10.9k citations
- Max Planck SocietyDE201 papers
- Heidelberg UniversityDE53 papers
- Centre National de la Recherche ScientifiqueFR47 papers
- Jagiellonian UniversityPL44 papers
- University of AmsterdamNL43 papers
- Charles UniversityCZ40 papers
- Humboldt-Universität zu BerlinDE40 papers
- Polish Academy of SciencesPL40 papers
- European Organization for Nuclear ResearchCH38 papers
- Institut National de Physique Nucléaire et de Physique des ParticulesFR38 papers
- University of BirminghamGB37 papers
- University of OxfordGB37 papers
9 papers · 1 filter
PASTE: A Tagging-Free Decoding Framework Using Pointer Networks for Aspect Sentiment Triplet Extraction
Rajdeep Mukherjee, Tapas Nayak, Yash Butala +2
Aspect Sentiment Triplet Extraction (ASTE) deals with extracting opinion triplets, consisting of an opinion target or aspect, its associated sentiment, and the corresponding opinio…
SocialVisTUM: An Interactive Visualization Toolkit for Correlated Neural Topic Models on Social Media Opinion Mining
Gerhard Johann Hagerer, Martin Kirchhoff, Hannah Danner +5
Recent research in opinion mining proposed word embedding-based topic modeling methods that provide superior coherence compared to traditional topic modeling. In this paper, we dem…
Preventing Author Profiling through Zero-Shot Multilingual Back-Translation
David Ifeoluwa Adelani, Miaoran Zhang, Xiaoyu Shen +3
Documents as short as a single sentence may inadvertently reveal sensitive information about their authors, including e.g. their gender or ethnicity. Style transfer is an effective…
Question Answering over Electronic Devices: A New Benchmark Dataset and a Multi-Task Learning based QA Framework
Abhilash Nandy, Soumya Sharma, Shubham Maddhashiya +3
Answering questions asked from instructional corpora such as E-manuals, recipe books, etc., has been far less studied than open-domain factoid context-based question answering. Thi…
To Share or not to Share: Predicting Sets of Sources for Model Transfer Learning
Lukas Lange, Jannik Strötgen, Heike Adel +1
In low-resource settings, model transfer can help to overcome a lack of labeled data for many tasks and domains. However, predicting useful transfer sources is a challenging proble…
FAME: Feature-Based Adversarial Meta-Embeddings for Robust Input Representations
Lukas Lange, Heike Adel, Jannik Strötgen +1
Combining several embeddings typically improves performance in downstream tasks as different embeddings encode different information. It has been shown that even models using embed…