Deep Inside-outside Recursive Autoencoder with All-span Objective
Deep inside-outside recursive autoencoder (DIORA) is a neural-based model designed for unsupervised constituency parsing. During its forward computation, it provides phrase and contextual representations for all spans in the input sentence. By utilizing the contextual representation of each leaf-level span, the span of length 1, to reconstruct the word inside the span, the model is trained without labeled data. In this work, we extend the training objective of DIORA by making use of all spans instead of only leaf-level spans. We test our new training objective on datasets of two languages: English and Japanese, and empirically show that our method achieves improvement in parsing accuracy over the original DIORA.
Code (0)
등록된 구현이 없습니다.
Tasks
AllConstituency ParsingSentenceSimilar Papers 제목 키워드 기반
Unsupervised Labeled Parsing with Deep Inside-Outside Recursive Autoencoders
Understanding text often requires identifying meaningful constituent spans such as noun phrases and verb phrases. In this work, we show that we can effectively recover these types of labels using the learned phrase vecto…
Constituency ParsingUnsupervised Latent Tree Induction with Deep Inside-Outside Recursive Autoencoders
We introduce deep inside-outside recursive autoencoders (DIORA), a fully-unsupervised method for discovering syntax that simultaneously learns representations for constituents within the induced tree. Our approach predic…
Constituency ParsingSentenceUnsupervised Latent Tree Induction with Deep Inside-Outside Recursive Auto-Encoders
We introduce the deep inside-outside recursive autoencoder (DIORA), a fully-unsupervised method for discovering syntax that simultaneously learns representations for constituents within the induced tree. Our approach pre…
Constituency Grammar InductionConstituency ParsingSentenceUnsupervised Parsing with S-DIORA: Single Tree Encoding for Deep Inside-Outside Recursive Autoencoders
The deep inside-outside recursive autoencoder (DIORA; Drozdov et al. 2019) is a self-supervised neural model that learns to induce syntactic tree structures for input sentences *without access to labeled training data*. …
Constituency Grammar InductionConstituency ParsingSentenceAugmenting Transformers with Recursively Composed Multi-grained Representations
We present ReCAT, a recursive composition augmented Transformer that is able to explicitly model hierarchical syntactic structures of raw texts without relying on gold trees during both learning and inference. Existing r…
Constituency Grammar InductionNatural Language InferenceSemantic Role LabelingSentence