1 |
Transformer Grammars: Augmenting Transformer Language Models with Syntactic Inductive Biases at Scale ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Diverse Pretrained Context Encodings Improve Document Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Better {C}hinese Sentence Segmentation with Reinforcement Learning ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Better Document-Level Machine Translation with Bayes’ Rule
|
|
|
|
In: Transactions of the Association for Computational Linguistics, Vol 8, Pp 346-360 (2020) (2020)
|
|
Abstract:
We show that Bayes’ rule provides an effective mechanism for creating document translation models that can be learned from only parallel sentences and monolingual documents a compelling benefit because parallel documents are not always available. In our formulation, the posterior probability of a candidate translation is the product of the unconditional (prior) probability of the candidate output document and the “reverse translation probability” of translating the candidate output back into the source language. Our proposed model uses a powerful autoregressive language model as the prior on target language documents, but it assumes that each sentence is translated independently from the target to the source language. Crucially, at test time, when a source document is observed, the document language model prior induces dependencies between the translations of the source sentences in the posterior. The model’s independence assumption not only enables efficient use of available data, but it additionally admits a practical left-to-right beam-search algorithm for carrying out inference. Experiments show that our model benefits from using cross-sentence context in the language model, and it outperforms existing document translation approaches.
|
|
Keyword:
Computational linguistics. Natural language processing; P98-98.5
|
|
URL: https://doi.org/10.1162/tacl_a_00319 https://doaj.org/article/bc1081a128a245a79fae343c5a133969
|
|
BASE
|
|
Hide details
|
|
8 |
Unsupervised Bilingual POS Tagging with Markov Random Fields ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Unsupervised Bilingual POS Tagging with Markov Random Fields ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Knowledge-Rich Morphological Priors for Bayesian Language Models ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Learning to Discover, Ground and Use Words with Segmental Neural Language Models ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
From Characters to Understanding Natural Language (C2NLU): Robust End-to-End Deep Learning for NLP (Dagstuhl Seminar 17042)
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Learning to Create and Reuse Words in Open-Vocabulary Neural Language Modeling ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
From Characters to Understanding Natural Language (C2NLU): Robust End-to-End Deep Learning for NLP (Dagstuhl Seminar 17042) ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Ontology-Aware Token Embeddings for Prepositional Phrase Attachment ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Learning the Curriculum with Bayesian Optimization for Task-Specific Word Representation Learning ...
|
|
|
|
BASE
|
|
Show details
|
|
20 |
Learning the Curriculum with Bayesian Optimization for Task-Specific Word Representation Learning ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|