Context-Aware Machine Translation with Source Coreference Explanation
Huy Hien Vu, Hidetaka Kamigaito, Taro Watanabe
https://arxiv.org/abs/2404.19505 https://arxiv.org/pdf/2404.19505
arXiv:2404.19505v1 Announce Type: new
Abstract: Despite significant improvements in enhancing the quality of translation, context-aware machine translation (MT) models underperform in many cases. One of the main reasons is that they fail to utilize the correct features from context when the context is too long or their models are overly complex. This can lead to the explain-away effect, wherein the models only consider features easier to explain predictions, resulting in inaccurate translations. To address this issue, we propose a model that explains the decisions made for translation by predicting coreference features in the input. We construct a model for input coreference by exploiting contextual features from both the input and translation output representations on top of an existing MT model. We evaluate and analyze our method in the WMT document-level translation task of English-German dataset, the English-Russian dataset, and the multilingual TED talk dataset, demonstrating an improvement of over 1.0 BLEU score when compared with other context-aware models.
Yksityisiä palveluja tuetaan samaanaikaan, kun julkisia palveluja leikataan, todetaan Lääkäriliitosta. Kuitenkaan tästä ei ole haluttu käydä keskustelua.
Tämä on ideologinen muutos, jolla myös viestitään mihin halutaan suunnata palveluja.
Vieraana johtaja tutkija Liina-Kaisa Tynkkynen THL:stä.
#sote #terveydenhuolto
Deci-Hz gravitational waves from the self-interacting axion cloud around the rotating stellar mass black hole
Hidetoshi Omiya, Takuya Takahashi, Takahiro Tanaka, Hirotaka Yoshino
https://arxiv.org/abs/2404.16265
Deformations of Prismatic Higher $(G,\mu)$-Displays over Quasi-Syntomic Rings
S. Mohammad Hadi Hedayatzadeh, Ali Partofard
https://arxiv.org/abs/2402.12879
Von @flaviengousset@instagram.com
paar dm's zu de 13. AHV – überzüüg dini friends! 🤝
de letsti slide isch für de hype, letsgoooo ❤️🔥
#AHVx13ja #13AHVRenteJA #AHVRente
🔊 Auf radioeins läuft...
The Smashing Pumpkins:
🎵 1979
#NowPlaying #TheSmashingPumpkins
https://open.spotify.com/track/3h5zik31hTTat9jmpCZZNC
https://soundwavesofficial.bandcamp.com/album/the-smashing-pumpkins-1979-layer-by-layer
Estimating the Absolute Parameters of W UMa-type Binary Stars Using Gaia DR3 Parallax
Atila Poro, Mahya Hedayatjoo, Maryam Nastaran, Mahshid Nourmohammad, Hossein Azarara, Sepideh AlipourSoudmand, Fatemeh AzarinBarzandig, Razieh Aliakbari, Sadegh Nasirian, Nazanin Kahali Poor
https://arxiv.org/abs/2403.09801
Can we obtain significant success in RST discourse parsing by using Large Language Models?
Aru Maekawa, Tsutomu Hirao, Hidetaka Kamigaito, Manabu Okumura
https://arxiv.org/abs/2403.05065
Can we obtain significant success in RST discourse parsing by using Large Language Models?
Aru Maekawa, Tsutomu Hirao, Hidetaka Kamigaito, Manabu Okumura
https://arxiv.org/abs/2403.05065