paper-with-me

홈 › Papers

Sentence Encoding with Tree-constrained Relation Networks

2018-11-26 · Lei Yu, Cyprien de Masson d'Autume, Chris Dyer, Phil Blunsom, Lingpeng Kong, Wang Ling

The meaning of a sentence is a function of the relations that hold between its words. We instantiate this relational view of semantics in a series of neural models based on variants of relation networks (RNs) which represent a set of objects (for us, words forming a sentence) in terms of representations of pairs of objects. We propose two extensions to the basic RN model for natural language. First, building on the intuition that not all word pairs are equally informative about the meaning of a sentence, we use constraints based on both supervised and unsupervised dependency syntax to control which relations influence the representation. Second, since higher-order relations are poorly captured by a sum of pairwise relations, we use a recurrent extension of RNs to propagate information so as to form representations of higher order relations. Experiments on sentence classification, sentence pair classification, and machine translation reveal that, while basic RNs are only modestly effective for sentence representation, recurrent RNs with latent syntax are a reliably powerful representational device.

📄 PDF Abstract BibTeX arXiv:1811.10475

Code (0)

등록된 구현이 없습니다.

Tasks

General ClassificationMachine TranslationRelationSentenceSentence ClassificationSentence-Pair ClassificationTranslation

Similar Papers 제목 키워드 기반

Graph-tree Fusion Model with Bidirectional Information Propagation for Long Document Classification

2024-10-03 · Sudipta Singha Roy, Xindi Wang, Robert E. Mercer, Frank Rudzicz

Long document classification presents challenges in capturing both local and global dependencies due to their extensive content and complex structure. Existing methods often struggle with token limits and fail to adequat…

Document ClassificationGraph AttentionSentence

Dependency Position Encoding for Relation Extraction

2022-07-01 · Findings (NAACL) 2022 7 · Qiushi Guo, Xin Wang, Dehong Gao

Leveraging the dependency tree of the input sentence is able to improve the model performance for relation extraction. A challenging issue is how to remove confusions from the tree. Efforts have been made to utilize the …

PositionRelationRelation ExtractionSentence

A Unifying Theory of Transition-based and Sequence Labeling Parsing

2020-11-01 · COLING 2020 8 · Carlos Gómez-Rodríguez, Michalina Strzyz, David Vilares

We define a mapping from transition-based parsing algorithms that read sentences from left to right to sequence labeling encodings of syntactic trees. This not only establishes a theoretical relation between transition-b…

Dependency Parsing

Syntax Encoding with Application in Authorship Attribution

2018-10-01 · EMNLP 2018 10 · Richong Zhang, Zhiyuan Hu, Hongyu Guo, Yongyi Mao

We propose a novel strategy to encode the syntax parse tree of sentence into a learnable distributed representation. The proposed syntax encoding scheme is provably information-lossless. In specific, an embedding vector …

Authorship AttributionBenchmarkingFeature EngineeringSentence+1

Natural Language Inference by Tree-Based Convolution and Heuristic Matching

2015-12-28 · ACL 2016 8 · Lili Mou, Rui Men, Ge Li, Yan Xu 외

In this paper, we propose the TBCNN-pair model to recognize entailment and contradiction between two sentences. In our model, a tree-based convolutional neural network (TBCNN) captures sentence-level semantics; then heur…

Natural Language InferenceSentence