Google AI Weblog: Google at EMNLP 2021

This week, the annual convention on Empirical Strategies in Pure Language Processing (EMNLP 2021) will probably be held each nearly and in Punta Cana, Dominican Republic. As a Diamond Stage sponsor of EMNLP 2021, Google will contribute analysis on a various set of matters, together with language interactions, causal inference, and query answering, moreover serving in varied ranges of group within the convention.

Under is a full record of Google’s involvement and publications being offered at EMNLP 2021. We congratulate these authors, and all different researchers who’re presenting their work on the convention (Google affiliations offered in daring).

Organizing Committee

Ethics Committee consists of: Nyalleng Moorosi

Publications

MATE: Multi-view Consideration for Desk Transformer Effectivity (see weblog put up)

Julian Martin Eisenschlos, Maharshi Gor^*, Thomas Müller^*, William W. Cohen

Residual Adapters for Parameter-Environment friendly ASR Adaptation to Atypical and Accented Speech (see weblog put up)

Katrin Tomanek, Vicky Zayats, Dirk Padfield, Kara Vaillancourt, Fadi Biadsy

In the direction of Computerized Analysis of Dialog Methods: A Mannequin-Free Off-Coverage Analysis Method (see weblog put up)

Haoming Jiang^*, Bo Dai, Mengjiao Yang,Tuo Zhao, Wei Wei

Case-Primarily based Reasoning for Pure Language Queries Over Information Bases

Rajarshi Das, Manzil Zaheer, Dung Thai, Ameya Godbole, Ethan Perez, Jay-Yoon Lee, Lizhen Tan, Lazaros Polymenakos, Andrew McCallum

XTREME-R: In the direction of Extra Difficult and Nuanced Multilingual Analysis (see weblog put up)

Sebastian Ruder, Noah Fixed, Jan Botha, Aditya Siddhant, Orhan Firat, Jinlan Fu, Pengfei Liu, Junjie Hu, Dan Garrette, Graham Neubig, Melvin Johnson

Constructing and Evaluating Open-Area Dialogue Corpora with Clarifying Questions

Mohammad Aliannejadi, Julia Kiseleva, Aleksandr Chuklin, Jeffrey Dalton, Mikhail Burtsev

Quick WordPiece Tokenization

Xinying Track, Alex Salcianu, Yang Track^*, Dave Dopson, Denny Zhou

Frequency Results on Syntactic Rule Studying in Transformers

Jason Wei, Dan Garrette, Tal Linzen, Ellie Pavlick

Controllable Semantic Parsing by way of Retrieval Augmentation

Panupong Pasupat, Yuan Zhang, Kelvin Guu

Systematic Generalization on gSCAN: What’s Almost Solved and What’s Subsequent?

Linlu Qiu^*, Hexiang Hu,Bowen Zhang, Peter Shaw, Fei Sha

Efficient Sequence-to-Sequence Dialogue State Monitoring

Jeffrey Zhao, Mahdis Mahdieh, Ye Zhang, Yuan Cao, Yonghui Wu

Studying Compact Metrics for MT

Amy Pu^*, Hyung Gained Chung^*, Ankur P. Parikh, Sebastian Gehrmann, Thibault Sellam

Joint Passage Rating for Various Multi-answer Retrieval

Sewon Min^*, Kenton Lee, Ming-Wei Chang, Kristina Toutanova, Hannaneh Hajishirzi

Towards Deconfounding the Impact of Entity Demographics for Query Answering Accuracy

Maharshi Gor^*, Kellie Webster, Jordan Boyd-Graber^*

Good-Sufficient Instance Extrapolation

Jason Wei

Q²: Evaluating Factual Consistency in Information-Grounded Dialogues by way of Query Era and Query Answering

Or Honovich^*, Leshem Choshen, Roee Aharoni, Ella Neeman, Idan Szpektor, Omri Abend

The Energy of Scale for Parameter-Environment friendly Immediate Tuning

Brian Lester^*, Rami Al-Rfou, Noah Fixed

A Easy and Efficient Technique to Remove the Self Language Bias in Multilingual Representations

Ziyi Yang^*, Yinfei Yang, Daniel Cer, Eric Darve

Common Sentence Illustration Studying with Conditional Masked Language Mannequin

Ziyi Yang^*, Yinfei Yang, Daniel Cer, Jax Regulation, Eric Darve

Scalable Font Reconstruction with Twin Latent Manifolds

Nikita Srivatsan, Si Wu, Jonathan T. Barron, Taylor Berg-Kirkpatrick

Structured Context and Excessive-Protection Grammar for Conversational Query Answering Over Information Graphs

Pierre Marion, Paweł Krzysztof Nowak, Francesco Piccinno

Don’t Seek for a Search Technique — Easy Heuristics Suffice for Adversarial Textual content Assaults

Nathaniel Berger^*, Stefan Riezler, Artem Sokolov, Sebastian Ebert

HintedBT: Augmenting Again-Translation with High quality and Transliteration Hints

Sahana Ramnath, Melvin Johnson, Abhirut Gupta, Aravindan Raghuveer

STraTA: Self-Coaching with Process Augmentation for Higher Few-Shot Studying

Tu Vu^*, Minh-Thang Luong, Quoc V. Le, Grady Simon,Mohit Iyyer

Do Transformer Modifications Switch Throughout Implementations and Purposes? (See weblog put up)

Sharan Narang, Hyung Gained Chung, Yi Tay, William Fedus, Thibault Fevry^*, Michael Matena^*, Karishma Malkan^*, Noah Fiedel, Noam Shazeer, Zhenzhong Lan^*, Yanqi Zhou, Wei Li, Nan Ding, Jake Marcus, Adam Roberts, Colin Raffel^*

A Massive-Scale Examine of Machine Translation in Turkic Languages

Jamshidbek Mirzakhalova, Anoop Babua, Duygu Atamana, Sherzod Karieva, Francis Tyersa, Otabek Abduraufova, Mammad Hajilia, Sardana Ivanovaa, Abror Khaytbaeva, Antonio Laverghetta Jr., Behzodbek Moydinboyeva, Esra Onala, Shaxnoza Pulatovaa, Ahsan Wahaba, Orhan Firat, Sriram Chellappan

ReasonBERT: Pre-trained to Purpose with Distant Supervision

Xiang Deng, Yu Su, Alyssa Lees, You Wu, Cong Yu, Huan Solar

MasakhaNER: Named Entity Recognition for African Languages

David Ifeoluwa Adelani, Jade Abbott, Graham Neubig, Daniel D’souza, Julia Kreutzer, Constantine Lignos, Chester Palen-Michel, Pleased Buzaaba, Shruti Rijhwani, Sebastian Ruder, Stephen Mayhew, Israel Abebe Azime, Shamsuddeen H. Muhammad, Chris Chinenye Emezue, Joyce Nakatumba-Nabende, Perez Ogayo, Anuoluwapo Aremu, Catherine Gitau, Derguene Mbaye, Jesujoba Alabi, Seid Muhie Yimam, Tajuddeen Rabiu Gwadabe, Ignatius Ezeani, Rubungo Andre Niyongabo, Jonathan Mukiibi, Verrah Otiende, Iroro Orife, Davis David, Samba Ngom, Tosin Adewumi, Paul Rayson, Mofetoluwa Adeyemi, Gerald Muriuki, Emmanuel Anebi, Chiamaka Chukwuneke, Nkiruka Odu, Eric Peter Wairagala, Samuel Oyerinde, Clemencia Siro, Tobius Saul Bateesa, Temilola Oloyede, Yvonne Wambui, Victor Akinode, Deborah Nabagereka, Maurice Katusiime, Ayodele Awokoya, Mouhamadane MBOUP, Dibora Gebreyohannes, Henok Tilaye, Kelechi Nwaike, Degaga Wolde, Abdoulaye Faye, Blessing Sibanda, Orevaoghene Ahia, Bonaventure F. P. Dossou, Kelechi Ogueji, Thierno Ibrahima DIOP, Abdoulaye Diallo, Adewale Akinfaderin, Tendai Marengereke, Salomey Osei

Multi-stage Coaching with Improved Damaging Distinction for Neural Passage Retrieval

Jing Lu^*, Gustavo Hernandez, Abrego, Ji Ma, Jianmo Ni, Yinfei Yang

Controlling Machine Translation for A number of Attributes with Additive Interventions

Andrea Schioppa, Artem Sokolov, David Vilar, Katja Filippova

A Easy and Efficient Positional Encoding for Transformers

Pu-Chin Chen, Henry Tsai, Srinadh Bhojanapalli, Hyung Gained Chung, Yin-Wen Chang, Chun-Sung Ferng

CrossVQA: Scalably Producing Benchmarks for Systematically Testing VQA Generalization

Arjun R. Akula^*, Soravit Changpinyo, Boqing Gong, Piyush Sharma, Track-Chun Zhu, Radu Soricut

Can We Enhance Mannequin Robustness by means of Secondary Attribute Counterfactuals?

Ananth Balashankar, Xuezhi Wang, Ben Packer, Nithum Thain, Ed Chi, Alex Beutel

Multi-Vector Consideration Fashions for Deep Re-ranking

Giulio Zhou^*, Jacob Devlin

Various Distributions of Self-Supervised Duties for Meta-Studying in NLP

Trapit Bansal, Karthick Gunasekaran, Tong Wang, Tsendsuren Munkhdalai, Andrew McCallum

Workshops

NLP for Conversational AI

Invited audio system embrace: Idan Szpektor

Organizers embrace: Abhinav Rastogi

Novel Concepts in Studying-to-Study By Interplay

Invited audio system embrace: Natasha Jaques

Analysis & Comparability of NLP Methods

Invited audio system embrace: Sebastian Ruder

Causal Inference & NLP

Organizers embrace: Amir Feder, Jacob Eisenstein, Victor Veitch

Machine Studying for Query Answering

Invited audio system embrace: Jon Clark

Computational Approaches to Discourse

Organizers embrace: Annie Louis

New Frontiers in Summarization

Invited audio system embrace: Sebastian Gehrmann, Shashi Narayan

Multi-lingual Illustration Studying

Invited audio system embrace: Melvin Johnson

Organizers embrace: Alexis Conneau, Orhan Firat, Sebastian Ruder

Widening in NLP

Invited audio system embrace: Jasmijn Bastings

Organizers embrace: Shaily Bhatt

Evaluations and Assessments of Neural Dialog Methods (EANCS)

Organizers embrace: Wei Wei, Bo Dai

BlackboxNLP

Invited audio system embrace: Sara Hooker

Organizers embrace: Jasmijn Bastings

Tutorials

Multi-Area Multilingual Query Answering

Organizers embrace: Sebastian Ruder

Demos

LMdiff: A Visible Diff Instrument to Evaluate Language Fashions

Hendrik Strobelt, Benjamin Hoover, Arvind Satyanarayan, Sebastian Gehrmann