DE eng

Search in the Catalogues and Directories

Hits 1 – 17 of 17

1
Enhancing Descriptive Image Captioning with Natural Language Inference ...
Abstract: Read paper: https://www.aclanthology.org/2021.acl-short.36 Abstract: Generating \textit{descriptive} sentences that convey non-trivial, detailed, and salient information about images is an important goal of image captioning. In this paper we propose a novel approach to encourage captioning models to produce more detailed captions using natural language inference, based on the motivation that, among different captions of an image, descriptive captions are more likely to entail less descriptive captions. Specifically, we construct directed inference graphs for reference captions based on natural language inference. A PageRank algorithm is then employed to estimate the descriptiveness score of each node. Built on that, we use reference sampling and weighted designated rewards to guide captioning to generate descriptive captions. The results on MSCOCO show that the proposed method outperforms the baselines significantly on a wide range of conventional and descriptiveness-related evaluation metrics. ...
Keyword: Computational Linguistics; Condensed Matter Physics; Deep Learning; Electromagnetism; FOS Physical sciences; Information and Knowledge Engineering; Neural Network; Semantics
URL: https://underline.io/lecture/26017-enhancing-descriptive-image-captioning-with-natural-language-inference
https://dx.doi.org/10.48448/txr6-qt98
BASE
Hide details
2
Detecting Speaker Personas from Conversational Texts ...
BASE
Show details
3
Unsupervised Conversation Disentanglement through Co-Training ...
BASE
Show details
4
Preview, Attend and Review: Schema-Aware Curriculum Learning for Multi-Domain Dialogue State Tracking ...
BASE
Show details
5
SemEval-2021 Task 12: Learning with Disagreements
Uma, Alexandra; Fornaciari, Tommaso; Dumitrache, Anca. - : Association for Computational Linguistics, 2021
BASE
Show details
6
Exploring End-to-End Differentiable Natural Logic Modeling ...
BASE
Show details
7
SemEval-2020 Task 5: Counterfactual Recognition ...
BASE
Show details
8
SemEval-2020 Task 2: Predicting multilingual and cross-lingual (graded) lexical entailment
Glavaš, Goran; Vulić, Ivan; Korhonen, Anna. - : Association for Computational Linguistics, 2020
BASE
Show details
9
Knowledge graph and semantic computing : knowledge computing and language understanding : 4th China Conference, CCKS 2019, Hangzhou, China, August 24-27, 2019 : revised selected papers
Zhu, Xiaoyan (Herausgeber); Qin, Bing (Herausgeber); Qian, LongHua (Herausgeber). - Singapore : Springer, 2019
BLLDB
UB Frankfurt Linguistik
Show details
10
Exploring Unsupervised Pretraining and Sentence Structure Modelling for Winograd Schema Challenge ...
BASE
Show details
11
Learning Cross-modal Context Graph for Visual Grounding ...
Liu, Yongfei; Wan, Bo; Zhu, Xiaodan. - : arXiv, 2019
BASE
Show details
12
Logographic Subword Model for Neural Machine Translation ...
Fang, Yihao; Zheng, Rong; Zhu, Xiaodan. - : arXiv, 2018
BASE
Show details
13
Commonsense Knowledge Enhanced Embeddings for Solving Pronoun Disambiguation Problems in Winograd Schema Challenge ...
Liu, Quan; Jiang, Hui; Ling, Zhen-Hua. - : arXiv, 2016
BASE
Show details
14
NRC-Canada: Building the State-of-the-Art in Sentiment Analysis of Tweets ...
BASE
Show details
15
Summarizing Spoken Documents Through Utterance Selection
Zhu, Xiaodan. - 2010
BASE
Show details
16
Analysis of Polarity Information in Medical Text
Niu, Yun; Zhu, Xiaodan; Li, Jianhua. - : American Medical Informatics Association, 2005
BASE
Show details
17
Summarizing Spoken Documents Through Utterance Selection
Zhu, Xiaodan. - NO_RESTRICTION
BASE
Show details

Catalogues
1
0
0
0
0
0
0
Bibliographies
1
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
16
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern