Zobrazeno 1 - 10
of 16
pro vyhledávání: '"Matthew R. Gormley"'
Autor:
Longxiang Zhang, Renato Negrinho, Arindam Ghosh, Vasudevan Jagannathan, Hamid Reza Hassanzadeh, Thomas Schaaf, Matthew R. Gormley
Fine-tuning pretrained models for automatically summarizing doctor-patient conversation transcripts presents many challenges: limited training data, significant domain shift, long and noisy transcripts, and high target summary variability. In this pa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::36571c6149eaddde5166dad9c20725e0
http://arxiv.org/abs/2109.12174
http://arxiv.org/abs/2109.12174
Traditionally, character-level transduction problems have been solved with finite-state models designed to encode structural and linguistic knowledge of the underlying process, whereas recent approaches rely on the power and flexibility of sequence-t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::91a4b1d7dc385a7c003eca463f489093
http://arxiv.org/abs/2106.12698
http://arxiv.org/abs/2106.12698
Publikováno v:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing.
Publikováno v:
NAACL-HLT
Standard autoregressive language models perform only polynomial-time computation to compute the probability of the next symbol. While this is attractive, it means they cannot model distributions whose next-symbol probability is hard to compute. Indee
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b1e3269f0d7d421a8bd0a1e553681fb0
http://arxiv.org/abs/2010.11939
http://arxiv.org/abs/2010.11939
Publikováno v:
EMNLP (Findings)
Structured prediction is often approached by training a locally normalized model with maximum likelihood and decoding approximately with beam search. This approach leads to mismatches as, during training, the model is not exposed to its mistakes and
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6ff4543016c2f2dca364842262bd1495
http://arxiv.org/abs/2010.04980
http://arxiv.org/abs/2010.04980
Publikováno v:
ACL
Informal romanization is an idiosyncratic process used by humans in informal digital communication to encode non-Latin script languages into Latin character sets found on common keyboards. Character substitution choices differ between users but have
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::12e79f0084203193900e64a095216e3d
http://arxiv.org/abs/2005.02517
http://arxiv.org/abs/2005.02517
Autor:
Matthew R. Gormley, Sida Gao
Publikováno v:
EMNLP (1)
Most recent improvements in NLP come from changes to the neural network architectures modeling the text input. Yet, state-of-the-art models often rely on simple approaches to model the label space, e.g. bigram Conditional Random Fields (CRFs) in sequ
Publikováno v:
NAACL-HLT (1)
We introduce neural finite state transducers (NFSTs), a family of string transduction models defining joint and conditional probability distributions over pairs of strings. The probability of a string pair is obtained by marginalizing over all its ac
Publikováno v:
ACL (1)
Recent work on bilingual lexicon induction (BLI) has frequently depended either on aligned bilingual lexicons or on distribution matching, often with an assumption about the isometry of the two spaces. We propose a technique to quantitatively estimat
Publikováno v:
Transactions of the Association for Computational Linguistics. 3:489-501
We show how to train the fast dependency parser of Smith and Eisner (2008) for improved accuracy. This parser can consider higher-order interactions among edges while retaining O( n3) runtime. It outputs the parse with maximum expected recall—but f