Wenjie Li

Determining Gains Acquired from Word Embedding Quantitatively Using Discrete Distribution Clustering

2017

Word embeddings have become widelyused in document analysis. While a large number of models for mapping words to vector spaces have been developed, it remains undetermined how much net gain can be achieved over traditional …

Incorporating Relevant Knowledge in Context Modeling and Response Generation

2018 · arXiv (Cornell University)

To sustain engaging conversation, it is critical for chatbots to make good use of relevant knowledge. Equipped with a knowledge base, chatbots are able to extract conversation-related attributes and entities to facilitate context modeling and …

Knowledge Graph Convolutional Networks for Recommender Systems

2019

To alleviate sparsity and cold start problem of collaborative filtering based recommender systems, researchers and engineers usually collect attributes of users and items, and design delicate algorithms to exploit these additional information. In general, the …

Component-Enhanced Chinese Character Embeddings

2015 · arXiv (Cornell University)

Distributed word representations are very useful for capturing semantic information and have been successfully applied in a variety of NLP tasks, especially on English. In this work, we innovatively develop two component-enhanced Chinese character embedding …

Knowledge-aware Graph Neural Networks with Label Smoothness Regularization for Recommender Systems

2019 · arXiv (Cornell University)

Knowledge graphs capture structured information and relations between a set of entities or items. As such knowledge graphs represent an attractive source of information that could help improve recommender systems. However, existing approaches in this …

Memory access integrity: detecting fine-grained memory access errors in binary code

2019 · Cybersecurity

As one of the most notorious programming errors, memory access errors still hurt modern software security. Particularly, they are hidden deeply in important software systems written in memory unsafe languages like C/C++. Plenty of work …

Three-Phase Inverter Fault Diagnosis Strategy Based on Compressed Sensing and Wavelet Packet Decomposition

2021 · 2021 China Automation Congress (CAC)

To solve the open circuit fault problem in the inverter system. a three-phase inverter fault feature extraction method based on compressed sensing and wavelet packet decomposition (CS-WPD) is proposed. Take the open circuit fault diagnosis …

Dual-Path Side Information Fusion for Sequential Recommendation

2023

Sequential recommendations are designed to capture user preferences based on their past actions and predict the items they may interact with in the next moment. Benefiting from the self-attention mechanism, methods that utilize side information …

Enhancing Tool Retrieval with Iterative Feedback from Large Language Models

2024 · arXiv (Cornell University)

Tool learning aims to enhance and expand large language models' (LLMs) capabilities with external tools, which has gained significant attention recently. Current methods have shown that LLMs can effectively handle a certain amount of tools …

Contrastive Preference Learning for Neural Machine Translation

2024

There exists a discrepancy between the tokenlevel objective during training and the overall sequence-level quality that is expected from the model.This discrepancy leads to issues like exposure bias.To align the model with human expectations, sequence-level …

Integrative Decoding: Improve Factuality via Implicit Self-consistency

2024 · arXiv (Cornell University)

Self-consistency-based approaches, which involve repeatedly sampling multiple outputs and selecting the most consistent one as the final response, prove to be remarkably effective in improving the factual accuracy of large language models. Nonetheless, existing methods …

DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset

2017 · arXiv (Cornell University)

We develop a high-quality multi-turn dialog dataset, DailyDialog, which is intriguing in several aspects. The language is human-written and less noisy. The dialogues in the dataset reflect our daily communication way and cover various topics …

Faithful to the Original: Fact Aware Neural Abstractive Summarization

2018 · Proceedings of the AAAI Conference on Artificial Intelligence

Unlike extractive summarization, abstractive summarization has to fuse different parts of the source text, which inclines to create fake facts. Our preliminary study reveals nearly 30% of the outputs from a state-of-the-art neural summarization system …

RippleNet

2018

To address the sparsity and cold start problem of collaborative filtering, researchers usually make use of side information, such as social networks or item attributes, to improve recommendation performance. This paper considers the knowledge graph …

Retrieve, Rerank and Rewrite: Soft Template Based Neural Summarization

2018

Most previous seq2seq summarization systems purely depend on the source text to generate summaries, which tends to work unstably. Inspired by the traditional template-based summarization approaches, this paper proposes to use existing summaries as soft …

Multi-Task Feature Learning for Knowledge Graph Enhanced Recommendation

2019

Collaborative filtering often suffers from sparsity and cold start problems in real recommendation scenarios, therefore, researchers and engineers usually use side information to address the issues and improve the performance of recommender systems. In this …

Exploring High-Order User Preference on the Knowledge Graph for Recommender Systems

2019 · ACM Transactions on Information Systems

To address the sparsity and cold-start problem of collaborative filtering, researchers usually make use of side information, such as social networks or item attributes, to improve the performance of recommendation. In this article, we consider …

Unpaired Sentiment-to-Sentiment Translation: A Cycled Reinforcement Learning Approach

2018

Jingjing Xu, Xu Sun, Qi Zeng, Xiaodong Zhang, Xuancheng Ren, Houfeng Wang, Wenjie Li. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2018.

Faithful to the Original: Fact Aware Neural Abstractive Summarization

2017 · arXiv (Cornell University)

Unlike extractive summarization, abstractive summarization has to fuse different parts of the source text, which inclines to create fake facts. Our preliminary study reveals nearly 30% of the outputs from a state-of-the-art neural summarization system …