Embeddings

Ngram language models tend to increase in size with inflating the corpus size, and con- sume considerable resources. In this pa- per, we propose an efficient method for im- plementing …...

We experiment with learning word representa- tions designed to be combined into sentence- level semantic representations, using an ob- jective function which does not directly make use of the supervised …...

A common problem in cognitive modelling is lack of access to accurate broad-coverage models of event-level surprisal. As shown in, e.g., Bicknell et al. (2010), event-level knowl- edge does affect …...

AbstractEvaluation of machine translation (MT) into morphologically rich languages (MRL) has not been well studied despite posing many challenges. In this paper, we explore the use of embeddings obtained from …...

AbstractWe train one multilingual model for dependency parsing and use it to parse sentences in several languages. The parsing model uses (i) multilingual word clusters and embeddings; (ii) token-level language …...

Semantic dependency parsing aims at ex- tracting arcs and semantic role labels for all words in a sentence. In this paper, we propose a semantic dependency parser which is based …...

AbstractWe propose a novel way to handle out of vocabulary (OOV) words in downstream natural language processing (NLP) tasks. We implement a network that predicts useful embeddings for OOV words …...

AbstractThis paper presents RuSentiment, a new dataset for sentiment analysis of social media posts in Russian, and a new set of comprehensive annotation guidelines that are extensible to other languages. …...

AbstractThis paper describes a warrant classification system for SemEval 2018 Task 12, that attempts to learn semantic representations of reasons, claims and warrants. The system consists of 3 stacked LSTMs: …...

AbstractIn this work, we address the evaluation of distributional semantic models trained on smaller, domain-specific texts, specifically, philosophical text. Specifically, we inspect the behaviour of models using a pre-trained background …...

AbstractWe examine the benefits of visual context in training neural language models to perform next-word prediction. A multi-modal neural architecture is introduced that outperform its equivalent trained on language alone …...

AbstractIn this paper, we present our contribution to SemEval 2019 Task 5 Multilingual Detection of Hate, specifically in the Subtask A (English and Spanish). We compare different configurations of shallow …...

AbstractWe investigate the political roles of “Internet trolls” in social media. Political trolls, such as the ones linked to the Russian Internet Research Agency (IRA), have recently gained enormous attention …...

AbstractRecent progress in text classification has been focused on high-resource languages such as English and Chinese. For low-resource languages, amongst them most African languages, the lack of well-annotated data and …...

AbstractAutomatic speech processing applications often have to deal with the problem of aggregating local descriptors (i.e., representations of input speech data corresponding to specific portions across the time dimension) and …...

AbstractSemEval Task 4 Commonsense Validation and Explanation Challenge is to validate whether a system can differentiate natural language statements that make sense from those that do not make sense. Two …...

AbstractStereotypical character roles-also known as archetypes or dramatis personae-play an important function in narratives: they facilitate efficient communication with bundles of default characteristics and associations and ease understanding of those …...

AbstractIn this paper we explore the improvement of intent recognition in conversational systems by the use of meta-knowledge embedded in intent identifiers. Developers often include such knowledge, structure as taxonomies, …...

AbstractWhile relation extraction is an essential task in knowledge acquisition and representation, and new-generated relations are common in the real world, less effort is made to predict unseen relations that …...

AbstractRecent work has demonstrated that entity representations can be extracted from pre-trained language models to develop knowledge graph completion models that are more robust to the naturally occurring sparsity found …...

AbstractEmbeddings, which compress information in raw text into semantics-preserving low-dimensional vectors, have been widely adopted for their efficacy. However, recent research has shown that embeddings can potentially leak private information …...

AbstractIn the context of the Multimedia Automatic Misogyny Identification (MAMI) competition 2022, we developed a framework for extracting lexical-semantic features from text and combine them with semantic descriptions of images, …...

AbstractHate speech detection is a prominent and challenging task, since hate messages are often expressed in subtle ways and with characteristics that may vary depending on the author. Hence, many …...

AbstractGenerative language models achieve the state of the art in many tasks within natural language processing (NLP). Although these models correctly capture syntactic information, they fail to interpret knowledge (semantics). …...

AbstractIdioms such as “call it a day” and “piece of cake,” are prevalent in natural language. How do Transformer language models process idioms? This study examines this question by analysing …...