Efficient Methods for Natural Language Processing: A Survey Marcos Treviso1∗, Ji-Ung Lee2∗, Tianchu Ji3∗, Betty van Aken4, Qingqing Cao5, Manuel R. Ciosici6, Michael Hassid7, Kenneth Heafield8, Sara Hooker9, Colin Raffel10, Pedro H. Martins1,11, Andr´e F. 时间. Martins1,11, Jessica Zosa Forde12, Peter Milder3, Edwin Simpson13, Noam Slonim14, Jesse Dodge15, Emma Strubell15,16, Niranjan Balasubramanian3, Leon Derczynski5,17, Iryna Gurevych2, Roy Schwartz7 1IST/U. of Lisbon and Instituto de Telecomunicac¸

MENLI: Robust Evaluation Metrics from Natural Language Inference Yanran Chen1,2 and Steffen Eger2 1Technische Universit¨at Darmstadt, Germany 2Natural Language Learning Group (NLLG), https://nl2g.github.io/ Faculty of Technology, Universit¨at Bielefeld, Germany yanran.chen@stud.tu-darmstadt.de, steffen.eger@uni-bielefeld.de Abstract Recently proposed BERT-based evaluation metrics for text generation perform well on standard benchmarks but are vulnerable to ad- versarial attacks, 例如, relating to information correctness. We argue that this stems (部分地) 从

Chinese Idiom Paraphrasing Jipeng Qiang1∗ Yang Li1 Chaowei Zhang1 Yun Li1 Yi Zhu1 Yunhao Yuan1 Xindong Wu2,3 1 Yangzhou University, 中国, 2 Hefei University of Technology, 中国, 3 Zhejiang Lab, 中国 {jpqiang,cwzhang,liyun,zhuyi,yhyuan}@yzu.edu.cn, xwu@hfut.edu.cn Abstract Idioms are a kind of idiomatic expression in Chinese, most of which consist of four Chinese characters. Due to the properties of non-compositionality and metaphorical mean- 英, Chinese idioms are hard

Supervised Gradual Machine Learning for Aspect-Term Sentiment Analysis Yanyan Wang†‡ Qun Chen∗†‡ Murtadha H.M. Ahmed†‡ Zhaoqiang Chen†‡ Jing Su†‡ Wei Pan†‡ Zhanhuai Li†‡ †School of Computer Science, Northwestern Polytechnical University, Xi’an, China ‡Key Laboratory of Big Data Storage and Management, Northwestern Polytechnical University, Ministry of Industry and Information Technology, Xi’an, 中国 {wangyanyan@mail., chenbenben@, murtadha@mail., chenzhaoqiang@mail., sujing@mail., panwei1002@, lizhh@}nwpu.edu.cn Abstract Recent work has shown that Aspect-Term

On Graph-based Reentrancy-free Semantic Parsing Alban Petit and Caio Corro Universite Paris-Saclay, 法国国家科学研究中心, LISN, 91400, Orsay, 法国 {alban.petit,caio.corro}@lisn.upsaclay.fr Abstract We propose a novel graph-based approach for semantic parsing that resolves two prob- lems observed in the literature: (1) seq2seq models fail on compositional generalization tasks; (2) previous work using phrase structure parsers cannot cover all the semantic parses observed in treebanks. We prove that both

OpenFact: Factuality Enhanced Open Knowledge Extraction Linfeng Song∗, Ante Wang∗,†, Xiaoman Pan, Hongming Zhang, Dian Yu, Lifeng Jin, Haitao Mi, Jinsong Su†, Yue Zhang‡ and Dong Yu Tencent AI Lab, Bellevue, WA, USA †School of Informatics, Xiamen University, China ‡School of Engineering, Westlake University, China lfsong@global.tencent.com Abstract We focus on the factuality property during the extraction of an OpenIE corpus named OpenFact, which contains more

FRMT: A Benchmark for Few-Shot Region-Aware Machine Translation Parker Riley∗, Timothy Dozat∗, Jan A. Botha∗, Xavier Garcia∗, Dan Garrette, Jason Riesa, Orhan Firat, Noah Constant Google Research, 美国 {prkriley,tdozat,jabot,xgarcia,dhgarrette, riesa,orhanf,nconstant}@google.com Abstract We present FRMT, a new dataset and evalu- ation benchmark for Few-shot Region-aware Machine Translation, a type of style-targeted translation. The dataset consists of professional translations from English into two regional variants each of

Visual Spatial Reasoning Fangyu Liu Guy Emerson Nigel Collier University of Cambridge, 英国 {fl399, gete2, nhc30}@cam.ac.uk Abstract Spatial relations are a basic part of human cog- 尼尼申. 然而, they are expressed in natural language in a variety of ways, and previous work has suggested that current vision-and- language models (VLMs) struggle to capture relational information. 在本文中, we pres- ent Visual Spatial Reasoning (VSR),

Transparency Helps Reveal When Language Models Learn Meaning Zhaofeng Wu ∗ William Merrill Hao Peng Iz Beltagy Noah A. Smith MIT New York University Allen Institute for Artificial Intelligence Paul G. Allen School of Computer Science & Engineering, University of Washington zfw@csail.mit.edu willm@nyu.edu {haop,beltagy,noah}@allenai.org Abstract Many current NLP systems are built from language models trained to optimize unsu- pervised objectives on large amounts of raw

Understanding and Detecting Hallucinations in Neural Machine Translation via Model Introspection Weijia Xu Microsoft Research, Redmond, USA weijiaxu@microsoft.com Sweta Agrawal University of Maryland, USA sweagraw@cs.umd.edu Eleftheria Briakou University of Maryland, USA ebriakou@cs.umd.edu Marianna J. Martindale University of Maryland, USA mmartind@umd.edu Marine Carpuat University of Maryland, USA marine@cs.umd.edu Abstract Neural sequence generation models are known to ‘‘hallucinate’’, by producing outputs that are unrelated to the source

The Parallelism Tradeoff: Limitations of Log-Precision Transformers William Merrill Center for Data Science New York University, 纽约, 纽约, USA willm@nyu.edu Ashish Sabharwal Allen Institute for AI Seattle, WA, USA ashishs@allenai.org Abstract Despite their omnipresence in modern NLP, characterizing the computational power of transformer neural nets remains an interest- ing open question. We prove that transformers whose arithmetic precision is logarithmic in the number of

Erasure of Unaligned Attributes from Neural Representations Shun Shao∗ Yftah Ziser∗ Shay B. Cohen Institute for Language, Cognition and Computation School of Informatics, 爱丁堡大学 10 Crichton Street, 爱丁堡, EH8 9AB, UK s.shao-11@inf.ed.ac.uk yftah.ziser@inf.ed.ac.uk scohen@inf.ed.ac.uk Abstract the Assignment-Maximization We present Spectral Attribute removaL (AMSAL) algo- rithm, which erases information from neural representations when the information to be erased is implicit rather than directly being

Unleashing the True Potential of Sequence-to-Sequence Models for Sequence Tagging and Structure Parsing Han He Department of Computer Science Emory University Atlanta, 遗传算法 30322 USA han.he@emory.edu Jinho D. Choi Department of Computer Science Emory University Atlanta, 遗传算法 30322 USA jinho.choi@emory.edu Abstract Sequence-to-Sequence (S2S) models have achieved remarkable success on various text generation tasks. 然而, learning complex structures with S2S models remains challeng- ing as external

Tracking Brand-Associated Polarity-Bearing Topics in User Reviews Runcong Zhao1,2, Lin Gui1, Hanqi Yan2, Yulan He1,2,3 1King’s College London, 英国, 2University of Warwick, 英国, 3The Alan Turing Institute, United Kingdom runcong.zhao@warwick.ac.uk, yulan.he@kcl.ac.uk Abstract Monitoring online customer reviews is im- portant for business organizations to measure customer satisfaction and better manage their reputations. 在本文中, we propose a novel dynamic Brand-Topic Model (dBTM) 哪个

Naturalistic Causal Probing for Morpho-Syntax Afra Amini1,2 Tiago Pimentel3 Clara Meister1 Ryan Cotterell1,2 1ETH Z¨urich, Switzerland 2ETH AI Center, 瑞士 3剑桥大学, UK afra.amini@inf.ethz.ch tp472@cam.ac.uk ryan.cotterell@inf.ethz.ch clara.meister@inf.ethz.ch Abstract Probing has become a go-to methodology for interpreting and analyzing deep neural mod- els in natural language processing. 然而, there is still a lack of understanding of the limitations and weaknesses of various types of probes.

Visual Writing Prompts: Character-Grounded Story Generation with Curated Image Sequences Xudong Hong1,2,4, Asad Sayeed3, Khushboo Mehra2,4, Vera Demberg2,4 and Bernt Schiele1,4 1Dept. of Computer Vision and Machine Learning, MPI Informatics, Germany 2Dept. of Language Science and Technology and Dept. of Computer Science, Saarland University, Germany 3Dept. of Philosophy, 语言学, and Theory of Science, University of Gothenburg, Sweden 4Saarland Informatics Campus, 萨尔布吕肯, 德国 {xhong,kmehra,维拉}@lst.uni-saarland.de schiele@mpi-inf.mpg.de, asad.sayeed@gu.se

Hate Speech Classifiers Learn Normative Social Stereotypes Aida Mostafazadeh Davani, Mohammad Atari, Brendan Kennedy, Morteza Dehghani University of Southern California, 美国 {mostafaz,atari,btkenned,mdehghan}@usc.edu Abstract Social stereotypes negatively impact individ- uals’ judgments about different groups and may have a critical role in understanding lan- guage directed toward marginalized groups. 这里, we assess the role of social stereotypes in the automated detection of hate speech in the English

On the Robustness of Dialogue History Representation in Conversational Question Answering: A Comprehensive Study and a New Prompt-based Method Zorik GekhmanT∗ Nadav OvedT ∗ Orgad KellerG Idan SzpektorG Roi ReichartT T Technion – Israel Institute of Technology, Israel GGoogle Research, 以色列 {zorik@campus.|nadavo@campus.|roiri@}technion.ac.il {orgad|szpektor}@google.com Abstract Most work on modeling the conversation his- tory in Conversational Question Answering (CQA) reports a single main result on a com-