paper-with-me

Papers

Structural generalization in COGS: Supertagging is (almost) all you need

2023-10-21 · Alban Petit, Caio Corro, François Yvon

In many Natural Language Processing applications, neural networks have been found to fail to generalize on out-of-distribution examples. In particular, several recent semantic parsing datasets have put forward important limitations of neural networks in cases where compositional generalization is required. In this work, we extend a neural graph-based semantic parsing framework in several ways to alleviate this issue. Notably, we propose: (1) the introduction of a supertagging step with valency constraints, expressed as an integer linear program; (2) a reduction of the graph prediction problem to the maximum matching problem; (3) the design of an incremental early-stopping training strategy to prevent overfitting. Experimentally, our approach significantly improves results on examples that require structural generalization in the COGS dataset, a known challenging benchmark for compositional generalization. Overall, our results confirm that structural constraints are important for generalization in semantic parsing.

📄 PDF Abstract BibTeX arXiv:2310.14124

Code (0)

등록된 구현이 없습니다.

Tasks

AllSemantic Parsing

Similar Papers 제목 키워드 기반

SLOG: A Structural Generalization Benchmark for Semantic Parsing

2023-10-23 · Bingzhi Li, Lucia Donatelli, Alexander Koller, Tal Linzen 외

The goal of compositional generalization benchmarks is to evaluate how well models generalize to new complex linguistic expressions. Existing benchmarks often focus on lexical generalization, the interpretation of novel …

Semantic Parsing

Compositional Generalization Requires Compositional Parsers

2021-10-16 · ACL ARR October 2021 10 · Anonymous

A growing body of research has focused on the task of \textit{compositional generalization}, the ability of a semantic parser to dynamically combine known linguistic elements in novel structures. We analyze the accuracy …

CogStereo: Neural Stereo Matching with Implicit Spatial Cognition Embedding

2025-10-25 · Lihuang Fang, Xiao Hu, Yuchen Zou, Hong Zhang arxiv

Deep stereo matching has advanced significantly on benchmark datasets through fine-tuning but falls short of the zero-shot generalization seen in foundation models in other vision tasks. We introduce CogStereo, a novel f…

Zero-shot GeneralizationDomain GeneralizationDisparity EstimationScene Understanding

TAG Parsing with Neural Networks and Vector Representations of Supertags

2017-09-01 · EMNLP 2017 9 · Jungo Kasai, Bob Frank, Tom McCoy, Owen Rambow 외

We present supertagging-based models for Tree Adjoining Grammar parsing that use neural network architectures and dense vector representation of supertags (elementary trees) to achieve state-of-the-art performance in unl…

SentenceTAG

A Dynamic Window Neural Network for CCG Supertagging

2016-10-10 · Huijia Wu, Jiajun Zhang, Cheng-qing Zong

Combinatory Category Grammar (CCG) supertagging is a task to assign lexical categories to each word in a sentence. Almost all previous methods use fixed context window sizes as input features. However, it is obvious that…

CCG SupertaggingSentenceWord Embeddings