SyGNS: A Systematic Generalization Testbed Based on Natural Language Semantics

• URL: http://arxiv.org/abs/2106.01077v1
• Date: Wed, 2 Jun 2021 11:24:41 GMT
• Title: SyGNS: A Systematic Generalization Testbed Based on Natural Language Semantics
• Authors: Hitomi Yanaka, Koji Mineshima, Kentaro Inui
• Abstract summary: We propose a Systematic Generalization testbed based on Natural language Semantics (SyGNS) We test whether neural networks can systematically parse sentences involving novel combinations of logical expressions such as quantifiers and negation. Experiments show that Transformer and GRU models can generalize to unseen combinations of quantifiers, negations, and modifier that are similar to given training instances in form, but not to the others.
• Score: 39.845425535943534
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recently, deep neural networks (DNNs) have achieved great success in semantically challenging NLP tasks, yet it remains unclear whether DNN models can capture compositional meanings, those aspects of meaning that have been long studied in formal semantics. To investigate this issue, we propose a Systematic Generalization testbed based on Natural language Semantics (SyGNS), whose challenge is to map natural language sentences to multiple forms of scoped meaning representations, designed to account for various semantic phenomena. Using SyGNS, we test whether neural networks can systematically parse sentences involving novel combinations of logical expressions such as quantifiers and negation. Experiments show that Transformer and GRU models can generalize to unseen combinations of quantifiers, negations, and modifiers that are similar to given training instances in form, but not to the others. We also find that the generalization performance to unseen combinations is better when the form of meaning representations is simpler. The data and code for SyGNS are publicly available at https://github.com/verypluming/SyGNS.

Related papers

• Training Neural Networks as Recognizers of Formal Languages [87.06906286950438]
  Formal language theory pertains specifically to recognizers. It is common to instead use proxy tasks that are similar in only an informal sense. We correct this mismatch by training and evaluating neural networks directly as binary classifiers of strings.
  arXiv  Detail & Related papers  (2024-11-11T16:33:25Z)
• Laziness Is a Virtue When It Comes to Compositionality in Neural Semantic Parsing [20.856601758389544]
  We introduce a neural semantic parsing generation method that constructs logical forms from the bottom up, beginning from the logical form's leaves. We show that our novel, bottom-up parsing semantic technique outperforms general-purpose semantics while also being competitive with comparable neurals.
  arXiv  Detail & Related papers  (2023-05-07T17:53:08Z)
• Permutation Equivariant Neural Functionals [92.0667671999604]
  This work studies the design of neural networks that can process the weights or gradients of other neural networks. We focus on the permutation symmetries that arise in the weights of deep feedforward networks because hidden layer neurons have no inherent order. In our experiments, we find that permutation equivariant neural functionals are effective on a diverse set of tasks.
  arXiv  Detail & Related papers  (2023-02-27T18:52:38Z)
• Neural-Symbolic Recursive Machine for Systematic Generalization [113.22455566135757]
  We introduce the Neural-Symbolic Recursive Machine (NSR), whose core is a Grounded Symbol System (GSS) NSR integrates neural perception, syntactic parsing, and semantic reasoning. We evaluate NSR's efficacy across four challenging benchmarks designed to probe systematic generalization capabilities.
  arXiv  Detail & Related papers  (2022-10-04T13:27:38Z)
• Equivariant Transduction through Invariant Alignment [71.45263447328374]
  We introduce a novel group-equivariant architecture that incorporates a group-in hard alignment mechanism. We find that our network's structure allows it to develop stronger equivariant properties than existing group-equivariant approaches. We additionally find that it outperforms previous group-equivariant networks empirically on the SCAN task.
  arXiv  Detail & Related papers  (2022-09-22T11:19:45Z)
• Sequence-to-Sequence Learning with Latent Neural Grammars [12.624691611049341]
  Sequence-to-sequence learning with neural networks has become the de facto standard for sequence prediction tasks. While flexible and performant, these models often require large datasets for training and can fail spectacularly on benchmarks designed to test for compositional generalization. This work explores an alternative, hierarchical approach to sequence-to-sequence learning with quasi-synchronous grammars.
  arXiv  Detail & Related papers  (2021-09-02T17:58:08Z)
• Can RNNs learn Recursive Nested Subject-Verb Agreements? [4.094098809740732]
  Language processing requires the ability to extract nested tree structures. Recent advances in Recurrent Neural Networks (RNNs) achieve near-human performance in some language tasks.
  arXiv  Detail & Related papers  (2021-01-06T20:47:02Z)
• Unnatural Language Inference [48.45003475966808]
  We find that state-of-the-art NLI models, such as RoBERTa and BART, are invariant to, and sometimes even perform better on, examples with randomly reordered words. Our findings call into question the idea that our natural language understanding models, and the tasks used for measuring their progress, genuinely require a human-like understanding of syntax.
  arXiv  Detail & Related papers  (2020-12-30T20:40:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.