Processing sentence constituency trees in binarised form is a common and popular approach in literature. However, constituency trees are non-binary by nature. The binarisation procedure changes deeply the structure, furthering constituents that instead are close. In this work, we introduce a new approach to deal with non-binary constituency trees which leverages tensor-based models. In particular, we show how a powerful composition function based on the canonical tensor decomposition can exploit such a rich structure. A key point of our approach is the weight sharing constraint imposed on the factor matrices, which allows limiting the number of model parameters. Finally, we introduce a Tree-LSTM model which takes advantage of this composition function and we experimentally assess its performance on different NLP tasks.
Learning from Non-Binary Constituency Trees via Tensor Decomposition / Castellana, Daniele; Bacciu, Davide. - ELETTRONICO. - (2020), pp. 3899-3910. (Intervento presentato al convegno 28th International Conference on Computational Linguistics) [10.18653/v1/2020.coling-main.346].
Learning from Non-Binary Constituency Trees via Tensor Decomposition
Castellana, Daniele
;
2020
Abstract
Processing sentence constituency trees in binarised form is a common and popular approach in literature. However, constituency trees are non-binary by nature. The binarisation procedure changes deeply the structure, furthering constituents that instead are close. In this work, we introduce a new approach to deal with non-binary constituency trees which leverages tensor-based models. In particular, we show how a powerful composition function based on the canonical tensor decomposition can exploit such a rich structure. A key point of our approach is the weight sharing constraint imposed on the factor matrices, which allows limiting the number of model parameters. Finally, we introduce a Tree-LSTM model which takes advantage of this composition function and we experimentally assess its performance on different NLP tasks.File | Dimensione | Formato | |
---|---|---|---|
2020.coling-main.346.pdf
accesso aperto
Licenza:
Open Access
Dimensione
460 kB
Formato
Adobe PDF
|
460 kB | Adobe PDF |
I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.