scaling, Context (archaeology), Parsing, Artificial intelligence, Syntax, Task (project management), Language model, Scale (ratio), Natural language processing, Machine learning, Mathematics, Artificial neural network, Economics, Management, Geometry, Mathematical analysis, Physics, Biology, Paleontology, Quantum mechanics

Top concepts (fields/topics) attached by OpenAlex

Cited by

4

Total citation count in OpenAlex

Citations by year (recent)

2024: 1, 2023: 2, 2022: 1

Per-year citation counts (last 5 years)

Related works (count)

10

Other works algorithmically related by OpenAlex

Full payload