Google at EMNLP 2022 – Google AI Weblog

This week, the premier convention on Empirical Strategies in Pure Language Processing (EMNLP 2022) is being held in Abu Dhabi, United Arab Emirates. We’re proud to be a Diamond Sponsor of EMNLP 2022, with Google researchers contributing in any respect ranges. This 12 months we’re presenting over 50 papers and are actively concerned in 10 totally different workshops and tutorials.

Reworking Sequence Tagging Into A Seq2Seq Process

Karthik Raman, Iftekhar Naim, Jiecao Chen, Kazuma Hashimoto, Kiran Yalasangi, Krishna Srinivasan

On the Limitations of Reference-Free Evaluations of Generated Textual content

Daniel Deutsch, Rotem Dror, Dan Roth

Chunk-Based mostly Nearest Neighbor Machine Translation

Pedro Henrique Martins, Zita Marinho, André F. T. Martins

Evaluating the Affect of Mannequin Scale for Compositional Generalization in Semantic Parsing

Linlu Qiu*, Peter Shaw, Panupong Pasupat, Tianze Shi, Jonathan Herzig, Emily Pitler, Fei Sha, Kristina Toutanova

MasakhaNER 2.0: Africa-centric Switch Studying for Named Entity Recognition

David Ifeoluwa Adelani, Graham Neubig, Sebastian Ruder, Shruti Rijhwani, Michael Beukman, Chester Palen-Michel, Constantine Lignos, Jesujoba O. Alabi, Shamsuddeen H. Muhammad, Peter Nabende, Cheikh M. Bamba Dione, Andiswa Bukula, Rooweither Mabuya, Bonaventure F. P. Dossou, Blessing Sibanda, Glad Buzaaba, Jonathan Mukiibi, Godson Kalipe, Derguene Mbaye, Amelia Taylor, Fatoumata Kabore, Chris Chinenye Emezue, Anuoluwapo Aremu, Perez Ogayo, Catherine Gitau, Edwin Munkoh-Buabeng, Victoire M. Koagne, Allahsera Auguste Tapo, Tebogo Macucwa, Vukosi Marivate, Elvis Mboning, Tajuddeen Gwadabe, Tosin Adewumi, Orevaoghene Ahia, Joyce Nakatumba-Nabende, Neo L. Mokono, Ignatius Ezeani, Chiamaka Chukwuneke, Mofetoluwa Adeyemi, Gilles Q. Hacheme, Idris Abdulmumin, Odunayo Ogundepo, Oreen Yousuf, Tatiana Moteu Ngoli, Dietrich Klakow

T-STAR: Truthful Fashion Switch Utilizing AMR Graph as Intermediate Illustration

Anubhav Jangra, Preksha Nema, Aravindan Raghuveer

Exploring Doc-Degree Literary Machine Translation with Parallel Paragraphs from World Literature

Katherine Thai, Marzena Karpinska, Kalpesh Krishna, Invoice Ray, Moira Inghilleri, John Wieting, Mohit Iyyer

ASQA: Factoid Questions Meet Lengthy-Type Solutions

Ivan Stelmakh*, Yi Luan, Bhuwan Dhingra, Ming-Wei Chang

Environment friendly Nearest Neighbor Seek for Cross-Encoder Fashions utilizing Matrix Factorization

Nishant Yadav, Nicholas Monath, Rico Angell, Manzil Zaheer, Andrew McCallum

CPL: Counterfactual Immediate Studying for Imaginative and prescient and Language Fashions

Xuehai He, Diji Yang, Weixi Feng, Tsu-Jui Fu, Arjun Akula, Varun Jampani, Pradyumna Narayana, Sugato Basu, William Yang Wang, Xin Eric Wang

Correcting Numerous Factual Errors in Abstractive Summarization by way of Publish-Modifying and Language Mannequin Infilling

Vidhisha Balachandran, Hannaneh Hajishirzi, William Cohen, Yulia Tsvetkov

Dungeons and Dragons as a Dialog Problem for Synthetic Intelligence

Chris Callison-Burch, Gaurav Singh Tomar, Lara J Martin, Daphne Ippolito, Suma Bailis, David Reitter

Exploring Twin Encoder Architectures for Query Answering

Zhe Dong, Jianmo Ni, Daniel M. Bikel, Enrique Alfonseca, Yuan Wang, Chen Qu, Imed Zitouni

RED-ACE: Strong Error Detection for ASR Utilizing Confidence Embeddings

Zorik Gekhman, Dina Zverinski, Jonathan Mallinson, Genady Beryozkin

Enhancing Passage Retrieval with Zero-Shot Query Era

Devendra Sachan, Mike Lewis, Mandar Joshi, Armen Aghajanyan, Wen-tau Yih, Joelle Pineau, Luke Zettlemoyer

MuRAG: Multimodal Retrieval-Augmented Generator for Open Query Answering Over Photographs and Textual content

Wenhu Chen, Hexiang Hu, Xi Chen, Pat Verga, William Cohen

Decoding a Neural Retriever’s Latent House for Question Suggestion

Leonard Adolphs, Michelle Chen Huebscher, Christian Buck, Sertan Girgin, Olivier Bachem, Massimiliano Ciaramita, Thomas Hofmann

Hyper-X: A Unified Hypernetwork for Multi-Process Multilingual Switch

Ahmet Üstün, Arianna Bisazza, Gosse Bouma, Gertjan van Noord, Sebastian Ruder

Supply a Completely different Perspective: Modeling the Perception Alignment of Arguments in Multi-party Debates

Suzanna Sia, Kokil Jaidka, Hansin Ahuja, Niyati Chhaya, Kevin Duh

Meta-Studying Quick Weight Language Mannequin

Kevin Clark, Kelvin Guu, Ming-Wei Chang, Panupong Pasupat, Geoffrey Hinton, Mohammad Norouzi

Giant Twin Encoders Are Generalizable Retrievers

Jianmo Ni, Chen Qu, Jing Lu, Zhuyun Dai, Gustavo Hernández Ábrego, Vincent Y. Zhao, Yi Luan, Keith B. Corridor, Ming-Wei Chang, Yinfei Yang

CONQRR: Conversational Question Rewriting for Retrieval with Reinforcement Studying

Zeqiu Wu*, Yi Luan, Hannah Rashkin, David Reitter, Hannaneh Hajishirzi, Mari Ostendorf, Gaurav Singh Tomar

Overcoming Catastrophic Forgetting in Zero-Shot Cross-Lingual Era

Tu Vu*, Aditya Barua, Brian Lester, Daniel Cer, Mohit Iyyer, Noah Fixed

RankGen: Enhancing Textual content Era with Giant Rating Fashions

Kalpesh Krishna, Yapei Chang, John Wieting, Mohit Iyyer

UnifiedSKG: Unifying and Multi-tasking Structured Data Grounding with Textual content-to-Textual content Language Fashions

Tianbao Xie, Chen Henry Wu, Peng Shi, Ruiqi Zhong, Torsten Scholak, Michihiro Yasunaga, Chien-Sheng Wu, Ming Zhong, Pengcheng Yin, Sida I. Wang, Victor Zhong, Bailin Wang, Chengzu Li, Connor Boyle, Ansong Ni, Ziyu Yao, Dragomir Radev, Caiming Xiong, Lingpeng Kong, Rui Zhang, Noah A. Smith, Luke Zettlemoyer and Tao Yu

M2D2: A Massively Multi-domain Language Modeling Dataset

Machel Reid, Victor Zhong, Suchin Gururangan, Luke Zettlemoyer

Tomayto, Tomahto. Past Token-Degree Reply Equivalence for Query Answering Analysis

Jannis Bulian, Christian Buck, Wojciech Gajewski, Benjamin Boerschinger, Tal Schuster

COCOA: An Encoder-Decoder Mannequin for Controllable Code-Switched Era

Sneha Mondal, Ritika Goyal, Shreya Pathak, Preethi Jyothi, Aravindan Raghuveer

Crossmodal-3600: A Massively Multilingual Multimodal Analysis Dataset (see weblog publish)

Ashish V. Thapliyal, Jordi Pont-Tuset, Xi Chen, Radu Soricut

“Will You Discover These Shortcuts?” A Protocol for Evaluating the Faithfulness of Enter Salience Strategies for Textual content Classification (see weblog publish)

Jasmijn Bastings, Sebastian Ebert, Polina Zablotskaia, Anders Sandholm, Katja Filippova

Intriguing Properties of Compression on Multilingual Fashions

Kelechi Ogueji*, Orevaoghene Ahia, Gbemileke A. Onilude, Sebastian Gehrmann, Sara Hooker, Julia Kreutzer

FETA: A Benchmark for Few-Pattern Process Switch in Open-Area Dialogue

Alon Albalak, Yi-Lin Tuan, Pegah Jandaghi, Connor Pryor, Luke Yoffe, Deepak Ramachandran, Lise Getoor, Jay Pujara, William Yang Wang

SHARE: a System for Hierarchical Assistive Recipe Modifying

Shuyang Li, Yufei Li, Jianmo Ni, Julian McAuley

Context Issues for Picture Descriptions for Accessibility: Challenges for Referenceless Analysis Metrics

Elisa Kreiss, Cynthia Bennett, Shayan Hooshmand, Eric Zelikman, Meredith Ringel Morris, Christopher Potts

Simply Effective-Tune Twice: Selective Differential Privateness for Giant Language Fashions

Weiyan Shi, Ryan Patrick Shea, Si Chen, Chiyuan Zhang, Ruoxi Jia, Zhou Yu

Findings of EMNLP

Leveraging Knowledge Recasting to Improve Tabular Reasoning

Aashna Jena, Manish Shrivastava, Vivek Gupta, Julian Martin Eisenschlos

QUILL: Question Intent with Giant Language Fashions Utilizing Retrieval Augmentation and Multi-stage Distillation

Krishna Srinivasan, Karthik Raman, Anupam Samanta, Lingrui Liao, Luca Bertelli, Michael Bendersky

Adapting Multilingual Fashions for Code-Combined Translation

Aditya Vavre, Abhirut Gupta, Sunita Sarawagi

Desk-To-Textual content Era and Pre-training with TABT5

Ewa Andrejczuk, Julian Martin Eisenschlos, Francesco Piccinno, Syrine Krichene, Yasemin Altun

Stretching Sentence-Pair NLI Fashions to Cause Over Lengthy Paperwork and Clusters

Tal Schuster, Sihao Chen, Senaka Buthpitiya, Alex Fabrikant, Donald Metzler

Data-Grounded Dialog State Monitoring

Dian Yu*, Mingqiu Wang, Yuan Cao, Izhak Shafran, Laurent El Shafey, Hagen Soltau

Sparse Mixers: Combining MoE and Mixing to Construct a Extra Environment friendly BERT

James Lee-Thorp, Joshua Ainslie

EdiT5: Semi-Autoregressive Textual content Modifying with T5 Heat-Begin

Jonathan Mallinson, Jakub Adamek, Eric Malmi, Aliaksei Severyn

Autoregressive Structured Prediction with Language Fashions

Tianyu Liu, Yuchen Eleanor Jiang, Nicholas Monath, Ryan Cotterell and Mrinmaya Sachan

Devoted to the Doc or to the World? Mitigating Hallucinations by way of Entity-Linked Data in Abstractive Summarization

Yue Dong*, John Wieting, Pat Verga

Investigating Ensemble Strategies for Mannequin Robustness Enchancment of Textual content Classifiers

Jieyu Zhao*, Xuezhi Wang, Yao Qin, Jilin Chen, Kai-Wei Chang

Matter Taxonomy Enlargement by way of Hierarchy-Conscious Matter Phrase Era

Dongha Lee, Jiaming Shen, Seonghyeon Lee, Susik Yoon, Hwanjo Yu, Jiawei Han

Benchmarking Language Fashions for Code Syntax Understanding

Da Shen, Xinyun Chen, Chenguang Wang, Koushik Sen, Daybreak Music

Giant-Scale Differentially Personal BERT

Rohan Anil, Badih Ghazi, Vineet Gupta, Ravi Kumar, Pasin Manurangsi

In the direction of Tracing Data in Language Fashions Again to the Coaching Knowledge

Ekin Akyurek, Tolga Bolukbasi, Frederick Liu, Binbin Xiong, Ian Tenney, Jacob Andreas, Kelvin Guu

Predicting Lengthy-Time period Citations from Quick-Time period Linguistic Affect

Sandeep Soni, David Bamman, Jacob Eisenstein

Workshops

Widening NLP

Organizers embody: Shaily Bhatt, Sunipa Dev, Isidora Tourni

The First Workshop on Ever Evolving NLP (EvoNLP)

Organizers embody: Bhuwan Dhingra

Invited Audio system embody: Eunsol Choi, Jacob Einstein

Massively Multilingual NLU 2022

Invited Audio system embody: Sebastian Ruder

Second Workshop on NLP for Constructive Affect

Invited Audio system embody: Milind Tambe

BlackboxNLP – Workshop on Analyzing and Decoding Neural Networks for NLP

Organizers embody: Jasmijn Bastings

MRL: The 2nd Workshop on Multi-lingual Illustration Studying

Organizers embody: Orhan Firat, Sebastian Ruder

Novel Concepts in Studying-to-Be taught By means of Interplay (NILLI)

Program Committee contains: Yu-Siang Wang

Tutorials

Emergent Language-Based mostly Coordination In Deep Multi-Agent Programs

Marco Baroni, Roberto Dessi, Angeliki Lazaridou

Tutorial on Causal Inference for Pure Language Processing

Zhijing Jin, Amir Feder, Kun Zhang

Modular and Parameter-Environment friendly Effective-Tuning for NLP Fashions

Sebastian Ruder, Jonas Pfeiffer, Ivan Vulic

* Work carried out whereas at Google