1.5k citations · 5.2k across the 138 of their papers we have counts for
36 papers · 1 filter
Synthetic Pre-Training Tasks for Neural Machine Translation
Zexue He, Graeme Blackwood, Rameswar Panda +2
Pre-training models with large crawled corpora can lead to issues such as toxicity and bias, as well as copyright and privacy concerns. A promising way of alleviating such concerns…
CLIPSep: Learning Text-queried Sound Separation with Noisy Unlabeled Videos
Hao-Wen Dong, Naoya Takahashi, Yuki Mitsufuji +2
Recent years have seen progress beyond domain-specific sound separation for speech or music towards universal sound separation for arbitrary sounds. Prior work on universal sound s…
Controlling Bias Exposure for Fair Interpretable Predictions
Zexue He, Yu Wang, Julian McAuley +1
Recent work on reducing bias in NLP models usually focuses on protecting or isolating information related to a sensitive attribute (like gender or race). However, when sensitive in…
InforMask: Unsupervised Informative Masking for Language Model Pretraining
Nafis Sadeq, Canwen Xu, Julian McAuley
Masked language modeling is widely used for pretraining large language models for natural language understanding (NLU). However, random masking is suboptimal, allocating an equal m…
Efficiently Tuned Parameters are Task Embeddings
Wangchunshu Zhou, Canwen Xu, Julian McAuley
Intermediate-task transfer can benefit a wide range of NLP tasks with properly selected source datasets. However, it is computationally infeasible to experiment with all intermedia…
CLIP also Understands Text: Prompting CLIP for Phrase Understanding
An Yan, Jiacheng Li, Wanrong Zhu +3
Contrastive Language-Image Pretraining (CLIP) efficiently learns visual concepts by pre-training with natural language supervision. CLIP and its visual encoder have been explored o…
Learning Vector-Quantized Item Representation for Transferable Sequential Recommenders
Yupeng Hou, Zhankui He, Julian McAuley +1
Recently, the generality of natural language text has been leveraged to develop transferable recommender systems. The basic idea is to employ pre-trained language models~(PLM) to e…
InterFair: Debiasing with Natural Language Feedback for Fair Interpretable Predictions
Bodhisattwa Prasad Majumder, Zexue He, Julian McAuley
Debiasing methods in NLP models traditionally focus on isolating information related to a sensitive attribute (e.g., gender or race). We instead argue that a favorable debiasing me…
Factual and Informative Review Generation for Explainable Recommendation
Zhouhang Xie, Sameer Singh, Julian McAuley +1
Recent models can generate fluent and grammatical synthetic reviews while accurately predicting user ratings. The generated reviews, expressing users' estimated opinions towards re…
On Faithfulness and Coherence of Language Explanations for Recommendation Systems
Zhouhang Xie, Julian McAuley, Bodhisattwa Prasad Majumder
Reviews contain rich information about product characteristics and user interests and thus are commonly used to boost recommender system performance. Specifically, previous work sh…
Improving Choral Music Separation through Expressive Synthesized Data from Sampled Instruments
Ke Chen, Hao-Wen Dong, Yi Luo +4
Choral music separation refers to the task of extracting tracks of voice parts (e.g., soprano, alto, tenor, and bass) from mixed audio. The lack of datasets has impeded research on…
UCEpic: Unifying Aspect Planning and Lexical Constraints for Generating Explanations in Recommendation
Jiacheng Li, Zhankui He, Jingbo Shang +1
Personalized natural language generation for explainable recommendations plays a key role in justifying why a recommendation might match a user's interests. Existing models usually…
Generating Negative Samples for Sequential Recommendation
Yongjun Chen, Jia Li, Zhiwei Liu +4
To make Sequential Recommendation (SR) successful, recent works focus on designing effective sequential encoders, fusing side information, and mining extra positive self-supervisio…
Plug-and-Play Model-Agnostic Counterfactual Policy Synthesis for Deep Reinforcement Learning based Recommendation
Siyu Wang, Xiaocong Chen, Lina Yao +2
Recent advances in recommender systems have proved the potential of Reinforcement Learning (RL) to handle the dynamic evolution processes between users and recommender systems. How…
Bundle MCR: Towards Conversational Bundle Recommendation
Zhankui He, Handong Zhao, Tong Yu +3
Bundle recommender systems recommend sets of items (e.g., pants, shirt, and shoes) to users, but they often suffer from two issues: significant interaction sparsity and a large out…
Contrastive Learning for Interactive Recommendation in Fashion
Karin Sevegnani, Arjun Seshadri, Tian Wang +4
Recommender systems and search are both indispensable in facilitating personalization and ease of browsing in online fashion platforms. However, the two tools often operate indepen…
Multitrack Music Transformer
Hao-Wen Dong, Ke Chen, Shlomo Dubnov +2
Existing approaches for generating multitrack music with transformer models have been limited in terms of the number of instruments, the length of the music segments and slow infer…
Personalized Showcases: Generating Multi-Modal Explanations for Recommendations
An Yan, Zhankui He, Jiacheng Li +2
Existing explanation models generate only text for recommendations but still struggle to produce diverse contents. In this paper, to further enrich explanations, we propose a new t…
Infinite Recommendation Networks: A Data-Centric Approach
Noveen Sachdeva, Mehak Preet Dhaliwal, Carole-Jean Wu +1
We leverage the Neural Tangent Kernel and its equivalence to training infinitely-wide neural networks to devise -AE: an autoencoder with infinitely-wide bottleneck layers.…
Assistive Recipe Editing through Critiquing
Diego Antognini, Shuyang Li, Boi Faltings +1
There has recently been growing interest in the automatic generation of cooking recipes that satisfy some form of dietary restrictions, thanks in part to the availability of online…
Instilling Type Knowledge in Language Models via Multi-Task QA
Shuyang Li, Mukund Sridhar, Chandana Satya Prakash +3
Understanding human language often necessitates understanding entities and their place in a taxonomy of knowledge -- their types. Previous methods to learn entity types rely on tra…
LaPraDoR: Unsupervised Pretrained Dense Retriever for Zero-Shot Text Retrieval
Canwen Xu, Daya Guo, Nan Duan +1
In this paper, we propose LaPraDoR, a pretrained dual-tower dense retriever that does not require any supervised data for training. Specifically, we first present Iterative Contras…
Automatic Multi-Label Prompting: Simple and Interpretable Few-Shot Classification
Han Wang, Canwen Xu, Julian McAuley
Prompt-based learning (i.e., prompting) is an emerging paradigm for exploiting knowledge learned by a pretrained language model. In this paper, we propose Automatic Multi-Label Pro…
FaceSigns: Semi-Fragile Neural Watermarks for Media Authentication and Countering Deepfakes
Paarth Neekhara, Shehzeen Hussain, Xinqiao Zhang +3
Deepfakes and manipulated media are becoming a prominent threat due to the recent advances in realistic image and video synthesis techniques. There have been several attempts at co…