arXiv subjects

Alexander Panchenko

Publications and source records attributed to Alexander Panchenko.

At least 109 records · Page 6Linked to original sources

arXiv2018

How much does a word weigh? Weighting word embeddings for word sense induction

The paper describes our participation in the first shared task on word sense induction and disambiguation for the Russian language RUSSE'2018 (Panchenko et al., 2018). For each of several dozens of ambiguous words, the participants were asked to group text fragments containing it according to the senses of this word, which were not provided beforehand, therefore the "induction" part of the task. For instance, a word "bank" and a set of text fragments (also known as "contexts") in which this word occurs, e.g. "bank is a financial institution that accepts deposits" and "river bank is a slope beside a body of water" were given. A participant was asked to cluster such contexts in the unknown in advance number of clusters corresponding to, in this case, the "company" and the "area" senses of the word "bank". The organizers proposed three evaluation datasets of varying complexity and text genres based respectively on texts of Wikipedia, Web pages, and a dictionary of the Russian language. We present two experiments: a positive and a negative one, based respectively on clustering of contexts represented as a weighted average of word embeddings and on machine translation using two state-of-the-art production neural machine translation systems. Our team showed the second best result on two datasets and the third best result on the remaining one dataset among 18 participating teams. We managed to substantially outperform competitive state-of-the-art baselines from the previous years based on sense embeddings.

cs.CL↗

arXiv2018

Unsupervised Sense-Aware Hypernymy Extraction

In this paper, we show how unsupervised sense representations can be used to improve hypernymy extraction. We present a method for extracting disambiguated hypernymy relationships that propagates hypernyms to sets of synonyms (synsets), constructs embeddings for these sets, and establishes sense-aware relationships between matching synsets. Evaluation on two gold standard datasets for English and Russian shows that the method successfully recognizes hypernymy relationships that cannot be found with standard Hearst patterns and Wiktionary datasets for the respective languages.

cs.CL↗

arXiv2018

Sentiment Index of the Russian Speaking Facebook

A sentiment index measures the average emotional level in a corpus. We introduce four such indexes and use them to gauge average "positiveness" of a population during some period based on posts in a social network. This article for the first time presents a text-, rather than word-based sentiment index. Furthermore, this study presents the first large-scale study of the sentiment index of the Russian-speaking Facebook. Our results are consistent with the prior experiments for the English language.

cs.CL↗

arXiv2018

RUSSE'2018: A Shared Task on Word Sense Induction for the Russian Language

The paper describes the results of the first shared task on word sense induction (WSI) for the Russian language. While similar shared tasks were conducted in the past for some Romance and Germanic languages, we explore the performance of sense induction and disambiguation methods for a Slavic language that shares many features with other Slavic languages, such as rich morphology and virtually free word order. The participants were asked to group contexts of a given word in accordance with its senses that were not provided beforehand. For instance, given a word "bank" and a set of contexts for this word, e.g. "bank is a financial institution that accepts deposits" and "river bank is a slope beside a body of water", a participant was asked to cluster such contexts in the unknown in advance number of clusters corresponding to, in this case, the "company" and the "area" senses of the word "bank". For the purpose of this evaluation campaign, we developed three new evaluation datasets based on sense inventories that have different sense granularity. The contexts in these datasets were sampled from texts of Wikipedia, the academic corpus of Russian, and an explanatory dictionary of Russian. Overall, 18 teams participated in the competition submitting 383 models. Multiple teams managed to substantially outperform competitive state-of-the-art baselines from the previous years based on sense embeddings.

cs.CL↗

arXiv2018

Unsupervised Semantic Frame Induction using Triclustering

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.

cs.CL↗

arXiv2018

An Unsupervised Word Sense Disambiguation System for Under-Resourced Languages

In this paper, we present Watasense, an unsupervised system for word sense disambiguation. Given a sentence, the system chooses the most relevant sense of each input word with respect to the semantic similarity between the given sentence and the synset constituting the sense of the target word. Watasense has two modes of operation. The sparse mode uses the traditional vector space model to estimate the most similar word sense corresponding to its context. The dense mode, instead, uses synset embeddings to cope with the sparsity problem. We describe the architecture of the present system and also conduct its evaluation on three different lexical semantic resources for Russian. We found that the dense mode substantially outperforms the sparse one on all datasets according to the adjusted Rand index.

cs.CL↗

arXiv2018

Neologisms on Facebook

In this paper, we present a study of neologisms and loan words frequently occurring in Facebook user posts. We have analyzed a dataset of several million publically available posts written during 2006-2013 by Russian-speaking Facebook users. From these, we have built a vocabulary of most frequent lemmatized words missing from the OpenCorpora dictionary the assumption being that many such words have entered common use only recently. This assumption is certainly not true for all the words extracted in this way; for that reason, we manually filtered the automatically obtained list in order to exclude non-Russian or incorrectly lemmatized words, as well as words recorded by other dictionaries or those occurring in texts from the Russian National Corpus. The result is a list of 168 words that can potentially be considered neologisms. We present an attempt at an etymological classification of these neologisms (unsurprisingly, most of them have recently been borrowed from English, but there are also quite a few new words composed of previously borrowed stems) and identify various derivational patterns. We also classify words into several large thematic areas, "internet", "marketing", and "multimedia" being among those with the largest number of words. We believe that, together with the word base collected in the process, they can serve as a starting point in further studies of neologisms and lexical processes that lead to their acceptance into the mainstream language.

cs.CL↗

arXiv2018

RUSSE: The First Workshop on Russian Semantic Similarity

The paper gives an overview of the Russian Semantic Similarity Evaluation (RUSSE) shared task held in conjunction with the Dialogue 2015 conference. There exist a lot of comparative studies on semantic similarity, yet no analysis of such measures was ever performed for the Russian language. Exploring this problem for the Russian language is even more interesting, because this language has features, such as rich morphology and free word order, which make it significantly different from English, German, and other well-studied languages. We attempt to bridge this gap by proposing a shared task on the semantic similarity of Russian nouns. Our key contribution is an evaluation methodology based on four novel benchmark datasets for the Russian language. Our analysis of the 105 submissions from 19 teams reveals that successful approaches for English, such as distributional and skip-gram models, are directly applicable to Russian as well. On the one hand, the best results in the contest were obtained by sophisticated supervised models that combine evidence from different sources. On the other hand, completely unsupervised approaches, such as a skip-gram model estimated on a large-scale corpus, were able score among the top 5 systems.

cs.CL↗

arXiv2018

Enriching Frame Representations with Distributionally Induced Senses

We introduce a new lexical resource that enriches the Framester knowledge graph, which links Framnet, WordNet, VerbNet and other resources, with semantic features from text corpora. These features are extracted from distributionally induced sense inventories and subsequently linked to the manually-constructed frame representations to boost the performance of frame disambiguation in context. Since Framester is a frame-based knowledge graph, which enables full-fledged OWL querying and reasoning, our resource paves the way for the development of novel, deeper semantic-aware applications that could benefit from the combination of knowledge from text and complex symbolic representations of events and participants. Together with the resource we also provide the software we developed for the evaluation in the task of Word Frame Disambiguation (WFD).

cs.CL↗

arXiv2018

Building a Web-Scale Dependency-Parsed Corpus from CommonCrawl

We present DepCC, the largest-to-date linguistically analyzed corpus in English including 365 million documents, composed of 252 billion tokens and 7.5 billion of named entity occurrences in 14.3 billion sentences from a web-scale crawl of the \textsc{Common Crawl} project. The sentences are processed with a dependency parser and with a named entity tagger and contain provenance information, enabling various applications ranging from training syntax-based word embeddings to open information extraction and question answering. We built an index of all sentences and their linguistic meta-data enabling quick search across the corpus. We demonstrate the utility of this corpus on the verb similarity task by showing that a distributional model trained on our corpus yields better results than models trained on smaller corpora, like Wikipedia. This distributional model outperforms the state of art models of verb similarity trained on smaller corpora on the SimVerb3500 dataset.

cs.CL↗

arXiv2018

Improving Hypernymy Extraction with Distributional Semantic Classes

In this paper, we show how distributionally-induced semantic classes can be helpful for extracting hypernyms. We present methods for inducing sense-aware semantic classes using distributional semantics and using these induced semantic classes for filtering noisy hypernymy relations. Denoising of hypernyms is performed by labeling each semantic class with its hypernyms. On the one hand, this allows us to filter out wrong extractions using the global structure of distributionally similar senses. On the other hand, we infer missing hypernyms via label propagation to cluster terms. We conduct a large-scale crowdsourcing study showing that processing of automatically extracted hypernyms using our approach improves the quality of the hypernymy extraction in terms of both precision and recall. Furthermore, we show the utility of our method in the domain taxonomy induction task, achieving the state-of-the-art results on a SemEval'16 task on taxonomy induction.

cs.CL↗

arXiv2018

Spatial averaging of a dissipative particle dynamics model for active suspensions

Starting from a fine-scale dissipative particle dynamics (DPD) model of self-motile point particles, we derive meso-scale continuum equations by applying a spatial averaging version of the Irving--Kirkwood--Noll procedure. Since the method does not rely on kinetic theory, the derivation is valid for highly concentrated particle systems. Spatial averaging yields a stochastic continuum equations similar to those of Toner and Tu. However, our theory also involves a constitutive equation for the average fluctuation force. According to this equation, both the strength and the probability distribution vary with time and position through the effective mass density. The statistics of the fluctuation force also depend on the fine scale dissipative force equation, the physical temperature, and two additional parameters which characterize fluctuation strengths. Although the self-propulsion force entering our DPD model contains no explicit mechanism for aligning the velocities of neighboring particles, our averaged coarse-scale equations include the commonly encountered cubically nonlinear (internal) body force density.

nlin.AO↗

arXiv2017

A Framework for Enriching Lexical Semantic Resources with Distributional Semantics

We present an approach to combining distributional semantic representations induced from text corpora with manually constructed lexical-semantic networks. While both kinds of semantic resources are available with high lexical coverage, our aligned resource combines the domain specificity and availability of contextual information from distributional models with the conciseness and high quality of manually crafted lexical networks. We start with a distributional representation of induced senses of vocabulary terms, which are accompanied with rich context information given by related lexical items. We then automatically disambiguate such representations to obtain a full-fledged proto-conceptualization, i.e. a typed graph of induced word senses. In a final step, this proto-conceptualization is aligned to a lexical ontology, resulting in a hybrid aligned resource. Moreover, unmapped induced senses are associated with a semantic type in order to connect them to the core resource. Manual evaluations against ground-truth judgments for different stages of our method as well as an extrinsic evaluation on a knowledge-based Word Sense Disambiguation benchmark all indicate the high quality of the new hybrid resource. Additionally, we show the benefits of enriching top-down lexical knowledge resources with bottom-up distributional information from text for addressing high-end knowledge acquisition tasks such as cleaning hypernym graphs and learning taxonomies from scratch.

cs.CL↗

arXiv2017

Human and Machine Judgements for Russian Semantic Relatedness

Semantic relatedness of terms represents similarity of meaning by a numerical score. On the one hand, humans easily make judgments about semantic relatedness. On the other hand, this kind of information is useful in language processing systems. While semantic relatedness has been extensively studied for English using numerous language resources, such as associative norms, human judgments, and datasets generated from lexical databases, no evaluation resources of this kind have been available for Russian to date. Our contribution addresses this problem. We present five language resources of different scale and purpose for Russian semantic relatedness, each being a list of triples (word_i, word_j, relatedness_ij). Four of them are designed for evaluation of systems for computing semantic relatedness, complementing each other in terms of the semantic relation type they represent. These benchmarks were used to organize a shared task on Russian semantic relatedness, which attracted 19 teams. We use one of the best approaches identified in this competition to generate the fifth high-coverage resource, the first open distributional thesaurus of Russian. Multiple evaluations of this thesaurus, including a large-scale crowdsourcing study involving native speakers, indicate its high accuracy.

cs.CL↗

arXiv2017

Fighting with the Sparsity of Synonymy Dictionaries

Graph-based synset induction methods, such as MaxMax and Watset, induce synsets by performing a global clustering of a synonymy graph. However, such methods are sensitive to the structure of the input synonymy graph: sparseness of the input dictionary can substantially reduce the quality of the extracted synsets. In this paper, we propose two different approaches designed to alleviate the incompleteness of the input dictionaries. The first one performs a pre-processing of the graph by adding missing edges, while the second one performs a post-processing by merging similar synset clusters. We evaluate these approaches on two datasets for the Russian language and discuss their impact on the performance of synset induction methods. Finally, we perform an extensive error analysis of each approach and discuss prominent alternative methods for coping with the problem of the sparsity of the synonymy dictionaries.

cs.CL↗

arXiv2017

Making Sense of Word Embeddings

We present a simple yet effective approach for learning word sense embeddings. In contrast to existing techniques, which either directly learn sense representations from corpora or rely on sense inventories from lexical resources, our approach can induce a sense inventory from existing word embeddings via clustering of ego-networks of related words. An integrated WSD mechanism enables labeling of words in context with learned sense vectors, which gives rise to downstream applications. Experiments show that the performance of our method is comparable to state-of-the-art unsupervised WSD systems.

cs.CL↗

arXiv2017

Unsupervised, Knowledge-Free, and Interpretable Word Sense Disambiguation

Interpretability of a predictive model is a powerful feature that gains the trust of users in the correctness of the predictions. In word sense disambiguation (WSD), knowledge-based systems tend to be much more interpretable than knowledge-free counterparts as they rely on the wealth of manually-encoded elements representing word senses, such as hypernyms, usage examples, and images. We present a WSD system that bridges the gap between these two so far disconnected groups of methods. Namely, our system, providing access to several state-of-the-art WSD models, aims to be interpretable as a knowledge-based system while it remains completely unsupervised and knowledge-free. The presented tool features a Web interface for all-word disambiguation of texts that makes the sense predictions human readable by providing interpretable word sense inventories, sense representations, and disambiguation results. We provide a public API, enabling seamless integration.

cs.CL↗

arXiv2017

Negative Sampling Improves Hypernymy Extraction Based on Projection Learning

We present a new approach to extraction of hypernyms based on projection learning and word embeddings. In contrast to classification-based approaches, projection-based methods require no candidate hyponym-hypernym pairs. While it is natural to use both positive and negative training examples in supervised relation extraction, the impact of negative examples on hypernym prediction was not studied so far. In this paper, we show that explicit negative examples used for regularization of the model significantly improve performance compared to the state-of-the-art approach of Fu et al. (2014) on three datasets from different languages.

cs.CL↗