activity
20152023
most citedA Structured Self-attentive Sentence Embedding

1.5k citations · 1.7k across the 19 of their papers we have counts for

collaborators
Showing 2020 · cs.CLShow all

7 papers · 2 filters

cs.CL2020★ 6 cited

Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-Training

Peng Shi, Patrick Ng, Zhiguo Wang +5

Most recently, there has been significant interest in learning contextual representations for various NLP tasks, by leveraging large scale text corpora to train large neural langua…

cs.CL2020

Answering Ambiguous Questions through Generative Evidence Fusion and Round-Trip Prediction

Yifan Gao, Henghui Zhu, Patrick Ng +7

In open-domain question answering, questions are highly likely to be ambiguous because users may not know the scope of relevant topics when formulating them. Therefore, a system ne…

cs.CL2020

DualTKB: A Dual Learning Bridge between Text and Knowledge Base

Pierre L. Dognin, Igor Melnyk, Inkit Padhi +2

In this work, we present a dual learning approach for unsupervised text to path and path to text transfers in Commonsense Knowledge Bases (KBs). We investigate the impact of weak s…

cs.CL2020

End-to-End Synthetic Data Generation for Domain Adaptation of Question Answering Systems

Siamak Shakeri, Cicero Nogueira dos Santos, Henry Zhu +5

We propose an end-to-end approach for synthetic QA data generation. Our model comprises a single transformer-based encoder-decoder network that is trained end-to-end to generate bo…

cs.CL2020

Beyond [CLS] through Ranking by Generation

Cicero Nogueira dos Santos, Xiaofei Ma, Ramesh Nallapati +2

Generative models for Information Retrieval, where ranking of documents is viewed as the task of generating a query from a document's language model, were very successful in variou…

cs.CL2020★ 3 cited

Augmented Natural Language for Generative Sequence Labeling

Ben Athiwaratkun, Cicero Nogueira dos Santos, Jason Krone +1

We propose a generative framework for joint sequence labeling and sentence-level classification. Our model performs multiple sequence labeling tasks at once using a single, shared…