会议背景

ACL 2023

在主会议和最近设立的ACL会议录中，某中心研究人员在今年计算语言学协会（ACL）会议上发表了超过65篇论文。

技术领域与论文精选

自动语音识别

• 掩码音频文本编码器作为有效的多模态重评分器 *Jason Cai, Monica Sunkara, Xilai Li, Anshu Bhatia, Xiao Pan, Sravan Bodapati

代码生成

• 大型语言模型代码补全的静态评估 Hantian Ding, Varun Kumar, Yuchen Tian, Zijian Wang, Rob Kwiatkowski, Xiaopeng LI, Murali Krishna Ramanathan, Baishakhi Ray, Parminder Bhatia, Sudipta Sengupta, Dan Roth, Bing Xiang

• 基于结构化知识的多任务预训练用于文本到SQL生成 Robert Giaquinto, Dejiao Zhang, Benjamin Kleiner, Yang Li, Ming Tan, Parminder Bhatia, Ramesh Nallapati, Xiaofei Ma

代码切换

• 未见语言对中的代码切换文本合成 *I-Hung Hsu, Avik Ray, Shubham Garg, Nanyun Peng, Jing Huang

• CoMix：使用POS结构和语音学指导变换器进行代码混合 *Gaurav Arora, Srujana Merugu, Vivek Sembium

持续学习

• 语言数据集漂移的特征描述与测量 Tyler A. Chang, Kishaloy Halder, Neha Anna John, Yogarshi Vyas, Yassine Benajiba, Miguel Ballesteros, Dan Roth

数据/表格到文本应用

• 用于鲁棒表格问答的内部表格检索器 Weizhe Lin, Rexhina Blloshmi, Bill Byrne, Adrià de Gispert, Gonzalo Iglesias

• 通过统一表示和多源学习进行少样本数据到文本生成 Alexander Hanbo Li, Mingyue Shang, Evangelia Spiliopoulou, JIE MA, Patrick Ng, Zhiguo Wang, Bonan Min, William Wang, Kathleen McKeown, Vittorio Castelli, Dan Roth, Bing Xiang

• 通过组合任务配置改进统一表格到文本模型的跨任务泛化能力 *Jifan Chen, Yuhao Zhang, Lan Liu, Rui Dong, Xinchi Chen, Patrick Ng, William Wang, Zhiheng Huang

• LI-RAGE：基于显式信号的延迟交互检索增强生成用于开放域表格问答 Weizhe Lin, Rexhina Blloshmi, Bill Byrne, Adrià de Gispert, Gonzalo Iglesias

对话系统

• Diable：将对话状态跟踪作为表格操作的高效实现 *Pietro Lesci, Yoshinari Fujinuma, Momchil Hardalov, Chao Shang, Lluis Marquez

• NatCS：引发自然客户支持对话 James Gung, Emily Moeng, Wesley Rose, Arshit Gupta, Yi Zhang, Saab Mansour

• 面向任务型对话的模式引导用户满意度建模 Yue Feng, Yunlong Jiao, Animesh Prasad, Nikolaos Aletras, Emine Yilmaz, Gabriella Kazai

• 面向更准确和可泛化的任务型对话评估指标 Abi Komma, Nagesh Panyam, Timothy Leffel, Anuj Goyal, Angeliki Metallinou, Spyros Matsoukas, Aram Galstyan

可解释人工智能

• 通过文本分类的摊销实现高效Shapley值估计 Alan Yang, Fan Yin, He He, Kai-Wei Chang, Xiaofei Ma, Bing Xiang

• 使用双教师自训练进行少样本原理生成 *Aditya Srikanth Veerubhotla, Lahari Poddar, Jun Yin, Gyuri Szarvas, Sharanya Eswaran

信息抽取

• 基于AMR的链接预测方法用于文档级事件论元抽取 Yuqing Yang, Qipeng Guo, Xiangkun Hu, Yue Zhang, Qipeng Guo, Zheng Zhang

• AVEN-GR：使用产品图进行属性值抽取和规范化 Donato Crisostomi, Thomas Ricatte

• 电子商务属性的大规模生成式多模态属性抽取 Anant Khandelwal, Happy Mittal, Shreyas Sunil Kulkarni, Deepak Gupta

• ParaAMR：通过AMR回译构建的大规模语法多样化释义数据集 Kuan-Hao Huang, Varun Iyer, I-Hung Hsu, Anoop Kumar, Kai-Wei Chang, Aram Galstyan

• 客户问题的弱监督分层多任务分类 Jitenkumar Rana, Promod Yenigalla, Chetan Aggarwal, Sandeep Mukku, Manan Soni, Rashmi Patange

• WebIE：网络上忠实且鲁棒的信息抽取 Chenxi Whitehouse, Clara Vania, Alham Fikri Aji, Christos Christodoulopoulos, Andrea Pierleoni

信息检索

• CUPID：基于课程学习的蒸馏实时预测 Arindam Bhattacharya, Ankith M S, Ankit Gandhi, Vijay Huddar, Atul Saroop, Rahul Bhagat

• 无需实体链接直接从知识图谱检索事实 Jinheon Baek, Alham Fikri Aji, Jens Lehmann, Sung Ju Hwang

语言建模

• 最近邻语言模型的适应方法 *Rishabh Bhardwaj, George Polovets, Monica Sunkara

• CONTRACLM：因果语言模型的对比学习 Nihal Jain, Dejiao Zhang, Wasi Ahmad, Zijian Wang, Feng Nan, Xiaopeng LI, Ming Tan, Baishakhi Ray, Parminder Bhatia, Xiaofei Ma, Ramesh Nallapati, Bing Xiang

• 通过隐藏表示变换进行受控文本生成 *Vaibhav Kumar, Hana Koorehdavoudi, Masud Moshtaghi, Amita Misra, Ankit Chadha, Emilio Ferrara

• KILM：向编码器-解码器语言模型注入知识 Yan XU, Mahdi Namazifar, Devamanyu Hazarika, Aishwarya Padmakumar, Yang Liu, Dilek Hakkani-Tür

• ReAugKD：预训练语言模型的检索增强知识蒸馏 Jianyi Zhang, Aashiq Muhamed, Aditya Anantharaman, Guoyin Wang, Changyou Chen, Kai Zhong, Qingjun Cui, Yi Xu, Belinda Zeng, Trishul Chilimbi, Yiran Chen

• 多语言编码器和seq2seq模型顺序预训练的实践方法 *Saleh Soltan, Andy Rosenbaum, Tobias Falke, Qin Lu, Anna Rumshisky, Wael Hamza

• 重新思考规模在上下文学习中的作用：基于660亿规模可解释性的案例研究 Hritik Bansal, Karthik Gopalakrishnan, Saket Dingliwal, Sravan Bodapati, Katrin Kirchhoff, Dan Roth

机器学习

• 通过批处理唯一样本和频率感知损失减轻冗余数据集的负担 Donato Crisostomi, Andrea Caciolai, Alessandro Pedrani, Alessandro Manzotti, Enrico Palumbo, Kay Rottmann, Davide Bernardi

机器翻译

• RAMP：检索和属性标记增强的提示用于属性控制翻译 Gabriele Sarti, Phu Mon Htut, Xing Niu, Benjamin Hsu, Anna Currey, Georgiana Dinu, Maria Nădejde

多模态模型

• 使用生成模型进行多样化模态实体链接的基准测试 *Sijia Wang, Alexander Li, Henry Zhu, Sheng Zhang, Pramuditha Perera, Chung-Wei Hang, JIE MA, William Wang, Zhiguo Wang, Vittorio Castelli, Bing Xiang, Patrick Ng

• 生成后选择：世界知识引导的开放式视觉问答 *Xingyu Fu, Sheng Zhang, Gukyeong Kwon, Pramuditha Perera, Henry Zhu, Yuhao Zhang, Alexander Hanbo Li, William Wang, Zhiguo Wang, Vittorio Castelli, Patrick Ng, Dan Roth, Bing Xiang

• KG-FLIP：电子商务中知识引导的时尚领域语言-图像预训练 Qinjin Jia, Yang Liu, Shaoyuan Xu, Huidong Liu, Daoping Wu, Jinmiao Fu, Roland Vollgraf, Bryan Wang

• 解决文本到图像生成模型中的歧义 Ninareh Mehrabi, Palash Goyal, Apurv Verma, Jwala Dhamala, Varun Kumar, Qian Hu, Kai-Wei Chang, Richard Zemel, Aram Galstyan, Rahul Gupta

• 翻译增强的多语言文本到图像生成 Yaoyiran Li, Ching-Yun (Frannie) Chang, Stephen Rawls, Ivan Vulić, Anna Korhonen

• 无监督旋律到歌词生成 Yufei Tian, Anjali Narayan-Chen, Shereen Oraby, Alessandra Cervone, Chenyang Tao, Gunnar Sigurdsson, Wenbo Zhao, Tagyoung Chung, Jing Huang, Violet Peng

自然语言处理

• Multi-VALUE：跨方言英语NLP框架 Caleb Ziems, William Held, Jingfeng Yang, Jwala Dhamala, Rahul Gupta, Diyi Yang

• vONTSS：基于vMF和最优传输的半监督神经主题建模 *Weijie Xu, Xiaoyu Jiang, Srinivasan Sengamedu, “SHS”, Francis Iannacci, Jinjin Zhao

自然语言理解

• ECG-QALM：使用上下文问答进行NER的实体控制合成文本生成 *Karan Aggarwal, Henry Jin, Aitzaz Ahmad

• 大规模虚拟助手中的实体对比学习 Jonathan Rubin, Jason Crowley, George Leung, Morteza Ziyadi, Maria Minakova

• EPIC：反语语料库的多视角标注 Simona Frenda, Alessandro Pedrani, Valerio Basile, Soda Marem Lo, Alessandra Teresa Cignarella, Raffaella Panizzon, Cristina Marco, Bianca Scarlini, Viviana Patti, Cristina Bosco, Davide Bernardi

• 深度神经网络中局部不稳定性的测量和缓解 *Arghya Datta, Subhrangshu Nandi, Jingcheng Xu, Greg Ver Steeg, He Xie, Anoop Kumar, Aram Galstyan

• 通过定向自训练方案减少自然语言理解系统中的群体偏差 Thu Le, Gabriela Cortes Hernandez, Bei Chen, Melanie Bradford

隐私保护

• 通过提示调优控制从大型语言模型中提取记忆数据 Mustafa Ozdayi, Charith Peris, Jack G. M. FitzGerald, Christophe Dupuy, Jimit Majmudar, Haidar Khan, Rahil Parikh, Rahul Gupta

查询重写

• 上下文感知查询重写以改善电子商务网站的用户搜索体验 Simiao Zuo, Qingyu Yin, Haoming Jiang, Shaohui Xi, Bing Yin, Chao Zhang, Tuo Zhao

• 统一上下文查询重写 Yingxue Zhou, Jie Hao, Mukund Rungta, Yang Liu, Eunah Cho, Xing Fan, Yanbin Lu, Vishal Vasudevan, Kellen Gillespie, Zeynab Raeesy, Sawyer Shen, Edward Guo, Gokhan Tur

问答系统

• 通过排名用户反馈准确训练基于网络的问答系统 Liang Wang, Ivano Lauriola, Alessandro Moschitti

• 上下文感知变换器预训练用于答案句子选择 Luca Di Liello, Siddhant Garg, Alessandro Moschitti

• 低资源语言中答案句子选择的跨语言知识蒸馏 *Shivanshu Gupta, Yoshitomo Matsubara, Ankit Chadha, Alessandro Moschitti

• 利用抽象意义表示进行开放域问答 *Cunxiang Wang, Zhikun Xu, Qipeng Guo, Xiangkun Hu, Xuefeng Bai, Zheng Zhang, Yue Zhang

• 开放域问答的混合分层检索 *Manoj Ghuhan Arivazhagan, Lan Liu, Peng Qi, Xinchi Chen, William Wang, Zhiheng Huang

• 使用自动问答评估器的监督学习答案生成 Matteo Gabburo, Siddhant Garg, Rik Koncel-Kedziorski, Alessandro Moschitti

• RobustQA：开放域问答领域适应鲁棒性的基准测试 *Rujun Han, Peng Qi, Yuhao Zhang, Lan Liu, Juliette Burger, William Wang, Zhiheng Huang, Bing Xiang, Dan Roth

推理

• FolkScope：电子商务常识发现中的意图知识图谱构建 *Changlong Yu, Weiqi Wang, Xin Liu, Jiaxin Bai, Yangqiu Song, Zheng Li, Yifan Gao, Tianyu Cao, Bing Yin

• SCOTT：自洽思维链蒸馏 Peifeng Wang, Zhengyang Wang, Zheng Li, Yifan Gao, Bing Yin, Xiang Ren

自学习

• 对话AI系统中受控自学习的约束策略优化 Mohammad Kachuee, Sungjin Lee

• 自学习对话系统中缺陷操作的可扩展安全修复 Sarthak Ahuja, Mohammad Kachuee, Fateme Sheikholeslami, Weiqing Liu, Jae Do

语义解析

• 利用知识进行低资源任务型语义解析的实证分析 *Mayank Kulkarni, Aoxiao Zhong, Nicolas Guenon Des Mesnards, Sahar Movaghati, Mukund Harakere, He Xie, Jianhua Lu

• XSEMPLR：多自然语言和意义表示中的跨语言语义解析 Yusen Zhang, Jun Wang, Zhiguo Wang, Rui Zhang

口语理解

• 口语理解的回归无关模型更新 Andrea Caciolai, Verena Weber, Tobias Falke, Alessandro Pedrani, Davide Bernardi

• 在大型口语理解中跨语言、领域和任务共享编码器表示 Jonathan Hueser, Judith Gaspers, Thomas Gueudre, Chandana Satya Prakash, Jin Cao, Daniil Sorokin, Quynh Do, Nicolas Anastassacos, Tobias Falke, Turan Gojayev, Mariusz Momotko, Denis Romasanta Rodriguez, Austin Doolittle, Kartik Balasubramaniam, Wael Hamza, Fabian Triefenbach, Patrick Lehnen

有害语言分类

• QCon在SemEval-2023任务10：数据增强和模型集成用于在线性别歧视检测 Wes Feely, Prabhakar Gupta, Manas Mohanty, Tim Chon, Tuhin Kundu, Vijit Singh, Sandeep Atluri, Tanya Roosta, Viviane Ghaderi, Peter Schulam, Heba Elfardy

• 构建鲁棒的有害内容预测器 Dmitriy Bespalov, Sourav Bhabesh, Yi Xiang, Yanjun (Jane) Qi

*已接受至ACL Findings