paper-with-me

홈 › Papers

Assessing the Unitary RNN as an End-to-End Compositional Model of Syntax

2022-08-11 · Jean-Philippe Bernardy, Shalom Lappin

We show that both an LSTM and a unitary-evolution recurrent neural network (URN) can achieve encouraging accuracy on two types of syntactic patterns: context-free long distance agreement, and mildly context-sensitive cross serial dependencies. This work extends recent experiments on deeply nested context-free long distance dependencies, with similar results. URNs differ from LSTMs in that they avoid non-linear activation functions, and they apply matrix multiplication to word embeddings encoded as unitary matrices. This permits them to retain all information in the processing of an input string over arbitrary distances. It also causes them to satisfy strict compositionality. URNs constitute a significant advance in the search for explainable models in deep learning applied to NLP.

📄 PDF Abstract BibTeX arXiv:2208.05719

Code (0)

등록된 구현이 없습니다.

Tasks

Explainable ModelsWord Embeddings

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…

Similar Papers 제목 키워드 기반

Syntax-guided Neural Module Distillation to Probe Compositionality in Sentence Embeddings

2023-01-21 · Rohan Pandey

Past work probing compositionality in sentence embedding models faces issues determining the causal impact of implicit syntax representations. Given a sentence, we construct a neural module net based on its syntax parse …

Semantic CompositionSentenceSentence EmbeddingSentence-Embedding+1

An Examination of the Compositionality of Large Generative Vision-Language Models

2023-08-21 · Teli Ma, Rong Li, Junwei Liang

With the success of Large Language Models (LLMs), many Generative Vision-Language Models (GVLMs) have been constructed via multimodal instruction tuning. However, the performance of GVLMs in multimodal compositional reas…

Visual Reasoning

Contribution d’informations syntaxiques aux capacités de généralisation compositionelle des modèles seq2seq convolutifs (Assessing the Contribution of Syntactic Information for Compositional Generalization of seq2seq Convolutional Networks)

2021-06-01 · JEP/TALN/RECITAL 2021 6 · Diana Nicoleta Popa, William N. Havard, Maximin Coavoux, Eric Gaussier 외

Les modèles neuronaux de type seq2seq manifestent d’étonnantes capacités de prédiction quand ils sont entraînés sur des données de taille suffisante. Cependant, ils échouent à généraliser de manière satisfaisante quand l…

Towards Syntax-aware Compositional Distributional Semantic Models

2014-08-01 · COLING 2014 8 · Lorenzo Ferrone, Fabio Massimo Zanzotto
Document SummarizationMulti-Document SummarizationNatural Language InferenceSemantic Textual Similarity

The Role of Syntax in Vector Space Models of Compositional Semantics

2013-08-01 · ACL 2013 8 · Karl Moritz Hermann, Phil Blunsom
Semantic Composition