Home
Catalogue search
Refine your search:
Keyword
Creator / Publisher:
The 2021 Conference on Empirical Methods in Natural Language Processing 2021 (1.029)
Cotterell, Ryan (8)
Neubig, Graham (8)
Ren, Xiang (8)
Søgaard, Anders (8)
Bansal, Mohit (7)
Berant, Jonathan (7)
Goldberg, Yoav (7)
Navigli, Roberto (7)
Peng, Nanyun (7)
more
Year
Medium:
Online (1.029)
Type:
Article (1.029)
BLLDB-Access
Search in the Catalogues and Directories
All fields
Title
Creator / Publisher
Keyword
Year
AND
OR
AND NOT
All fields
Title
Creator / Publisher
Keyword
Year
AND
OR
AND NOT
All fields
Title
Creator / Publisher
Keyword
Year
AND
OR
AND NOT
All fields
Title
Creator / Publisher
Keyword
Year
AND
OR
AND NOT
All fields
Title
Creator / Publisher
Keyword
Year
Sort by
creator [A → Z]
'
creator [Z → A]
'
publishing year ↑ (asc)
'
publishing year ↓ (desc)
'
title [A → Z]
'
title [Z → A]
'
Simple Search
Page:
1
...
3
4
5
6
7
8
9
10
11
...
52
Hits 121 – 140 of 1.029
121
End-to-end style-conditioned poetry generation: What does it take to learn from examples alone? ...
The 2021 Conference on Empirical Methods in Natural Language Processing 2021
;
Eger, Steffen
. - : Underline Science Inc., 2021
BASE
Show details
122
Memory and Knowledge Augmented Language Models for Inferring Salience in Long-Form Stories ...
The 2021 Conference on Empirical Methods in Natural Language Processing 2021
;
Keller, Frank
;
Wilmot, David
. - : Underline Science Inc., 2021
BASE
Show details
123
A Thorough Evaluation of Task-Specific Pretraining for Summarization ...
The 2021 Conference on Empirical Methods in Natural Language Processing 2021
;
Maynez, Joshua
;
Narayan, Shashi
. - : Underline Science Inc., 2021
BASE
Show details
124
Rethinking Data Augmentation for Low-Resource Neural Machine Translation: A Multi-Task Learning Approach ...
The 2021 Conference on Empirical Methods in Natural Language Processing 2021
;
Esplà-Gomis, Miquel
;
Pérez-Ortiz, Juan Antonio
. - : Underline Science Inc., 2021
BASE
Show details
125
PAQ: 65 Million Probably-Asked Questions and What You Can Do With Them ...
The 2021 Conference on Empirical Methods in Natural Language Processing 2021
;
Lewis, Patrick
. - : Underline Science Inc., 2021
BASE
Show details
126
Good-Enough Example Extrapolation ...
The 2021 Conference on Empirical Methods in Natural Language Processing 2021
;
Wei, Jason
. - : Underline Science Inc., 2021
BASE
Show details
127
To what extent do human explanations of model behavior align with actual model behavior? ...
The 2021 Conference on Empirical Methods in Natural Language Processing 2021
;
Prasad, Grusha
. - : Underline Science Inc., 2021
BASE
Show details
128
Sequence Length is a Domain: Length-based Overfitting in Transformer Models ...
The 2021 Conference on Empirical Methods in Natural Language Processing 2021
;
Bojar, Ondřej
;
Variš, Dušan
. - : Underline Science Inc., 2021
BASE
Show details
129
Enhancing Multiple-choice Machine Reading Comprehension by Punishing Illogical Interpretations ...
The 2021 Conference on Empirical Methods in Natural Language Processing 2021
;
Ju, Yiming
;
Zhang, Yuanzhe
. - : Underline Science Inc., 2021
BASE
Show details
130
Disentangling Generative Factors in Natural Language with Discrete Variational Autoencoders ...
The 2021 Conference on Empirical Methods in Natural Language Processing 2021
;
Mercatali, Giangiacomo
. - : Underline Science Inc., 2021
BASE
Show details
131
Effective Sequence-to-Sequence Dialogue State Tracking ...
The 2021 Conference on Empirical Methods in Natural Language Processing 2021
;
Cao, Yuan
;
Mahdieh, Mahdis
;
Wu, Yonghui
;
Zhang, Ye
;
Zhao, Jeffrey
. - : Underline Science Inc., 2021
Abstract:
Anthology paper link: https://aclanthology.org/2021.emnlp-main.593/ Abstract: Sequence-to-sequence models have been applied to a wide variety of NLP tasks, but how to properly use them for dialogue state tracking has not been systematically investigated. In this paper, we study this problem from the perspectives of pre-training objectives as well as the formats of context representations. We demonstrate that the choice of pre-training objective makes a significant difference to the state tracking quality. In particular, we find that masked span prediction is more effective than auto-regressive language modeling. We also explore using Pegasus, a span prediction-based pre-training objective for text summarization, for the state tracking model. We found that pre-training for the seemingly distant summarization task works surprisingly well for dialogue state tracking. In addition, we found that while recurrent state context representation works also reasonably well, the model may have a hard time recovering from ...
Keyword:
Computational Linguistics
;
Language Models
;
Machine Learning
;
Machine Learning and Data Mining
;
Natural Language Processing
;
Text Summarization
URL:
https://underline.io/lecture/38022-effective-sequence-to-sequence-dialogue-state-tracking
https://dx.doi.org/10.48448/nj9n-m011
BASE
Hide details
132
An Investigation into the Contribution of Locally Aggregated Descriptors to Figurative Language Identification ...
The 2021 Conference on Empirical Methods in Natural Language Processing 2021
;
., Indrakshi
;
Banerjee, Ritwik
. - : Underline Science Inc., 2021
BASE
Show details
133
Solving Aspect Category Sentiment Analysis as a Text Generation Task ...
The 2021 Conference on Empirical Methods in Natural Language Processing 2021
;
Liu, Jian
. - : Underline Science Inc., 2021
BASE
Show details
134
Discourse-Driven Integrated Dialogue Development Environment for Open-Domain Dialogue Systems ...
The 2021 Conference on Empirical Methods in Natural Language Processing 2021
;
., Dmitry
;
Burtsev, Mikhail
. - : Underline Science Inc., 2021
BASE
Show details
135
Context or No Context? A preliminary exploration of human-in-the-loop approach for Incremental Temporal Summarization in meetings ...
The 2021 Conference on Empirical Methods in Natural Language Processing 2021
;
., Saurav
;
Beckage, Nicole
. - : Underline Science Inc., 2021
BASE
Show details
136
Learning Data Augmentation Schedules for Natural Language Processing ...
The 2021 Conference on Empirical Methods in Natural Language Processing 2021
;
., Irena
;
Chopard, Daphné
. - : Underline Science Inc., 2021
BASE
Show details
137
Locke's Holiday: Belief Bias in Machine Reading ...
The 2021 Conference on Empirical Methods in Natural Language Processing 2021
;
Søgaard, Anders
. - : Underline Science Inc., 2021
BASE
Show details
138
Searching for More Efficient Dynamic Programs ...
The 2021 Conference on Empirical Methods in Natural Language Processing 2021
. - : Underline Science Inc., 2021
BASE
Show details
139
Logic-level Evidence Retrieval and Graph-based Verification Network for Table-based Fact Verification ...
The 2021 Conference on Empirical Methods in Natural Language Processing 2021
;
Shi, Qi
. - : Underline Science Inc., 2021
BASE
Show details
140
Improving Synonym Recommendation Using Sentence Context ...
The 2021 Conference on Empirical Methods in Natural Language Processing 2021
;
., William
;
Arendt, Dustin
. - : Underline Science Inc., 2021
BASE
Show details
Page:
1
...
3
4
5
6
7
8
9
10
11
...
52
Mobile view
All
Catalogues
UB Frankfurt Linguistik
0
IDS Mannheim
0
OLC Linguistik
0
UB Frankfurt Retrokatalog
0
DNB Subject Category Language
0
Institut für Empirische Sprachwissenschaft
0
Leibniz-Centre General Linguistics (ZAS)
0
Bibliographies
BLLDB
0
BDSL
0
IDS Bibliografie zur deutschen Grammatik
0
IDS Bibliografie zur Gesprächsforschung
0
IDS Konnektoren im Deutschen
0
IDS Präpositionen im Deutschen
0
IDS OBELEX meta
0
MPI-SHH Linguistics Collection
0
MPI for Psycholinguistics
0
Linked Open Data catalogues
Annohub
0
Online resources
Link directory
0
Journal directory
0
Database directory
0
Dictionary directory
0
Open access documents
BASE
1.029
Linguistik-Repository
0
IDS Publikationsserver
0
Online dissertations
0
Language Description Heritage
0
© 2013 - 2024 Lin|gu|is|tik
|
Imprint
|
Privacy Policy
|
Datenschutzeinstellungen ändern