1 |
Three-Module Modeling For End-to-End Spoken Language Understanding Using Pre-trained DNN-HMM-Based Acoustic-Phonetic Model ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Tonsilla subrostrum Zhang & Irfan & Wang & Zhang 2022, sp. nov. ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Tonsilla subrostrum Zhang & Irfan & Wang & Zhang 2022, sp. nov. ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
DYPLOC: Dynamic Planning of Content Using Mixed Language Models for Text Generation ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
CLIFF: Contrastive Learning for Improving Faithfulness and Factuality in Abstractive Summarization ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Controllable Open-ended Question Generation with A New Question Type Ontology ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Serratacosa medogensis Wang & Peng & Zhang 2021, gen. et sp. nov. ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Serratacosa medogensis Wang & Peng & Zhang 2021, gen. et sp. nov. ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Ectatosticta pingwuensis Wang & Zhao & Irfan & Zhang 2021, sp. nov. ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Ectatosticta pingwuensis Wang & Zhao & Irfan & Zhang 2021, sp. nov. ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Ectatosticta shennongjiaensis Wang & Zhao & Irfan & Zhang 2021, sp. nov. ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Ectatosticta shennongjiaensis Wang & Zhao & Irfan & Zhang 2021, sp. nov. ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Inference Time Style Control for Summarization ...
|
|
|
|
Abstract:
Read the paper on the folowing link: https://www.aclweb.org/anthology/2021.naacl-main.476/ Abstract: How to generate summaries of different styles without requiring corpora in the target styles, or training separate models? We present two novel methods that can be deployed during summary decoding on any pre-trained Transformer-based summarization model. (1) Decoder state adjustment instantly modifies decoder final states with externally trained style scorers, to iteratively refine the output against a target style. (2) Word unit prediction constrains the word usage to impose strong lexical control during generation. In experiments of summarizing with simplicity control, automatic evaluation and human judges both find our models producing outputs in simpler languages while still informative. We also generate news headlines with various ideological leanings, which can be distinguished by humans with a reasonable probability. ...
|
|
Keyword:
Artificial Intelligence; Computer Science and Engineering; Intelligent System; Natural Language Processing
|
|
URL: https://underline.io/lecture/19779-inference-time-style-control-for-summarization https://dx.doi.org/10.48448/jxt2-n591
|
|
BASE
|
|
Hide details
|
|
17 |
Variation in Surgeon Proficiency Scores and Association With Digit Replantation Outcomes
|
|
|
|
In: JAMA Netw Open (2021)
|
|
BASE
|
|
Show details
|
|
18 |
Pulmonary Rehabilitation Programmes Within Three Days of Hospitalization for Acute Exacerbation of Chronic Obstructive Pulmonary Disease: A Systematic Review and Meta-Analysis
|
|
|
|
In: Int J Chron Obstruct Pulmon Dis (2021)
|
|
BASE
|
|
Show details
|
|
|
|