Skip to search formSkip to main contentSkip to account menu

S3-Rec: Self-Supervised Learning for Sequential Recommendation with Mutual Information Maximization

This work proposes the model S3-Rec, which stands for Self-Supervised learning for Sequential Recommendation, based on the self-attentive neural architecture, to utilize the intrinsic data correlation to derive self-supervision signals and enhance the data representations via pre-training methods for improving sequential recommendation.
View on ACM (opens in a new tab)

Counterfactual VQA: A Cause-Effect Look at Language Bias

A novel counterfactual inference framework is proposed, which enables the language bias to be captured as the direct causal effect of questions on answers and reduced by subtracting the direct language effect from the total causal effect.
View on IEEE (opens in a new tab)

Improving Conversational Recommender Systems via Knowledge Graph based Semantic Fusion

This work incorporates both word-oriented and entity-oriented knowledge graphs~(KG) to enhance the data representations in CRSs, and adopts Mutual Information Maximization to align the word-level andentity-level semantic spaces.
View on ACM (opens in a new tab)

RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-ranking

A novel joint training approach for dense passage retrieval and passage reranking is proposed, where the dynamic listwise distillation is introduced, where a unified listwise training approach is designed for both the retriever and the re-ranker.
View on ACL (opens in a new tab)

Scalable Graph Neural Networks via Bidirectional Propagation

GBP is the first method that achieves sub-linear time complexity for both the precomputation and the training phases and can deliver superior performance on a graph with over 60 million nodes and 1.8 billion edges in less than half an hour on a single machine.
View PDF on arXiv (opens in a new tab)

Towards Topic-Guided Conversational Recommender System

This paper presents the task of topic-guided conversational recommendation, and proposes an effective approach to this task, and contributes a new CRS dataset named TG-ReDial (Recommendation through Topic-Guided Dialog), which has two major features.
View on ACL (opens in a new tab)

Improving Sequential Recommendation with Knowledge-Enhanced Memory Networks

This paper proposes a novel knowledge enhanced sequential recommender that integrates the RNN-based networks with Key-Value Memory Network (KV-MN) and incorporates knowledge base information to enhance the semantic representation of KV- MN.
View on ACM (opens in a new tab)

Improving Multi-hop Knowledge Base Question Answering by Learning Intermediate Supervision Signals

A novel teacher-student approach for the multi-hop KBQA task, where the teacher network tries to learn intermediate supervision signals for improving the reasoning capacity of the student network, and both forward and backward reasoning are utilized to enhance the learning of intermediate entity distributions.
View on ACM (opens in a new tab)

PAIR: Leveraging Passage-Centric Similarity Relation for Improving Dense Passage Retrieval

This work proposes a novel approach that leverages both query-centric and PAssage-centric sImilarity Relations (called PAIR) for dense passage retrieval that significantly outperforms previous state-of-the-art models on both MSMARCO and Natural Questions datasets.
View on ACL (opens in a new tab)

Probabilistic Analysis

View via Publisher (opens in a new tab)
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)