3 |
Guilt by Association: Emotion Intensities in Lexical Representations ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Guilt by Association: Emotion Intensities in Lexical Representations ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Leveraging Adversarial Training in Self-Learning for Cross-Lingual Text Classification ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Incorporating Pragmatic Reasoning Communication into Emergent Language ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Sentence Analogies: Exploring Linguistic Relationships and Regularities in Sentence Embeddings ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Sentence Analogies: Linguistic Regularities in Sentence Embeddings ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
1055 - Domain-Specific Sentiment Lexicons Induced from Labeled Documents ...
|
|
|
|
Abstract:
Sentiment analysis is an area of substantial relevance both in industry and in academia, including for instance in social studies. Although supervised learning algorithms have advanced considerably in recent years, in many settings it remains more practical to apply an unsupervised technique. The latter are oftentimes based on sentiment lexicons. However, existing sentiment lexicons reflect an abstract notion of polarity and do not do justice to the substantial differences of word polarities between different domains. In this work, we draw on a collection of domain-specific data to induce a set of 24 domain-specific sentiment lexicons. We rely on initial linear models to induce initial word intensity scores, and then train new deep models based on word vector representations to overcome the scarcity of the original seed data. Our analysis shows substantial differences between domains, which make domain-specific sentiment lexicons a promising form of lexical resource in downstream tasks, and the predicted ...
|
|
Keyword:
Information and Knowledge Engineering; Intelligent System; Natural Language Processing; Neural Network
|
|
URL: https://dx.doi.org/10.48448/ftvw-8821 https://underline.io/lecture/5695-1055---domain-specific-sentiment-lexicons-induced-from-labeled-documents
|
|
BASE
|
|
Hide details
|
|
12 |
Cross-Lingual Emotion Lexicon Induction using Representation Alignment in Low-Resource Settings ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
The Open Linguistics Working Group: Developing the Linguistic Linked Open Data Cloud ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
The Open Linguistics Working Group: Developing the Linguistic Linked Open Data Cloud
|
|
|
|
In: McCrae, John Philip; Chiarcos, Christian; Bond, Francis; Cimiano, Philipp; Declerck, Thierry; de Melo, Gerard; Gracia, Jorge; Hellmann, Sebastian; Klimek, Bettina; Moran, Steven; Osenova, Petya; Pareja-Lora, Antonio; Pool, Jonathan (2016). The Open Linguistics Working Group: Developing the Linguistic Linked Open Data Cloud. In: Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016), Portorož, Slovenia, 23 May 2016 - 28 May 2016. European Language Resources Association (ELRA), 2435-2441. (2016)
|
|
BASE
|
|
Show details
|
|
16 |
Graph-based Methods for Large-Scale Multilingual Knowledge Integration ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Graph-based Methods for Large-Scale Multilingual Knowledge Integration
|
|
de Melo, Gerard. - : Universität des Saarlandes, 2012. : Fakultät 6 - Naturwissenschaftlich-Technische Fakultät I. Fachrichtung 6.2 - Informatik, 2012
|
|
BASE
|
|
Show details
|
|
18 |
Graph-based Methods for Large-Scale Multilingual Knowledge Integration
|
|
de Melo, Gerard. - : Saarländische Universitäts- und Landesbibliothek, 2012
|
|
BASE
|
|
Show details
|
|
|
|