Zobrazeno 1 - 10
of 60
pro vyhledávání: '"Anoop Sarkar"'
We propose a novel data-augmentation technique for neural machine translation based on ROT-$k$ ciphertexts. ROT-$k$ is a simple letter substitution cipher that replaces a letter in the plaintext with the $k$th letter after it in the alphabet. We firs
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::284b8a70676ea0a94d7e22127e57973c
Autor:
Anoop Sarkar, Hassan S. Shavarani
Publikováno v:
EACL
Adding linguistic information (syntax or semantics) to neural machine translation (NMT) have mostly focused on using point estimates from pre-trained models. Directly using the capacity of massive pre-trained contextual word embedding models such as
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::333162b0f7de016023568b1cbe58a4c5
Publikováno v:
EACL
While the attention heatmaps produced by neural machine translation (NMT) models seem insightful, there is little evidence that they reflect a model’s true internal reasoning. We provide a measure of faithfulness for NMT based on a variety of stres
Publikováno v:
ACL/IJCNLP (Findings)
Publikováno v:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing.
Autor:
Ashkan Alinejad, Anoop Sarkar
Publikováno v:
EMNLP (1)
Directly translating from speech to text using an end-to-end approach is still challenging for many language pairs due to insufficient data. Although pretraining the encoder parameters using the Automatic Speech Recognition (ASR) task improves the re
Publikováno v:
Transactions of the Association for Computational Linguistics. 5:501-514
Current word alignment models do not distinguish between different types of alignment links. In this paper, we provide a new probabilistic model for word alignment where word alignments are associated with linguistically motivated alignment types. We
Publikováno v:
NGT@EMNLP-IJCNLP
Attention models have become a crucial component in neural machine translation (NMT). They are often implicitly or explicitly used to justify the model's decision in generating a specific token but it has not yet been rigorously established to what e
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::41b456552a50e0ea3d1435b5ff14b32f
http://arxiv.org/abs/1910.00139
http://arxiv.org/abs/1910.00139
Publikováno v:
LaTeCH@NAACL-HLT
We describe a first attempt at using techniques from computational linguistics to analyze the undeciphered proto-Elamite script. Using hierarchical clustering, n-gram frequencies, and LDA topic models, we both replicate results obtained by manual dec
Autor:
Zhenqi Zhu, Anoop Sarkar
Publikováno v:
CoNLL
Supertagging is a sequence prediction task where each word is assigned a piece of complex syntactic structure called a supertag. We provide a novel approach to multi-task learning for Tree Adjoining Grammar (TAG) supertagging by deconstructing these