We present the HPLT (High Performance Language Technologies) language resources, a new massive multilingual dataset including both monolingual and bilingual corpora extracted from CommonCrawl and previously unused web crawls from the Internet Archive. We describe our methods for data acquisition, management and processing of large corpora, which rely on open-source software tools and high-performance computing. Our monolingual collection focuses on low- to medium-resourced languages and covers 75 languages and a total of ≈ 5.6 trillion word tokens de-duplicated on the document level. Our English-centric parallel corpus is derived from its monolingual counterpart and covers 18 language pairs and more than 96 million aligned sentence pairs with roughly 1.4 billion English tokens. The HPLT language resources are one of the largest open text corpora ever released, providing a great resource for language modeling and machine translation training. We publicly release the corpora, the software, and the tools used in this work.

We present a dataset of word usage graphs (WUGs), where the existing WUGs for multiple languages are enriched with cluster labels functioning as sense definitions. They are generated from scratch by fine-tuned encoder-decoder language models. The conducted human evaluation has shown that these definitions match the existing clusters in WUGs better than the definitions chosen from WordNet by two baseline systems. At the same time, the method is straightforward to use and easy to extend to new languages. The resulting enriched datasets can be extremely helpful for moving on to explainable semantic change modeling.

Foundational large language models (LLMs) can be instruction-tuned to perform open-domain question answering, facilitating applications like chat assistants. While such efforts are often carried out in a single language, we empirically analyze cost-efficient strategies for multilingual scenarios. Our study employs the Alpaca dataset and machine translations of it to form multilingual data, which is then used to tune LLMs through either low-rank adaptation or full-parameter training. Under a controlled computation budget, comparisons show that multilingual tuning is on par or better than tuning a model for each language. Furthermore, multilingual tuning with downsampled data can be as powerful and more robust. Our findings serve as a guide for expanding language support through instruction tuning.

We present NorBench: a streamlined suite of NLP tasks and probes for evaluating Norwegian language models (LMs) on standardized data splits and evaluation metrics. We also introduce a range of new Norwegian language models (both encoder and encoder-decoder based). Finally, we compare and analyze their performance, along with other existing LMs, across the different benchmark tests of NorBench.

While modern masked language models (LMs) are trained on ever larger corpora, we here explore the effects of down-scaling training to a modestly-sized but representative, well-balanced, and publicly available English text source – the British National Corpus. We show that pre-training on this carefully curated corpus can reach better performance than the original BERT model. We argue that this type of corpora has great potential as a language modeling benchmark. To showcase this potential, we present fair, reproducible and data-efficient comparative studies of LMs, in which we evaluate several training objectives and model architectures and replicate previous empirical results in a systematic way. We propose an optimized LM architecture called LTG-BERT.

We propose using automatically generated natural language definitions of contextualised word usages as interpretable word and word sense representations. Given a collection of usage examples for a target word, and the corresponding data-driven usage clusters (i.e., word senses), a definition is generated for each usage with a specialised Flan-T5 language model, and the most prototypical definition in a usage cluster is chosen as the sense label. We demonstrate how the resulting sense labels can make existing approaches to semantic change analysis more interpretable, and how they can allow users — historical linguists, lexicographers, or social scientists — to explore and intuitively explain diachronic trajectories of word meaning. Semantic change analysis is only one of many possible applications of the ‘definitions as representations’ paradigm. Beyond being human-readable, contextualised definitions also outperform token or usage sentence embeddings in word-in-context semantic similarity judgements, making them a new promising type of lexical representation for NLP.

Morphological and syntactic changes in word usage — as captured, e.g., by grammatical profiles — have been shown to be good predictors of a word’s meaning change. In this work, we explore whether large pre-trained contextualised language models, a common tool for lexical semantic change detection, are sensitive to such morphosyntactic changes. To this end, we first compare the performance of grammatical profiles against that of a multilingual neural language model (XLM-R) on 10 datasets, covering 7 languages, and then combine the two approaches in ensembles to assess their complementarity. Our results show that ensembling grammatical profiles with XLM-R improves semantic change detection performance for most datasets and languages. This indicates that language models do not fully cover the fine-grained morphological and syntactic signals that are explicitly represented in grammatical profiles. An interesting exception are the test sets where the time spans under analysis are much longer than the time gap between them (for example, century-long spans with a one-year gap between them). Morphosyntactic change is slow so grammatical profiles do not detect in such cases. In contrast, language models, thanks to their access to lexical information, are able to detect fast topical changes.

We describe NorDiaChange: the first diachronic semantic change dataset for Norwegian. NorDiaChange comprises two novel subsets, covering about 80 Norwegian nouns manually annotated with graded semantic change over time. Both datasets follow the same annotation procedure and can be used interchangeably as train and test splits for each other. NorDiaChange covers the time periods related to pre- and post-war events, oil and gas discovery in Norway, and technological developments. The annotation was done using the DURel framework and two large historical Norwegian corpora. NorDiaChange is published in full under a permissive licence, complete with raw annotation data and inferred diachronic word usage graphs (DWUGs).

In this paper, we introduce the first SemEval shared task on Structured Sentiment Analysis, for which participants are required to predict all sentiment graphs in a text, where a single sentiment graph is composed of a sentiment holder, target, expression and polarity. This new shared task includes two subtracks (monolingual and cross-lingual) with seven datasets available in five languages, namely Norwegian, Catalan, Basque, Spanish and English. Participants submitted their predictions on a held-out test set and were evaluated on Sentiment Graph F1 . Overall, the task received over 200 submissions from 32 participating teams. We present the results of the 15 teams that provided system descriptions and our own expanded analysis of the test predictions.

We present a qualitative analysis of the (potentially erroneous) outputs of contextualized embedding-based methods for detecting diachronic semantic change. First, we introduce an ensemble method outperforming previously described contextualized approaches. This method is used as a basis for an in-depth analysis of the degrees of semantic change predicted for English words across 5 decades. Our findings show that contextualized methods can often predict high change scores for words which are not undergoing any real diachronic semantic shift in the lexicographic sense of the term (or at least the status of these shifts is questionable). Such challenging cases are discussed in detail with examples, and their linguistic categorization is proposed. Our conclusion is that pre-trained contextualized language models are prone to confound changes in lexicographic senses and changes in contextual variance, which naturally stem from their distributional nature, but is different from the types of issues observed in methods based on static embeddings. Additionally, they often merge together syntactic and semantic aspects of lexical entities. We propose a range of possible future solutions to these issues.

We present RuDSI, a new benchmark for word sense induction (WSI) in Russian. The dataset was created using manual annotation and semi-automatic clustering of Word Usage Graphs (WUGs). RuDSI is completely data-driven (based on texts from Russian National Corpus), with no external word senses imposed on annotators. We present and analyze RuDSI, describe our annotation workflow, show how graph clustering parameters affect the dataset, report the performance that several baseline WSI methods obtain on RuDSI and discuss possibilities for improving these scores.

We present a manually annotated lexical semantic change dataset for Russian: RuShiftEval. Its novelty is ensured by a single set of target words annotated for their diachronic semantic shifts across three time periods, while the previous work either used only two time periods, or different sets of target words. The paper describes the composition and annotation procedure for the dataset. In addition, it is shown how the ternary nature of RuShiftEval allows to trace specific diachronic trajectories: ‘changed at a particular time period and stable afterwards’ or ‘was changing throughout all time periods’. Based on the analysis of the submissions to the recent shared task on semantic change detection for Russian, we argue that correctly identifying such trajectories can be an interesting sub-task itself.

Semantics, morphology and syntax are strongly interdependent. However, the majority of computational methods for semantic change detection use distributional word representations which encode mostly semantics. We investigate an alternative method, grammatical profiling, based entirely on changes in the morphosyntactic behaviour of words. We demonstrate that it can be used for semantic change detection and even outperforms some distributional semantic methods. We present an in-depth qualitative and quantitative analysis of the predictions made by our grammatical profiling system, showing that they are plausible and interpretable.

We describe a new addition to the WebVectors toolkit which is used to serve word embedding models over the Web. The new ELMoViz module adds support for contextualized embedding architectures, in particular for ELMo models. The provided visualizations follow the metaphor of ‘two-dimensional text’ by showing lexical substitutes: words which are most semantically similar in context to the words of the input sentence. The system allows the user to change the ELMo layers from which token embeddings are inferred. It also conveys corpus information about the query words and their lexical substitutes (namely their frequency tiers and parts of speech). The module is well integrated into the rest of the WebVectors toolkit, providing lexical hyperlinks to word representations in static embedding models. Two web services have already implemented the new functionality with pre-trained ELMo models for Russian, Norwegian and English.

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.

Disambiguation of word senses in context is easy for humans, but is a major challenge for automatic approaches. Sophisticated supervised and knowledge-based models were developed to solve this task. However, (i) the inherent Zipfian distribution of supervised training instances for a given word and/or (ii) the quality of linguistic knowledge representations motivate the development of completely unsupervised and knowledge-free approaches to word sense disambiguation (WSD). They are particularly useful for under-resourced languages which do not have any resources for building either supervised and/or knowledge-based models. In this paper, we present a method that takes as input a standard pre-trained word embedding model and induces a fully-fledged word sense inventory, which can be used for disambiguation in context. We use this method to induce a collection of sense inventories for 158 languages on the basis of the original pre-trained fastText word embeddings by Grave et al., (2018), enabling WSD in these languages. Models and system are available online.

We present RuSemShift, a large-scale manually annotated test set for the task of semantic change modeling in Russian for two long-term time period pairs: from the pre-Soviet through the Soviet times and from the Soviet through the post-Soviet times. Target words were annotated by multiple crowd-source workers. The annotation process was organized following the DURel framework and was based on sentence contexts extracted from the Russian National Corpus. Additionally, we report the performance of several distributional approaches on RuSemShift, achieving promising results, which at the same time leave room for other researchers to improve.

We apply contextualised word embeddings to lexical semantic change detection in the SemEval-2020 Shared Task 1. This paper focuses on Subtask 2, ranking words by the degree of their semantic drift over time. We analyse the performance of two contextualising architectures (BERT and ELMo) and three change detection algorithms. We find that the most effective algorithms rely on the cosine similarity between averaged token embeddings and the pairwise distances between token embeddings. They outperform strong baselines by a large margin (in the post-evaluation phase, we have the best Subtask 2 submission for SemEval-2020 Task 1), but interestingly, the choice of a particular algorithm depends on the distribution of gold scores in the test set.

This paper describes the ÚFAL--Oslo system submission to the shared task on Cross-Framework Meaning Representation Parsing (MRP, Oepen et al. 2019). The submission is based on several third-party parsers. Within the official shared task results, the submission ranked 11th out of 13 participating systems.

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.

We measure the intensity of diachronic semantic shifts in adjectives in English, Norwegian and Russian across 5 decades. This is done in order to test the hypothesis that evaluative adjectives are more prone to temporal semantic change. To this end, 6 different methods of quantifying semantic change are used. Frequency-controlled experimental results show that, depending on the particular method, evaluative adjectives either do not differ from other types of adjectives in terms of semantic change or appear to actually be less prone to shifting (particularly, to ‘jitter’-type shifting). Thus, in spite of many well-known examples of semantically changing evaluative adjectives (like ‘terrific’ or ‘incredible’), it seems that such cases are not specific to this particular type of words.

In this paper, we critically evaluate the widespread assumption that deep learning NLP models do not require lemmatized input. To test this, we trained versions of contextualised word embedding ELMo models on raw tokenized corpora and on the corpora with word tokens replaced by their lemmas. Then, these models were evaluated on the word sense disambiguation task. This was done for the English and Russian languages. The experiments showed that while lemmatization is indeed not necessary for English, the situation is different for Russian. It seems that for rich-morphology languages, using lemmatized training and testing data yields small but consistent improvements: at least for word sense disambiguation. This means that the decisions about text pre-processing before training ELMo should consider the linguistic nature of the language in question.

Graph measures, such as node distances, are inefficient to compute. We explore dense vector representations as an effective way to approximate the same information. We introduce a simple yet efficient and effective approach for learning graph embeddings. Instead of directly operating on the graph structure, our method takes structural measures of pairwise node similarities into account and learns dense node representations reflecting user-defined graph distance measures, such as e.g. the shortest path distance or distance measures that take information beyond the graph structure into account. We demonstrate a speed-up of several orders of magnitude when predicting word similarity by vector operations on our embeddings as opposed to directly computing the respective path-based measures, while outperforming various other graph embeddings on semantic similarity and word sense disambiguation tasks.

We present path2vec, a new approach for learning graph embeddings that relies on structural measures of pairwise node similarities. The model learns representations for nodes in a dense space that approximate a given user-defined graph distance measure, such as e.g. the shortest path distance or distance measures that take information beyond the graph structure into account. Evaluation of the proposed model on semantic similarity and word sense disambiguation tasks, using various WordNet-based similarity measures, show that our approach yields competitive results, outperforming strong graph embedding baselines. The model is computationally efficient, being orders of magnitude faster than the direct computation of graph-based distances.

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.

We use dependency triples automatically extracted from a Web-scale corpus to perform unsupervised semantic frame induction. We cast the frame induction problem as a triclustering problem that is a generalization of clustering for triadic data. Our replicable benchmarks demonstrate that the proposed graph-based approach, Triframes, shows state-of-the art results on this task on a FrameNet-derived dataset and performing on par with competitive methods on a verb class clustering task.

This paper presents a method of automatic construction extraction from a large corpus of Russian. The term ‘construction’ here means a multi-word expression in which a variable can be replaced with another word from the same semantic class, for example, ‘a glass of [water/juice/milk]’. We deal with constructions that consist of a noun and its adjective modifier. We propose a method of grouping such constructions into semantic classes via 2-step clustering of word vectors in distributional models. We compare it with other clustering techniques and evaluate it against A Russian-English Collocational Dictionary of the Human Body that contains manually annotated groups of constructions with nouns meaning human body parts. The best performing method is used to cluster all adjective-noun bigrams in the Russian National Corpus. Results of this procedure are publicly available and can be used for building Russian construction dictionary as well as to accelerate theoretical studies of constructions.

Recent studies have shown that word embedding models can be used to trace time-related (diachronic) semantic shifts in particular words. In this paper, we evaluate some of these approaches on the new task of predicting the dynamics of global armed conflicts on a year-to-year basis, using a dataset from the conflict research field as the gold standard and the Gigaword news corpus as the training data. The results show that much work still remains in extracting ‘cultural’ semantic shifts from diachronic word embedding models. At the same time, we present a new task complete with an evaluation set and introduce the ‘anchor words’ method which outperforms previous approaches on this set.

In this demo we present WebVectors, a free and open-source toolkit helping to deploy web services which demonstrate and visualize distributional semantic models (widely known as word embeddings). WebVectors can be useful in a very common situation when one has trained a distributional semantics model for one’s particular corpus or language (tools for this are now widespread and simple to use), but then there is a need to demonstrate the results to general public over the Web. We show its abilities on the example of the living web services featuring distributional models for English, Norwegian and Russian.

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 1994–2010 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.

In this paper, a new approach towards semantic clustering of the results of ambiguous search queries is presented. We propose using distributed vector representations of words trained with the help of prediction-based neural embedding models to detect senses of search queries and to cluster search engine results page according to these senses. The words from titles and snippets together with semantic relationships between them form a graph, which is further partitioned into components related to different query senses. This approach to search engine results clustering is evaluated against a new manually annotated evaluation data set of Russian search queries. We show that in the task of semantically clustering search results, prediction-based models slightly but stably outperform traditional count-based ones, with the same training corpora.

We present an approach to detect differences in lexical semantics across English language registers, using word embedding models from distributional semantics paradigm. Models trained on register-specific subcorpora of the BNC corpus are employed to compare lists of nearest associates for particular words and draw conclusions about their semantic shifts depending on register in which they are used. The models are evaluated on the task of register classification with the help of the deep inverse regression approach. Additionally, we present a demo web service featuring most of the described models and allowing to explore word meanings in different English registers and to detect register affiliation for arbitrary texts. The code for the service can be easily adapted to any set of underlying models.