activity
20172023
most citedMultilingual Universal Sentence Encoder for Semantic Retrieval

67 citations · 120 across the 13 of their papers we have counts for

collaborators
Showing 2018 · cs.CLShow all

7 papers · 2 filters

cs.CL2018

Learning Cross-Lingual Sentence Representations via a Multi-task Dual-Encoder Model

Muthuraman Chidambaram, Yinfei Yang, Daniel Cer +4

A significant roadblock in multilingual neural language modeling is the lack of labeled non-English data. One potential method for overcoming this issue is learning cross-lingual t…

cs.CL2018

Review Helpfulness Prediction with Embedding-Gated CNN

Cen Chen, Minghui Qiu, Yinfei Yang +4

Product reviews, in the form of texts dominantly, significantly help consumers finalize their purchasing decisions. Thus, it is important for e-commerce companies to predict review…

cs.CL2018

Effective Parallel Corpus Mining using Bilingual Sentence Embeddings

Mandy Guo, Qinlan Shen, Yinfei Yang +8

This paper presents an effective approach for parallel corpus mining using bilingual sentence embeddings. Our embedding models are trained to produce similar representations exclus…

cs.CL2018

A Corpus with Multi-Level Annotations of Patients, Interventions and Outcomes to Support Language Processing for Medical Literature

Benjamin Nye, Junyi Jessy Li, Roma Patel +4

We present a corpus of 5,000 richly annotated abstracts of medical articles describing clinical randomized controlled trials. Annotations include demarcations of text spans that de…

cs.CL2018

Syntactic Patterns Improve Information Extraction for Medical Search

Roma Patel, Yinfei Yang, Iain Marshall +2

Medical professionals search the published literature by specifying the type of patients, the medical intervention(s) and the outcome measure(s) of interest. In this paper we demon…

cs.CL2018

Learning Semantic Textual Similarity from Conversations

Yinfei Yang, Steve Yuan, Daniel Cer +7

We present a novel approach to learn representations for sentence-level semantic similarity using conversational data. Our method trains an unsupervised model to predict conversati…