1 |
Are we summarizing the right way? : a survey of dialogue summarization data sets ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
ZHAW-CAI : ensemble method for Swiss German speech to Standard German text ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
ZHAW-InIT at GermEval 2020 task 4 : low-resource speech-to-text ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Spot The Bot : a robust and efficient framework for the evaluation of conversational dialogue systems ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
DoQA : accessing domain-specific FAQs via conversational QA ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
A methodology for creating question answering corpora using inverse data annotation ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
SwissNLP : the Swiss association for natural language processing position paper at Computational Linguistics European nAtional and Regional Associations Meeting (CLEARA-MEET) at LREC ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Overview of the GermEval 2020 shared task on Swiss German language identification ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Correlating Twitter Language with Community-Level Health Outcomes
|
|
|
|
In: http://infoscience.epfl.ch/record/278185 (2020)
|
|
BASE
|
|
Show details
|
|
12 |
TwistBytes - identification of Cuneiform languages and German dialects at VarDial 2019 ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Towards integration of statistical hypothesis tests into deep neural networks ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Twist Bytes : German dialect identification with data mining optimization ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
spMMMP at GermEval 2018 Shared Task: Classification of Offensive Content in Tweets using Convolutional Neural Networks and Gated Recurrent Units
|
|
|
|
In: http://hw.oeaw.ac.at/8435-5 (2018)
|
|
BASE
|
|
Show details
|
|
16 |
Syntactic manipulation for generating more diverse and interesting texts ...
|
|
|
|
Abstract:
Natural Language Generation plays an important role in the domain of dialogue systems as it determines how users perceive the system. Recently, deep-learning based systems have been proposed to tackle this task, as they generalize better and require less amounts of manual effort to implement them for new domains. However, deep learning systems usually adapt a very homogeneous sounding writing style which expresses little variation. In this work, we present our system for Natural Language Generation where we control various aspects of the surface realization in order to increase the lexical variability of the utterances, such that they sound more diverse and interesting. For this, we use a Semantically Controlled Long Short-term Memory Network (SCLSTM), and apply its specialized cell to control various syntactic features of the generated texts. We present an in-depth human evaluation where we show the effects of these surface manipulation on the perception of potential users. ...
|
|
Keyword:
006 Spezielle Computerverfahren; 410.285 Computerlinguistik; Deep neural networks; Natural language generation; Natural language processing; Neural networks; Text embellishment
|
|
URL: https://dx.doi.org/10.21256/zhaw-4875 https://digitalcollection.zhaw.ch/handle/11475/13074
|
|
BASE
|
|
Hide details
|
|
17 |
SwissAlps at SemEval-2017 Task 3 : attention-based convolutional neural network for community question answering ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
TopicThunder at SemEval-2017 Task 4 : sentiment classification using a convolutional neural network with distant supervision ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Potential and limitations of cross-domain sentiment classification ...
|
|
|
|
BASE
|
|
Show details
|
|
20 |
A Twitter corpus and benchmark resources for german sentiment analysis ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|