User profiles for Hang Li
Hang LiBytedance Research Verified email at bytedance.com Cited by 30284 |
Learning to rank: from pairwise approach to listwise approach
The paper is concerned with learning to rank, which is to construct a model or a function for
ranking objects. Learning to rank is useful for document retrieval, collaborative filtering, and …
ranking objects. Learning to rank is useful for document retrieval, collaborative filtering, and …
Ultrathin, molecular-sieving graphene oxide membranes for selective hydrogen separation
Ultrathin, molecular-sieving membranes have great potential to realize high-flux, high-selectivity
mixture separation at low energy cost. Current microporous membranes [pore size < 1 …
mixture separation at low energy cost. Current microporous membranes [pore size < 1 …
Incorporating copying mechanism in sequence-to-sequence learning
We address an important problem in sequence-to-sequence (Seq2Seq) learning referred to
as copying, in which certain segments in the input sequence are selectively replicated in the …
as copying, in which certain segments in the input sequence are selectively replicated in the …
Convolutional neural network architectures for matching natural language sentences
Semantic matching is of central importance to many natural language tasks\cite {bordes2014semantic,
RetrievalQA}. A successful matching algorithm needs to adequately model the …
RetrievalQA}. A successful matching algorithm needs to adequately model the …
Neural responding machine for short-text conversation
We propose Neural Responding Machine (NRM), a neural network-based response
generator for Short-Text Conversation. NRM takes the general encoder-decoder framework: it …
generator for Short-Text Conversation. NRM takes the general encoder-decoder framework: it …
Meta-sgd: Learning to learn quickly for few-shot learning
Few-shot learning is challenging for learning algorithms that learn each task in isolation and
from scratch. In contrast, meta-learning learns from many related tasks a meta-learner that …
from scratch. In contrast, meta-learning learns from many related tasks a meta-learner that …
Skin damage among health care workers managing coronavirus disease-2019
J Lan, Z Song, X Miao, H Li, Y Li, L Dong, J Yang… - Journal of the American …, 2020 - jaad.org
From January to February 2020, self-administered online questionnaires were distributed to
700 individuals, consisting of physicians and nurses who worked in the designated …
700 individuals, consisting of physicians and nurses who worked in the designated …
Adarank: a boosting algorithm for information retrieval
In this paper we address the issue of learning to rank for document retrieval. In the task, a
model is automatically created with some training data and then is utilized for ranking of …
model is automatically created with some training data and then is utilized for ranking of …
Consensus of Chinese experts on protection of skin and mucous membrane barrier for health‐care workers fighting against coronavirus disease 2019
…, C Ji, H Jin, W Lai, T Lei, L Li, L Li, R Li… - Dermatologic …, 2020 - Wiley Online Library
Health professions preventing and controlling Coronavirus Disease 2019 are prone to skin
and mucous membrane injury, which may cause acute and chronic dermatitis, secondary …
and mucous membrane injury, which may cause acute and chronic dermatitis, secondary …
Adapting ranking SVM to document retrieval
The paper is concerned with applying learning to rank to document retrieval. Ranking SVM
is a typical method of learning to rank. We point out that there are two factors one must …
is a typical method of learning to rank. We point out that there are two factors one must …