Home
Papertalks
About
Help
Improve
Upload
Login
Register
Login Required
×
You have to login to use this feature.
EMNLP
Member since:
2020-12-20
Last seen:
2020-12-20
User details
Name:
Conference on Empirical Methods in Natural Language Processing
Affiliation:
Association for Computational Linguistics
Website:
https://2020.emnlp.org/
About me:
The 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP 2020) invites the submission of long and short papers on substantial, original, and unpublished research in empirical methods for Natural Language Processing.
Papertalks of EMNLP
16/11/2020
Task-Oriented Dialogue as Dataflow Synthesis
Jacob Andreas
,
John Bufe
,
David Burkett
and
Charles Chen
,
Josh Clausman
,
Jean Crawford
,
Kate Crim
,
Jordan DeLoach
,
Leah Dorner
,
Jason Eisner
,
Hao Fang
,
Alan Guo
,
David Hall
,
Kristin Hayes
,
Kellie Hill
,
Diana Ho
,
Wendy Iwaszuk
,
Smriti Jha
,
Dan Klein
,
Jayant Krishnamurthy
,
Theo Lanman
,
Percy Liang
,
Christopher Lin
,
Ilya Lintsbakh
,
Andy McGovern
,
Alexander Nisnevich
,
Adam Pauls
,
Brent Read
,
Dan Roth
,
Subhro Roy
,
Beth Short
,
Div Slomin
,
Ben Snyder
,
Stephon Striplin
,
Yu Su
,
Zachary Tellman
,
Sam Thomson
,
Andrei Vorobev
,
Izabela Witoszko
,
Jason Wolfe
,
Abby Wray
,
Yuchen Zhang
,
Alexander Zotov
,
Jesse Rusak
,
Dmitrij Petters
Keywords
Abstract
Paper
task-oriented dialogue
,
revision
,
dialogue agent
,
metacomputation operators
12:02
16/11/2020
Learning Which Features Matter: RoBERTa Acquires a Preference for Linguistic Generalizations (Eventually)
Alex Warstadt
,
Yian Zhang
,
Xiaocheng Li
and
Haokun Liu
,
Samuel R. Bowman
Keywords
Abstract
Paper
self-supervised tasks
,
language understanding
,
ambiguous tasks
,
finetuning
12:04
16/11/2020
BLEU might be Guilty but References are not Innocent
Markus Freitag
,
David Grangier
,
Isaac Caswell
Keywords
Abstract
Paper
machine translation
,
automated evaluation
,
paraphrasing task
,
human evaluation
12:03
16/11/2020
KERMIT: Complementing Transformer Architectures with Encoders of Explicit Syntactic Interpretations
Fabio Massimo Zanzotto
,
Andrea Santilli
,
Leonardo Ranaldi
and
Dario Onorati
,
Pierfrancesco Tommasino
,
Francesca Fallucchi
Keywords
Abstract
Paper
natural understanding
,
inference
,
syntactic parsers
,
large-scale learners
11:26
16/11/2020
If beam search is the answer, what was the question?
Clara Meister
,
Ryan Cotterell
,
Tim Vieira
Keywords
Abstract
Paper
language tasks
,
beam search
,
decoding
,
maximum decoding
12:18
16/11/2020
Calibration of Pre-trained Transformers
Shrey Desai
,
Greg Durrett
Keywords
Abstract
Paper
natural processing
,
natural inference
,
paraphrase detection
,
commonsense reasoning
6:55
16/11/2020
Pre-Training Transformers as Energy-Based Cloze Models
Kevin Clark
,
Minh-Thang Luong
,
Quoc Le
,
Christopher D. Manning
Keywords
Abstract
Paper
representation text
,
downstream tasks
,
pre-training
,
electric
7:12
16/11/2020
ETC: Encoding Long and Structured Inputs in Transformers
Joshua Ainslie
,
Santiago Ontanon
,
Chris Alberti
and
Vaclav Cvicek
,
Zachary Fisher
,
Philip Pham
,
Anirudh Ravula
,
Sumit Sanghai
,
Qifan Wang
,
Li Yang
Keywords
Abstract
Paper
natural tasks
,
encoding inputs
,
transformer models
,
transformer architecture
11:04
16/11/2020
Digital Voicing of Silent Speech
David Gaddy
,
Dan Klein
Keywords
Abstract
Paper
digitally speech
,
speech models
,
emg
,
silently words
10:56
16/11/2020
A matter of framing: The impact of linguistic formalism on probing results
Ilia Kuznetsov
,
Iryna Gurevych
Keywords
Abstract
Paper
downstream tasks
,
pre-training
,
probing
,
linguistic tasks
11:06
16/11/2020
What Have We Achieved on Text Summarization?
Dandan Huang
,
Leyang Cui
,
Sen Yang
and
Guangsheng Bao
,
Kun Wang
,
Jun Xie
,
Yue Zhang
Keywords
Abstract
Paper
text summarization
,
deep learning
,
automatic summarizers
,
summarization systems
11:20
16/11/2020
Self-Supervised Meta-Learning for Few-Shot Natural Language Classification Tasks
Trapit Bansal
,
Rishikesh Jha
,
Tsendsuren Munkhdalai
,
Andrew McCallum
Keywords
Abstract
Paper
nlp applications
,
fine-tuning
,
meta-learning problem
,
supervised tasks
11:49
16/11/2020
Information-Theoretic Probing with Minimum Description Length
Elena Voita
,
Ivan Titov
Keywords
Abstract
Paper
random tasks
,
estimating mdl
,
representations
,
pretrained representations
11:29
16/11/2020
Unsupervised Discovery of Implicit Gender Bias
Anjalie Field
,
Yulia Tsvetkov
Keywords
Abstract
Paper
appearance sexualization
,
unsupervised approach
,
adversarial learning
,
female politicians
8:44
16/11/2020
PRover: Proof Generation for Interpretable Reasoning over Rules
Swarnadeep Saha
,
Sayan Ghosh
,
Shashank Srivastava
,
Mohit Bansal
Keywords
Abstract
Paper
inference
,
qa generation
,
generalization
,
qa task
11:30
16/11/2020
BAE: BERT-based Adversarial Examples for Text Classification
Siddhant Garg
,
Goutham Ramakrishnan
Keywords
Abstract
Paper
nlp
,
generating examples
,
automatic evaluations
,
modern models
6:45
16/11/2020
Intrinsic Probing through Dimension Selection
Lucas Torroba Hennigen
,
Adina Williams
,
Ryan Cotterell
Keywords
Abstract
Paper
intrinsic probing
,
nlp systems
,
pre-trained representations
,
extrinsic probing
12:27
16/11/2020
Statistical Power and Translationese in Machine Translation Evaluation
Yvette Graham
,
Barry Haddow
,
Philipp Koehn
Keywords
Abstract
Paper
machine evaluation
,
human-parity mt
,
human translation
,
significance tests
11:48
16/11/2020
Experience Grounds Language
Yonatan Bisk
,
Ari Holtzman
,
Jesse Thomason
and
Jacob Andreas
,
Yoshua Bengio
,
Joyce Chai
,
Mirella Lapata
,
Angeliki Lazaridou
,
Jonathan May
,
Aleksandr Nisnevich
,
Nicolas Pinto
,
Joseph Turian
Keywords
Abstract
Paper
language research
,
tasks
,
linguistic communication
,
natural processing
11:55
16/11/2020
Automatic Machine Translation Evaluation in Many Languages via Zero-Shot Paraphrasing
Brian Thompson
,
Matt Post
Keywords
Abstract
Paper
machine evaluation
,
zero-shot task
,
wmt task
,
quality estimation
11:02
16/11/2020
FIND: Human-in-the-Loop Debugging Deep Text Classifiers
Piyawat Lertvittayakumjorn
,
Lucia Specia
,
Francesca Toni
Keywords
Abstract
Paper
real-world classifiers
,
classifiers
,
find
,
deep classifiers
11:45
16/11/2020
Which *BERT? A Survey Organizing Contextualized Encoders
Patrick Xia
,
Shijie Wu
,
Benjamin Van Durme
Keywords
Abstract
Paper
language learning
,
pretrained encoders
,
model
11:18
16/11/2020
Social Chemistry 101: Learning to Reason about Social and Moral Norms
Maxwell Forbes
,
Jena D. Hwang
,
Vered Shwartz
and
Maarten Sap
,
Yejin Choi
Keywords
Abstract
Paper
computational norms
,
conceptual formalism
,
neural models
,
neural transformer
12:00
16/11/2020
Simulated multiple reference training improves low-resource machine translation
Huda Khayrallah
,
Brian Thompson
,
Matt Post
,
Philipp Koehn
Keywords
Abstract
Paper
machine mt
,
mt
,
simulated training
,
simulated
6:56
16/11/2020
With Little Power Comes Great Responsibility
Dallas Card
,
Peter Henderson
,
Urvashi Khandelwal
and
Robin Jia
,
Kyle Mahowald
,
Dan Jurafsky
Keywords
Abstract
Paper
human studies
,
machine translation
,
power analysis
,
power analyses
11:51
16/11/2020
Language Model Prior for Low-Resource Neural Machine Translation
Christos Baziotis
,
Barry Haddow
,
Alexandra Birch
Keywords
Abstract
Paper
neural translation
,
neural tm
,
knowledge distillation
,
training time
11:16
16/11/2020
Unsupervised Quality Estimation for Neural Machine Translation
Marina Fomicheva
,
Shuo Sun
,
Lisa Yankovskaya
and
Frédéric Blain
,
Francisco Guzmán
,
Mark Fishel
,
Nikolaos Aletras
,
Vishrav Chaudhary
,
Lucia Specia
Keywords
Abstract
Paper
machine mt
,
real-world applications
,
qe
,
uncertainty quantification
12:19
16/11/2020
What Does My QA Model Know? Devising Controlled Probes using Expert
Kyle Richardson
,
Ashish Sabharwal
Keywords
Abstract
Paper
knowledge challenges
,
benchmark tasks
,
diagnostic tasks
,
taxonomic reasoning
12:16
16/11/2020
Learning from Task Descriptions
Orion Weller
,
Nicholas Lourie
,
Matt Gardner
,
Matthew Peters
Keywords
Abstract
Paper
task-oriented evaluation
,
systematic generalization
,
machine systems
,
nlp systems
11:48
16/11/2020
Self-Supervised Knowledge Triplet Learning for Zero-Shot Question Answering
Pratyay Banerjee
,
Chitta Baral
Keywords
Abstract
Paper
data annotation
,
knowledge learning
,
knowledge
,
self-supervised task
11:16
16/11/2020
Masking as an Efficient Alternative to Finetuning for Pretrained Language Models
Mengjie Zhao
,
Tao Lin
,
Fei Mi
and
Martin Jaggi
,
Hinrich Schütze
Keywords
Abstract
Paper
masking bert
,
nlp tasks
,
downstream tasks
,
masking
12:40
16/11/2020
Best-First Beam Search
Clara Meister
,
Ryan Cotterell
,
Tim Vieira
Keywords
Abstract
Paper
nlp tasks
,
exact search
,
decoding
,
heuristic algorithm
12:19
16/11/2020
What do Models Learn from Question Answering Datasets?
Priyanka Sen
,
Amir Saffari
Keywords
Abstract
Paper
question answering
,
reading comprehension
,
bert-based models
,
question variations
11:41
16/11/2020
Learning to Explain: Datasets and Models for Identifying Valid Reasoning Chains in Multihop Question-Answering
Harsh Jhamtani
,
Peter Clark
Keywords
Abstract
Paper
multihop qa
,
multihop
,
eqasc
,
qasc
10:42
16/11/2020
Sequence-Level Mixed Sample Data Augmentation
Demi Guo
,
Yoon Kim
,
Alexander Rush
Keywords
Abstract
Paper
sequence-to-sequence problems
,
scan
,
semantic parsing
,
neural networks
5:58
16/11/2020
Event Extraction by Answering (Almost) Natural Questions
Xinya Du
,
Claire Cardie
Keywords
Abstract
Paper
event extraction
,
entity recognition
,
error propagation
,
question task
13:37
16/11/2020
Multi-Dimensional Gender Bias Classification
Emily Dinan
,
Angela Fan
,
Ledell Wu
and
Jason Weston
,
Douwe Kiela
,
Adina Williams
Keywords
Abstract
Paper
detecting bias
,
machine models
,
nlp models
,
fine-grained framework
12:02
16/11/2020
On Losses for Modern Language Models
Stéphane Aroca-Ouellette
,
Frank Rudzicz
Keywords
Abstract
Paper
pre-training
,
masked modelling
,
next prediction
,
nsp
11:44
16/11/2020
F1 is Not Enough! Models and Evaluation Towards User-Centered Explainable Question Answering
Hendrik Schuff
,
Heike Adel
,
Ngoc Thang Vu
Keywords
Abstract
Paper
reasoning process
,
user study
,
model selection
,
explainable systems
12:03
16/11/2020
Identifying Elements Essential for BERT's Multilinguality
Philipp Dufter
,
Hinrich Schütze
Keywords
Abstract
Paper
zero-shot transfer
,
training
,
unsupervised alignment
,
xnli
10:45
«
1
2
3
4
5
…
19
20
»