activity
20162019
most citedERNIE: Enhanced Language Representation with Informative Entities

135 citations · 159 across the 4 of their papers we have counts for

collaborators

5 papers

cs.CL20193 cited

Decomposable Neural Paraphrase Generation

Zichao Li, Xin Jiang, Lifeng Shang +1

Paraphrasing exists at different granularity levels, such as lexical level, phrasal level and sentential level. This paper presents Decomposable Neural Paraphrase Generator (DNPG),…

cs.CL2019135 cited

ERNIE: Enhanced Language Representation with Informative Entities

Zhengyan Zhang, Xu Han, Zhiyuan Liu +3

Neural language representation models such as BERT pre-trained on large-scale corpora can well capture rich semantic patterns from plain text, and be fine-tuned to consistently imp…

cs.CL201917 cited

Triple-to-Text: Converting RDF Triples into High-Quality Natural Languages via Optimizing an Inverse KL Divergence

Yaoming Zhu, Juncheng Wan, Zhiming Zhou +5

Knowledge base is one of the main forms to represent information in a structured way. A knowledge base typically consists of Resource Description Frameworks (RDF) triples which des…

cs.CL20174 cited

Affective Neural Response Generation

Nabiha Asghar, Pascal Poupart, Jesse Hoey +2

Existing neural conversational models process natural language primarily on a lexico-syntactic level, thereby ignoring one of the most crucial components of human-to-human dialogue…

cs.IR2016

Incorporating Semantic Knowledge into Latent Matching Model in Search

Shuxin Wang, Xin Jiang, Hang Li +2

The relevance between a query and a document in search can be represented as matching degree between the two objects. Latent space models have been proven to be effective for the t…