paper-with-me

홈 › Papers

LSTMs Can Learn Syntax-Sensitive Dependencies Well, But Modeling Structure Makes Them Better

2018-07-01 · ACL 2018 7 · Adhiguna Kuncoro, Chris Dyer, John Hale, Dani Yogatama, Stephen Clark, Phil Blunsom

Language exhibits hierarchical structure, but recent work using a subject-verb agreement diagnostic argued that state-of-the-art language models, LSTMs, fail to learn long-range syntax sensitive dependencies. Using the same diagnostic, we show that, in fact, LSTMs do succeed in learning such dependencies{---}provided they have enough capacity. We then explore whether models that have access to explicit syntactic information learn agreement more effectively, and how the way in which this structural information is incorporated into the model impacts performance. We find that the mere presence of syntactic information does not improve accuracy, but when model architecture is determined by syntax, number agreement is improved. Further, we find that the choice of how syntactic structure is built affects how well number agreement is learned: top-down construction outperforms left-corner and bottom-up variants in capturing non-local structural dependencies.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

DiagnosticLanguage ModelingLanguage ModellingMachine TranslationText Summarization

Similar Papers 제목 키워드 기반

Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependencies

2016-11-04 · TACL 2016 1 · Tal Linzen, Emmanuel Dupoux, Yoav Goldberg

The success of long short-term memory (LSTM) neural networks in language processing is typically attributed to their ability to capture long-distance statistical regularities. Linguistic regularities are often sensitive …

Language ModelingLanguage Modelling

Attribution Analysis of Grammatical Dependencies in LSTMs

2020-04-30 · Yiding Hao

LSTM language models have been shown to capture syntax-sensitive grammatical dependencies such as subject-verb agreement with a high degree of accuracy (Linzen et al., 2016, inter alia). However, questions remain regardi…

How much complexity does an RNN architecture need to learn syntax-sensitive dependencies?

2020-05-17 · ACL 2020 6 · Gantavya Bhatt, Hritik Bansal, Rishubh Singh, Sumeet Agarwal

Long short-term memory (LSTM) networks and their variants are capable of encapsulating long-range dependencies, which is evident from their performance on a variety of linguistic tasks. On the other hand, simple recurren…

Language ModelingLanguage ModellingSentence

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 cro…

Explainable ModelsWord Embeddings

The emergence of number and syntax units in LSTM language models

2019-03-18 · NAACL 2019 6 · Yair Lakretz, German Kruszewski, Theo Desbordes, Dieuwke Hupkes 외

Recent work has shown that LSTMs trained on a generic language modeling objective capture syntax-sensitive generalizations such as long-distance number agreement. We have however no mechanistic understanding of how they …

Language ModelingLanguage Modelling