[ad_1]
Pure-language understanding (NLU) has lengthy been a central focus of the papers that Amazon researchers publish on the Convention on Empirical Strategies in Pure-Language Processing (EMNLP), however at this 12 months’s convention, which begins right now, Amazon’s NLU analysis reveals a specific curiosity in harnessing the ability of huge language fashions (LLMs). Query answering additionally stays an energetic analysis subject, whereas question reformulation and textual content summarization emerge as new areas of focus.
Automated speech recognition
AdaBERT-CTC: Leveraging BERT-CTC for text-only area adaptation in ASR
Tyler Vuong, Karel Mundnich, Dhanush Bekal, Veera Raghavendra Elluru, Srikanth Ronanki, Sravan Bodapati
Continuous studying
Coordinated replay pattern choice for continuous federated studying
Jack Good, Jimit Majmudar, Christophe Dupuy, Jixuan Wang, Charith Peris, Clement Chung, Richard Zemel, Rahul Gupta
Knowledge extraction
InsightNet: Structured perception mining from buyer suggestions
Sandeep Mukku, Manan Soni, Chetan Aggarwal, Jitenkumar Rana, Promod Yenigalla, Rashmi Patange, Shyam Mohan
Information-selective pretraining for attribute worth extraction
Hui Liu, Qingyu Yin, Zhengyang Wang, Chenwei Zhang, Haoming Jiang, Yifan Gao, Zheng Li, Xian Li, Chenwei Zhang, Bing Yin, William Wang, Xiaodan Zhu
Knowledge choice
Affect scores at scale for environment friendly language information sampling
Nikhil Anand, Joshua Tan, Maria Minakova
Doc understanding
A multi-modal multilingual benchmark for doc picture classification
Yoshinari Fujinuma, Siddharth Varia, Nishant Sankaran, Bonan Min, Srikar Appalaraju, Yogarshi Vyas
Semantic matching for textual content classification with complicated class descriptions
Brian de Silva, Kuan-Wen Huang, Gwang Lee, Karen Hovsepian, Yan Xu, Mingwei Shen
Embodied job completion
Multimodal embodied plan prediction augmented with artificial embodied dialogue
Aishwarya Padmakumar, Mert Inan, Spandana Gella, Patrick Lange, Dilek Hakkani-Tür
Entity linking
MReFinED: An environment friendly end-to-end multilingual entity linking system
Peerat Limkonchotiwat, Weiwei Cheng, Christos Christodoulopoulos, Amir Saffari, Jens Lehmann
Few-shot studying
Automated few-shot classification with instruction-finetuned language fashions
Rami Aly, Xingjian Shi, Kaixiang Lin, Aston Zhang, Andrew Wilson
Data retrieval
Deep metric studying to hierarchically rank—An software in product retrieval
Kee Kiat Koo, Ashutosh Joshi, Nishaanth Reddy, Ismail Tutar, Vaclav Petricek, Changhe Yuan, Karim Bouyarmane
KD-Enhance: Boosting real-time semantic matching in e-commerce with information distillation
Sanjay Agrawal, Vivek Sembium, Ankith M S
Multi-teacher distillation for multilingual spelling correction
Jingfen Zhang, Xuan Guo, Sravan Bodapati, Christopher Potts
Instruction tuning
CESAR: Automated induction of compositional directions for multi-turn dialogs
Taha Aksu, Devamanyu Hazarika, Shikib Mehri, Seokhwan Kim, Dilek Hakkani-Tür, Yang Liu, Mahdi Namazifar
LLM hallucination
INVITE: A testbed of robotically generated invalid questions to judge giant language fashions for hallucinations
Anil Ramakrishna, Rahul Gupta, Jens Lehmann, Morteza Ziyadi
Machine studying
Environment friendly long-range transformers: It’s good to attend extra, however not essentially at each layer
Qingru Zhang, Dhananjay Ram, Cole Hawkins, Sheng Zha, Tuo Zhao
Pure-language processing
NameGuess: Column title enlargement for tabular information
Jiani Zhang, Zhengyuan Shen, Balasubramaniam Srinivasan, Shen Wang, Huzefa Rangwala, George Karypis
Pure-language understanding
Adversarial robustness for large-language NER fashions utilizing disentanglement and phrase attributions
Xiaomeng Jin, Bhanu Vinzamuri, Sriram Venkatapathy, Heng Ji, Pradeep Natarajan
Measuring and mitigating dialog-to-API constraint violations of in-context studying
Shufan Wang, Sebastien Jean, Sailik Sengupta, James Gung, Nikolaos Pappas, Yi Zhang
MultiCoNER v2: A big multilingual dataset for fine-grained and noisy named entity recognition
Besnik Fetahu, Zhiyu Chen, Sudipta Kar, Oleg Rokhlenko, Shervin Malmasi
Pre-training intent-aware encoders for zero- and few-shot intent classification
Mujeen Sung, James Gung, Elman Mansimov, Nikolaos Pappas, Raphael Shu, Salvatore Romeo, Yi Zhang, Vittorio Castelli
Personalization
Customized dense retrieval on international index for voice-enabled conversational techniques
Masha Belyi, Charlotte Dzialo, Chaitanya Dwivedi, Prajit Reddy Muppidi, Kanna Shimizu
Retrieve and duplicate: Scaling ASR personalization to giant catalogs
Sai Muralidhar Jayanthi, Devang Kulshreshtha, Saket Dingliwal, Srikanth Ronanki, Sravan Bodapati
Question reformulation
CL-QR: Cross-lingual enhanced question reformulation for multi-lingual conversational AI brokers
Zhongkai Solar, Zhengyang Zhao, Sixing Lu, Chengyuan Ma, Xiaohu Liu, Xing Fan, Wei (Sawyer) Shen, Chenlei (Edward) Guo
Graph meets LLM: A novel strategy to collaborative filtering for sturdy conversational understanding
Zheng Chen, Ziyan Jiang, Fan Yang, Eunah Cho, Xing Fan, Xiaojiang Huang, Yanbin Lu, Aram Galstyan
Bettering contextual question rewrite for conversational AI brokers by means of user-preference suggestions studying
Zhongkai Solar, Yingxue Zhou, Jie Hao, Xing Fan, Yanbin Lu, Chengyuan Ma, Wei (Sawyer) Shen, Chenlei (Edward) Guo
Query-answer databases
Protege: Immediate-based various query technology from internet articles
Vinayak Puranik, Anirban Majumder, Vineet Chaoji
QUADRo: Dataset and fashions for question-answer database retrieval
Stefano Campese, Ivano Lauriola, Alessandro Moschitti
Query answering
Robust and environment friendly baselines for open area conversational query answering
Andrei C. Coman, Gianni Barlacchi, Adrià de Gispert
Tokenization consistency issues for generative fashions on extractive NLP duties
Kaiser Solar, Peng Qi, Yuhao Zhang, Lan Liu, William Yang Wang, Zhiheng Huang
An excessive amount of of product data: Don’t fear, let’s search for proof!
Aryan Jain, Jitenkumar Rana, Chetan Aggarwal
Reasoning
Plan, confirm and swap: Built-in reasoning with various x-of-thoughts
Tengxiao Liu, Qipeng Guo, Yuqing Yang, Xiangkun Hu, Yue Zhang, Xipeng Qiu, Zheng Zhang
Accountable AI
Geographical erasure in language technology
Pola Schwöbel, Jacek Golebiowski, Michele Donini, Cédric Archambeau, Danish Pruthi
Speech translation
Finish-to-end single-channel speaker-turn conscious conversational speech translation
Juan Pablo Zuluaga Gomez, Zhaocheng Huang, Xing Niu, Rohit Paturi, Sundararajan Srinivasan, Prashant Mathur, Brian Thompson, Marcello Federico
Textual content summarization
Enhancing abstractiveness of summarization fashions by means of calibrated distillation
Hwanjun Tune, Igor Shalyminov, Grasp Su, Siffi Singh, Kaisheng Yao, Saab Mansour
Producing summaries with controllable readability ranges
Leonardo Ribeiro, Mohit Bansal, Markus Dreyer
Bettering consistency for textual content summarization with power features
Qi Zeng, Qingyu Yin, Zheng Li, Yifan Gao, Sreyashi Nag, Zhengyang Wang, Bing Yin, Heng Ji, Chao Zhang
InstructPTS: Instruction-tuning LLMs for product title summarization
Besnik Fetahu, Zhiyu Chen, Oleg Rokhlenko, Shervin Malmasi
Multi doc summarization analysis within the presence of damaging content material
Avshalom Manevich, David Carmel, Nachshon Cohen, Elad Kravi, Ori Shapira
Re-examining summarization analysis throughout a number of high quality standards
Ori Ernst, Ori Shapira, Ido Dagan, Ran Levy
Matter modeling
DeTiME: Diffusion-enhanced subject modeling utilizing encoder-decoder based mostly LLM
Weijie Xu, Wenxiang Hu, Fanyou Wu, Srinivasan Sengamedu, “SHS”
[ad_2]
