We describe our exploratory system for the shallow surface realization task, which combines morphological inflection using character sequence-to-sequence models ...
We describe our exploratory system for the shallow surface realization task, which combines morphological inflection using character sequence-to-sequence ...
Preliminary linearization results were decent, with a small benefit from reranking to prefer valid output trees, but inadequate control over the words in ...
The OSU-FB pipeline for generation (Upasani et al., 2019) starts by generating inflected word forms in the tree using character seq2seq models.
The OSU/Facebook Realizer for SRST 2019: Seq2Seq Inflection and Serialized Tree2Tree Linearization. Kartikeya Upasani | David King | Jinfeng Rao | Anusha ...
2019. The OSU/Facebook Realizer for SRST 2019: Seq2Seq Inflection and Serialized Tree2Tree Linearization. In Proc. of the 2nd Workshop on Multilingual ...
The OSU/Facebook Realizer for SRST 2019: Seq2Seq Inflection and Serialized Tree2Tree Linearization · no code implementations • WS 2019 • Kartikeya Upasani ...
The OSU/Facebook Realizer for SRST 2019: Seq2Seq Inflection and Serialized Tree2Tree Linearization. K Upasani, D King, J Rao, A Balakrishnan, M White.
The OSU/Facebook Realizer for SRST 2019: Seq2Seq Inflection and Serialized Tree2Tree Linearization. K Upasani, D King, J Rao, A Balakrishnan, M White.
The OSU Realizer for SRST 18: Neural Sequence-to-Sequence. Inflection and Incremental Locality-Based Linearization. In Proc. of the Workshop on Multilingual.