We present the ongoing NorLM initiative to support the creation and use of very large contextualised language models for Norwegian (and in principle other Nordic languages), including a ready-to-use software environment, as well as an experience report for data preparation and training. This paper introduces the first large-scale monolingual language models for Norwegian, based on both the ELMo and BERT frameworks. In addition to detailing the training process, we present contrastive benchmark results on a suite of NLP tasks for Norwegian. For additional background and access to the data, models, and software, please see : http://norlm.nlpl.eu

Multilingual pretrained language models are rapidly gaining popularity in NLP systems for non-English languages. Most of these models feature an important corpus sampling step in the process of accumulating training data in different languages, to ensure that the signal from better resourced languages does not drown out poorly resourced ones. In this study, we train multiple multilingual recurrent language models, based on the ELMo architecture, and analyse both the effect of varying corpus size ratios on downstream performance, as well as the performance difference between monolingual models for each language, and broader multilingual language models. As part of this effort, we also make these trained models available for public use.

Fine-grained sentiment analysis attempts to extract sentiment holders, targets and polar expressions and resolve the relationship between them, but progress has been hampered by the difficulty of annotation. Targeted sentiment analysis, on the other hand, is a more narrow task, focusing on extracting sentiment targets and classifying their polarity. In this paper, we explore whether incorporating holder and expression information can improve target extraction and classification and perform experiments on eight English datasets. We conclude that jointly predicting target and polarity BIO labels improves target extraction, and that augmenting the input text with gold expressions generally improves targeted polarity classification. This highlights the potential importance of annotating expressions for fine-grained sentiment datasets. At the same time, our results show that performance of current models for predicting polar expressions is poor, hampering the benefit of this information in practice.

We here introduce NoReC_fine, a dataset for fine-grained sentiment analysis in Norwegian, annotated with respect to polar expressions, targets and holders of opinion. The underlying texts are taken from a corpus of professionally authored reviews from multiple news-sources and across a wide variety of domains, including literature, games, music, products, movies and more. We here present a detailed description of this annotation effort. We provide an overview of the developed annotation guidelines, illustrated with examples and present an analysis of inter-annotator agreement. We also report the first experimental results on the dataset, intended as a preliminary benchmark for further experiments.

This paper extends the task of probing sentence representations for linguistic insight in a multilingual domain. In doing so, we make two contributions : first, we provide datasets for multilingual probing, derived from Wikipedia, in five languages, viz. English, French, German, Spanish and Russian. Second, we evaluate six sentence encoders for each language, each trained by mapping sentence representations to English sentence representations, using sentences in a parallel corpus. We discover that cross-lingually mapped representations are often better at retaining certain linguistic information than representations derived from English encoders trained on natural language inference (NLI) as a downstream task.

In this paper we present first results for the task of Automated Essay Scoring for Norwegian learner language. We analyze a number of properties of this task experimentally and assess (i) the formulation of the task as either regression or classification, (ii) the use of various non-neural and neural machine learning architectures with various types of input representations, and (iii) applying multi-task learning for joint prediction of essay scoring and native language identification. We find that a GRU-based attention model trained in a single-task setting performs best at the AES task.

We extend the well-known word analogy task to a one-to-X formulation, including one-to-none cases, when no correct answer exists. The task is cast as a relation discovery problem and applied to historical armed conflicts datasets, attempting to predict new relations of type ‘location : armed-group’ based on data about past events. As the source of semantic information, we use diachronic word embedding models trained on English news texts. A simple technique to improve diachronic performance in such task is demonstrated, using a threshold based on a function of cosine distance to decrease the number of false positives ; this approach is shown to be beneficial on two different corpora. Finally, we publish a ready-to-use test set for one-to-X analogy evaluation on historical armed conflicts data.

Neural methods for sentiment analysis 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. 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.

Recent years have witnessed a surge of publications aimed at tracing temporal changes in lexical semantics using distributional methods, particularly prediction-based word embedding models. However, this vein of research lacks the cohesion, common terminology and shared practices of more established areas of natural language processing. In this paper, we survey the current state of academic research related to diachronic word embeddings and semantic shifts detection. We start with discussing the notion of semantic shifts, and then continue with an overview of the existing methods for tracing such time-related shifts with word embedding models. We propose several axes along which these methods can be compared, and outline the main challenges before this emerging subfield of NLP, as well as prospects and possible applications.

This article presents the SIRIUS-LTG-UiO system for the SemEval 2018 Task 7 on Semantic Relation Extraction and Classification in Scientific Papers. First we extract the shortest dependency path (sdp) between two entities, then we introduce a convolutional neural network (CNN) which takes the shortest dependency path embeddings as input and performs relation classification with differing objectives for each subtask of the shared task. This approach achieved overall F1 scores of 76.7 and 83.2 for relation classification on clean and noisy data, respectively. Furthermore, for combined relation extraction and classification on clean data, it obtained F1 scores of 37.4 and 33.6 for each phase. Our system ranks 3rd in all three sub-tasks of the shared task.

We investigate the use of different syntactic dependency representations in a neural relation classification task and compare the CoNLL, Stanford Basic and Universal Dependencies schemes. We further compare with a syntax-agnostic approach and perform an error analysis in order to gain a better understanding of the results.

This article presents the SIRIUS-LTG system for the Fact Extraction and VERification (FEVER) Shared Task. It consists of three components : 1) Wikipedia Page Retrieval : First we extract the entities in the claim, then we find potential Wikipedia URI candidates for each of the entities using a SPARQL query over DBpedia 2) Sentence selection : We investigate various techniques i.e. Smooth Inverse Frequency (SIF), Word Mover’s Distance (WMD), Soft-Cosine Similarity, Cosine similarity with unigram Term Frequency Inverse Document Frequency (TF-IDF) to rank sentences by their similarity to the claim. 3) Textual Entailment : We compare three models for the task of claim classification. We apply a Decomposable Attention (DA) model (Parikh et al., 2016), a Decomposed Graph Entailment (DGE) model (Khot et al., 2018) and a Gradient-Boosted Decision Trees (TalosTree) model (Sean et al., 2017) for this task. The experiments show that the pipeline with simple Cosine Similarity using TFIDF in sentence selection along with DA model as labelling model achieves the best results on the development set (F1 evidence : 32.17, label accuracy : 59.61 and FEVER score : 0.3778). Furthermore, it obtains 30.19, 48.87 and 36.55 in terms of F1 evidence, label accuracy and FEVER score, respectively, on the test set. Our system ranks 15th among 23 participants in the shared task prior to any human-evaluation of the evidence.Wikipedia Page Retrieval: First we extract the entities in the claim, then we find potential Wikipedia URI candidates for each of the entities using a SPARQL query over DBpedia 2) Sentence selection: We investigate various techniques i.e. Smooth Inverse Frequency (SIF), Word Mover’s Distance (WMD), Soft-Cosine Similarity, Cosine similarity with unigram Term Frequency Inverse Document Frequency (TF-IDF) to rank sentences by their similarity to the claim. 3) Textual Entailment: We compare three models for the task of claim classification. We apply a Decomposable Attention (DA) model (Parikh et al., 2016), a Decomposed Graph Entailment (DGE) model (Khot et al., 2018) and a Gradient-Boosted Decision Trees (TalosTree) model (Sean et al., 2017) for this task. The experiments show that the pipeline with simple Cosine Similarity using TFIDF in sentence selection along with DA model as labelling model achieves the best results on the development set (F1 evidence: 32.17, label accuracy: 59.61 and FEVER score: 0.3778). Furthermore, it obtains 30.19, 48.87 and 36.55 in terms of F1 evidence, label accuracy and FEVER score, respectively, on the test set. Our system ranks 15th among 23 participants in the shared task prior to any human-evaluation of the evidence.

In this article, we describe the development of annotation guidelines for family history information in Norwegian clinical text. We make use of incrementally developed synthetic clinical text describing patients’ family history relating to cases of cardiac disease and present a general methodology which integrates the synthetically produced clinical statements and guideline development. We analyze inter-annotator agreement based on the developed guidelines and present results from experiments aimed at evaluating the validity and applicability of the annotated corpus using machine learning techniques. The resulting annotated corpus contains 477 sentences and 6030 tokens. Both the annotation guidelines and the annotated corpus are made freely available and as such constitutes the first publicly available resource of Norwegian clinical text.

Although treebanks annotated according to the guidelines of Universal Dependencies (UD) now exist for many languages, the goal of annotating the same phenomena in a cross-linguistically consistent fashion is not always met. In this paper, we investigate one phenomenon where we believe such consistency is lacking, namely expletive elements. Such elements occupy a position that is structurally associated with a core argument (or sometimes an oblique dependent), yet are non-referential and semantically void. Many UD treebanks identify at least some elements as expletive, but the range of phenomena differs between treebanks, even for closely related languages, and sometimes even for different treebanks for the same language. In this paper, we present criteria for identifying expletives that are applicable across languages and compatible with the goals of UD, give an overview of expletives as found in current UD treebanks, and present recommendations for the annotation of expletives so that more consistent annotation can be achieved in future releases.

This paper presents an open-source toolkit for negation detection. It identifies negation cues and their corresponding scope in either raw or parsed text using maximum-margin classification. The system design draws on best practice from the existing literature on negation detection, aiming for a simple and portable system that still achieves competitive performance. Pre-trained models and experimental results are provided for English.

This paper deals with using word embedding models to trace the temporal dynamics of semantic relations between pairs of words. The set-up is similar to the well-known analogies task, but expanded with a time dimension. To this end, we apply incremental updating of the models with new training texts, including incremental vocabulary expansion, coupled with learned transformation matrices that let us map between members of the relation. The proposed approach is evaluated on the task of predicting insurgent armed groups based on geographical locations. The gold standard data for the time span 19942010 is extracted from the UCDP Armed Conflicts dataset. The results show that the method is feasible and outperforms the baselines, but also that important work still remains to be done.