Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Meng, Yuanliang"'
Autor:
Meng, Yuanliang
This paper demonstrates a task to finetune a BART model so it can construct a sentence from an arbitrary set of words, which used to be a difficult NLP task. The training task is making sentences with four words, but the trained model can generate se
Externí odkaz:
http://arxiv.org/abs/2206.12565
Recent dialogue approaches operate by reading each word in a conversation history, and aggregating accrued dialogue information into a single state. This fixed-size vector is not expandable and must maintain a consistent format over time. Other recen
Externí odkaz:
http://arxiv.org/abs/1910.10487
Autor:
Meng, Yuanliang, Rumshisky, Anna
This paper proposes a Transformer-based model to generate equations for math word problems. It achieves much better results than RNN models when copy and align mechanisms are not used, and can outperform complex copy and align RNN models. We also sho
Externí odkaz:
http://arxiv.org/abs/1908.10924
Autor:
Meng, Yuanliang, Rumshisky, Anna
Publikováno v:
Proceedings of 27th International Conference on Computational Linguistics (2018) 35-43
We propose a triad-based neural network system that generates affinity scores between entity mentions for coreference resolution. The system simultaneously accepts three mentions as input, taking mutual dependency and logical constraints of all three
Externí odkaz:
http://arxiv.org/abs/1809.06491
In this paper, we propose to use a set of simple, uniform in architecture LSTM-based models to recover different kinds of temporal relations from text. Using the shortest dependency path between entities as input, the same architecture is used to ext
Externí odkaz:
http://arxiv.org/abs/1703.05851
Publikováno v:
2016 25th IEEE International Symposium on Robot & Human Interactive Communication (RO-MAN); 2016, p1126-1131, 6p
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
2016 11th ACM/IEEE International Conference on Human-Robot Interaction (HRI); 2016, p565-565, 1p
Publikováno v:
IEEE ... International Conference on Rehabilitation Robotics : [proceedings] [IEEE Int Conf Rehabil Robot] 2017 Jul; Vol. 2017, pp. 1233-1238.