Lifeng Shang

Dual Sequence Transformer for Query-based Interactive Recommendation

2021

Interactive recommendation has drawn widespread attention from both academia and industry due to its effectiveness in real-world mobile applications. Instead of receiving message passively, customers can exploit further with less effort through generated queries. Usually, …

PanGu-Bot: Efficient Generative Dialogue Pre-training from Pre-trained Language Model

2022 · arXiv (Cornell University)

In this paper, we introduce PanGu-Bot, a Chinese pre-trained open-domain dialogue generation model based on a large pre-trained language model (PLM) PANGU-alpha (Zeng et al.,2021). Different from other pre-trained dialogue models trained over a massive …

Pre-training Language Models with Deterministic Factual Knowledge

2022 · arXiv (Cornell University)

Previous works show that Pre-trained Language Models (PLMs) can capture factual knowledge. However, some analyses reveal that PLMs fail to perform it robustly, e.g., being sensitive to the changes of prompts when extracting factual knowledge. …

Learning to Edit: Aligning LLMs with Knowledge Editing

2024 · arXiv (Cornell University)

Knowledge editing techniques, aiming to efficiently modify a minor proportion of knowledge in large language models (LLMs) without negatively impacting performance across other inputs, have garnered widespread attention. However, existing methods predominantly rely on memorizing …

Neural Responding Machine for Short-Text Conversation

2015 · arXiv (Cornell University)

We propose Neural Responding Machine (NRM), a neural network-based response generator for Short-Text Conversation. NRM takes the general encoder-decoder framework: it formalizes the generation of response as a decoding process based on the latent representation …

Neural Generative Question Answering

2015 · arXiv (Cornell University)

This paper presents an end-to-end neural network model, named Neural Generative Question Answering (GENQA), that can generate answers to simple factoid questions, based on the facts in a knowledge-base. More specifically, the model is built …

Decomposable Neural Paraphrase Generation

2019

Paraphrasing exists at different granularity levels, such as lexical level, phrasal level and sentential level. This paper presents Decomposable Neural Paraphrase Generator (DNPG), a Transformer-based model that can learn and generate paraphrases of a sentence …

Paraphrase Generation with Deep Reinforcement Learning

2018

Automatic generation of paraphrases from a given sentence is an important yet challenging task in natural language processing (NLP). In this paper, we present a deep reinforcement learning approach to paraphrase generation. Specifically, we propose …

Neural Generative Question Answering

2016

This paper presents an end-to-end neural network model, named Neural Generative Question Answering (GENQA), that can generate answers to simple factoid questions, based on the facts in a knowledge-base.More specifically, the model is built on …

TinyBERT: Distilling BERT for Natural Language Understanding

2019 · arXiv (Cornell University)

Language model pre-training, such as BERT, has significantly improved the performances of many natural language processing tasks. However, pre-trained language models are usually computationally expensive, so it is difficult to efficiently execute them on resource-restricted …

TinyBERT: Distilling BERT for Natural Language Understanding

2020

Language model pre-training, such as BERT, has significantly improved the performances of many natural language processing tasks. However, pre-trained language models are usually computationally expensive, so it is difficult to efficiently execute them on resourcerestricted …

Noninvasive Self-attention for Side Information Fusion in Sequential Recommendation

2021 · Proceedings of the AAAI Conference on Artificial Intelligence

Sequential recommender systems aim to model users’ evolving interests from their historical behaviors, and hence make customized time-relevant recommendations. Compared with traditional models, deep learning approaches such as CNN and RNN have achieved remarkable advancements …