Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Kai-Fu LeeSuggested from co-authorship
- Changning HuangSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works414 from public data
- Embedding Entities and Relations for Learning and Inference in Knowledge Bases3,965
It is found that embeddings learned from the bilinear objective are particularly good at capturing relational semantics and that the composition of relations is characterized by matrix multiplication.
- MS MARCO: A Human Generated MAchine Reading COmprehension Dataset.3,691
This new dataset is aimed to overcome a number of well-known weaknesses of previous publicly available datasets for the same task of reading comprehension and question answering, and is the most comprehensive real-world dataset of its kind in both quantity and quality.
- PIQA: Reasoning about Physical Commonsense in Natural Language3,673
The task of physical commonsense reasoning and a corresponding benchmark dataset Physical Interaction: Question Answering or PIQA are introduced and analysis about the dimensions of knowledge that existing models lack are provided, which offers significant opportunities for future research.
- A Diversity-Promoting Objective Function for Neural Conversation Models2,879
This work proposes using Maximum Mutual Information (MMI) as the objective function in neural models, and demonstrates that the proposed MMI models produce more diverse, interesting, and appropriate responses, yielding substantive gains in BLEU scores on two conversational datasets and in human evaluations.
- Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing2,830
It is shown that for domains with abundant unlabeled text, such as biomedicine, pretraining language models from scratch results in substantial gains over continual pretraining of general-domain language models.
- DIALOGPT : Large-Scale Generative Pre-training for Conversational Response Generation1,771
It is shown that conversational systems that leverage DialoGPT generate more relevant, contentful and context-consistent responses than strong baseline systems.
- Deep Learning--based Text Classification1,537
A comprehensive review of more than 150 deep learning--based models for text classification developed in recent years is provided, and their technical contributions, similarities, and strengths are discussed.
- Deep Reinforcement Learning for Dialogue Generation1,434
This work simulates dialogues between two virtual agents, using policy gradient methods to reward sequences that display three useful conversational properties: informativity, non-repetitive turns, coherence, and ease of answering.
- Multi-Task Deep Neural Networks for Natural Language Understanding1,376
A Multi-Task Deep Neural Network (MT-DNN) for learning representations across multiple natural language understanding (NLU) tasks that allows domain adaptation with substantially fewer in-domain labels than the pre-trained BERT representations.
- 1,188
- Large Language Models: A Survey1,136
This paper reviews some of the most prominent LLMs, including three popular LLM families (GPT, LLaMA, PaLM), and discusses their characteristics, contributions and limitations, and gives an overview of techniques developed to build, and augment LLMs.
- A Neural Network Approach to Context-Sensitive Generation of Conversational Responses915
A neural network architecture is used to address sparsity issues that arise when integrating contextual information into classic statistical models, allowing the system to take into account previous dialog utterances.
- 906
- 889
- Semantic Parsing via Staged Query Graph Generation: Question Answering with Knowledge Base847
This work proposes a novel semantic parsing framework for question answering using a knowledge base that leverages the knowledge base in an early stage to prune the search space and thus simplifies the semantic matching problem.
- The Design and Implementation of XiaoIce, an Empathetic Social Chatbot777
This article describes the development of Microsoft XiaoIce, the most popular social chatbot in the world, and shows how XiaoIce dynamically recognizes human feelings and states, understands user intent, and responds to user needs throughout long conversations.
- Neural Approaches to Conversational AI767
This tutorial surveys neural approaches to conversational AI that were developed in the last few years, and presents a review of state-of-the-art neural approaches, drawing the connection between neural approaches and traditional symbolic approaches.
- Learning semantic representations using convolutional neural networks for web search730
This paper presents a series of new latent semantic models based on a convolutional neural network to learn low-dimensional semantic vectors for search queries and Web documents that significantly outperforms other se-mantic models in retrieval performance.
- A Latent Semantic Model with Convolutional-Pooling Structure for Information Retrieval728
A new latent semantic model that incorporates a convolutional-pooling structure over word sequences to learn low-dimensional, semantic vector representations for search queries and Web documents is proposed.
- MIND: A Large-scale Dataset for News Recommendation718
This paper presents a large-scale dataset named MIND, constructed from the user click logs of Microsoft News, which contains 1 million users and more than 160k English news articles, each of which has rich textual content such as title, abstract and body.
- Scalable training of L 1 -regularized log-linear models671
This work presents an algorithm Orthant-Wise Limited-memory Quasi-Newton (OWL-QN), based on L-BFGS, that can efficiently optimize the L1-regularized log-likelihood of log-linear models with millions of parameters.
- A Knowledge-Grounded Neural Conversation Model595
This paper presents a novel, fully data-driven, and knowledge-grounded neural conversation model aimed at producing more contentful responses, generalizing the widely-used Sequence-to-Sequence (Seq2Seq) approach by conditioning responses on both conversation history and external “facts”, allowing the model to be versatile and applicable in an open-domain setting.
- Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback552
A LLM-Augmenter system, which augments a black-box LLM with a set of plug-and-play modules to significantly reduces ChatGPT's hallucinations without sacrificing the fluency and informativeness of its responses.
- Multi-Domain Joint Semantic Frame Parsing Using Bi-Directional RNN-LSTM490
Experimental results show the power of a holistic multi-domain, multi-task modeling approach to estimate complete semantic frames for all user utterances addressed to a conversational system over alternative methods based on single domain/task deep learning.
- Cyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishing473
A cyclical annealing schedule is proposed, which simply repeats the process of increasing \beta multiple times, and allows to learn more meaningful latent codes progressively by leveraging the results of previous learning cycles as warm re-restart.
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-13. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.