paper-with-me

Papers

Hierarchical Poset Decoding for Compositional Generalization in Language

2020-10-15 · NeurIPS 2020 12 · Yinuo Guo, Zeqi Lin, Jian-Guang Lou, Dongmei Zhang

We formalize human language understanding as a structured prediction task where the output is a partially ordered set (poset). Current encoder-decoder architectures do not take the poset structure of semantics into account properly, thus suffering from poor compositional generalization ability. In this paper, we propose a novel hierarchical poset decoding paradigm for compositional generalization in language. Intuitively: (1) the proposed paradigm enforces partial permutation invariance in semantics, thus avoiding overfitting to bias ordering information; (2) the hierarchical mechanism allows to capture high-level structures of posets. We evaluate our proposed decoder on Compositional Freebase Questions (CFQ), a large and realistic natural language question answering dataset that is specifically designed to measure compositional generalization. Results show that it outperforms current decoders.

📄 PDF Abstract BibTeX arXiv:2010.07792

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderQuestion AnsweringSemantic ParsingStructured Prediction

Similar Papers 제목 키워드 기반

Exclusive Hierarchical Decoding for Deep Keyphrase Generation

2020-04-18 · ACL 2020 6 · Wang Chen, Hou Pong Chan, Piji Li, Irwin King

Keyphrase generation (KG) aims to summarize the main ideas of a document into a set of keyphrases. A new setting is recently introduced into this problem, in which, given a document, the model needs to predict a set of k…

DiversityKeyphrase Generation

Grounded Graph Decoding Improves Compositional Generalization in Question Answering

2021-11-05 · Findings (EMNLP) 2021 11 · Yu Gai, Paras Jain, Wendi Zhang, Joseph E. Gonzalez 외

Question answering models struggle to generalize to novel compositions of training patterns, such to longer sequences or more complex test structures. Current end-to-end models learn a flat input embedding which can lose…

Question Answering

Recursive Decoding: A Situated Cognition Approach to Compositional Generation in Grounded Language Understanding

2022-01-27 · Matthew Setzler, Scott Howland, Lauren Phillips

Compositional generalization is a troubling blind spot for neural language models. Recent efforts have presented techniques for improving a model's ability to encode novel combinations of known inputs, but less work has …

Decoder

Hierarchical Partial-Order Models for Ranking

2026-06-23 · Dongqing Li, Geoff K. Nicholls, Jeong Eun Lee, Chuxuan 외 arxiv

Rank aggregation combines information from ordered lists ranking items by preference. Classical parametric models for such data, including the Mallows and Plackett-Luce models, assume the orders concentrate around one or…

Bayesian Inference

Forming Trees with Treeformers

2022-07-14 · Nilay Patel, Jeffrey Flanigan

Human language is known to exhibit a nested, hierarchical structure, allowing us to form complex sentences out of smaller pieces. However, many state-of-the-art neural networks models such as Transformers have no explici…

Abstractive Text SummarizationInductive BiasMachine TranslationNatural Language Understanding+1