Named Entity Recognition (NER) performance often degrades rapidly when applied to target domains that differ from the texts observed during training. When in-domain labelled data is available, transfer learning techniques can be used to adapt existing NER models to the target domain. But what should one do when there is no hand-labelled data for the target domain? This paper presents a simple but powerful approach to learn NER models in the absence of labelled data through weak supervision. The approach relies on a broad spectrum of labelling functions to automatically annotate texts from the target domain. These annotations are then merged together using a hidden Markov model which captures the varying accuracies and confusions of the labelling functions. A sequence labelling model can finally be trained on the basis of this unified annotation. We evaluate the approach on two English datasets (CoNLL 2003 and news articles from Reuters and Bloomberg) and demonstrate an improvement of about 7 percentage points in entity-level F 1 scores compared to an out-of-domain neural NER model.

Structured sentiment analysis attempts to extract full opinion tuples from a text, but over time this task has been subdivided into smaller and smaller sub-tasks, e.g., target extraction or targeted polarity classification. We argue that this division has become counterproductive and propose a new unified framework to remedy the situation. We cast the structured sentiment problem as dependency graph parsing, where the nodes are spans of sentiment holders, targets and expressions, and the arcs are the relations between them. We perform experiments on five datasets in four languages (English, Norwegian, Basque, and Catalan) and show that this approach leads to strong improvements over state-of-the-art baselines. Our analysis shows that refining the sentiment graphs with syntactic dependency information further improves results.

There has been a good amount of progress in sentiment analysis over the past 10 years, including the proposal of new methods and the creation of benchmark datasets. In some papers, however, there is a tendency to compare models only on one or two datasets, either because of time restraints or because the model is tailored to a specific task. Accordingly, it is hard to understand how well a certain model generalizes across different tasks and datasets. In this paper, we contribute to this situation by comparing several models on six different benchmarks, which belong to different domains and additionally have different levels of granularity (binary, 3-class, 4-class and 5-class). We show that BiLSTMs perform well across datasets and that both LSTMs and Bi-LSTMs are particularly good at fine-grained sentiment tasks (i. e., with more than two classes). Incorporating sentiment information into word embeddings during training gives good results for datasets that are lexically similar to the training data. With our experiments, we contribute to a better understanding of the performance of different model architectures on different data sets. Consequently, we detect novel state-of-the-art results on the SenTube datasets.

There is a rich variety of data sets for sentiment analysis (viz., polarity and subjectivity classification). For the more challenging task of detecting discrete emotions following the definitions of Ekman and Plutchik, however, there are much fewer data sets, and notably no resources for the social media domain. This paper contributes to closing this gap by extending the SemEval 2016 stance and sentiment dataset with emotion annotation. We (a) analyse annotation reliability and annotation merging; (b) investigate the relation between emotion annotation and the other annotation layers (stance, sentiment); (c) report modelling results as a baseline for future work.

Sentiment analysis in low-resource languages suffers from a lack of annotated corpora to estimate high-performing models. Machine translation and bilingual word embeddings provide some relief through cross-lingual sentiment approaches. However, they either require large amounts of parallel data or do not sufficiently capture sentiment information. We introduce Bilingual Sentiment Embeddings (BLSE), which jointly represent sentiment information in a source and target language. This model only requires a small bilingual lexicon, a source-language corpus annotated for sentiment, and monolingual word embeddings for each language. We perform experiments on three language combinations (Spanish, Catalan, Basque) for sentencelevel cross-lingual sentiment classification and find that our model significantly outperforms state-of-the-art methods on four out of six experimental setups, as well as capturing complementary information to machine translation. Our analysis of the resulting embedding space provides evidence that it represents sentiment information in the resource-poor target language without any annotated data in that language.

Neural methods for SA have led to quantitative improvements over previous approaches, but these advances are not always accompanied with a thorough analysis of the qualitative differences. Therefore, it is not clear what outstanding conceptual challenges for sentiment analysis remain. In this work, we attempt to discover what challenges still prove a problem for sentiment classifiers for English and to provide a challenging dataset. We collect the subset of sentences that an (oracle) ensemble of state-of-the-art sentiment classifiers misclassify and then annotate them for 18 linguistic and paralinguistic phenomena, such as negation, sarcasm, modality, etc. 1 Finally, we provide a case study that demonstrates the usefulness of the dataset to probe the performance of a given sentiment classifier with respect to linguistic phenomena.

Hybrid quantum mechanical methods can assist in the interpretation and prediction of the electronic spectra of large molecular structures. In this work, we study the performance of the ONIOM (Our own N-layered Integrated molecular Orbital molecular Mechanics) hybrid method for the calculation of transition energies and oscillator strengths by embedding the core region in a field of fixed point charges. These charges introduce polarization effects from the substituent groups to the core region. We test various charge definitions, with particular attention to the issue of overpolarization near the boundary between layers. To minimize this issue, we fit the charges on the electrostatic potential of the entire structure in the presence of the link atoms used to cap dangling bonds. We propose two constrained fitting strategies: one that produces an average set of charges common to both model system calculations, EE(L1), and one that produces two separate sets of embedding charges, EE(L2). The results from our tests show that indeed electronic embedding with constrained-fitted charges tends to improve the performance of ONIOM compared to non-embedded calculations. However, the EE(L2) charges work best for transition energies, and the EE(L1) charges work best for oscillator strengths. This may be an indication that fixed point charges do not have enough flexibility to adapt to each system, and other effects (e.g., polarization of the embedding field) may be necessary. Published by AIP Publishing. [http://dx

Sentiment analysis is directly affected by compositional phenomena in language that act on the prior polarity of the words and phrases found in the text. Negation is the most prevalent of these phenomena, and in order to correctly predict sentiment, a classifier must be able to identify negation and disentangle the effect that its scope has on the final polarity of a text. This paper proposes a multi-task approach to explicitly incorporate information about negation in sentiment analysis, which we show outperforms learning negation implicitly in an end-to-end manner. We describe our approach, a cascading and hierarchical neural architecture with selective sharing of Long Short-term Memory layers, and show that explicitly training the model with negation as an auxiliary task helps improve the main task of sentiment analysis. The effect is demonstrated across several different standard English-language data sets for both tasks, and we analyze several aspects of our system related to its performance, varying types and amounts of input data and different multi-task setups.