Сөз Өкілдіктері

Vector-space word representations have been very successful in recent years at im- proving performance across a variety of NLP tasks. However, common to most existing work, words are regarded as …...

In this article, we describe a new approach to distributional semantics. This approach relies on a generative model of sentences with latent variables, which takes the syntax into account by …...

Random walks over large knowledge bases like WordNet have been successfully used in word similarity, relatedness and disambigua- tion tasks. Unfortunately, those algorithms are relatively slow for large repositories, with …...

Automated Text Scoring (ATS) provides a cost-effective and consistent alternative to human marking. However, in order to achieve good performance, the pre- dictive features of the system need to be …...

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 …...

AbstractRecent work for learning word representations has applied successfully to many NLP applications, such as sentiment analysis and question answering. However, most of these models assume a single vector per …...

AbstractDetecting aspectual properties of clauses in the form of situation entity types has been shown to depend on a combination of syntactic-semantic and contextual features. We explore this task in …...

AbstractWords can be represented by composing the representations of subword units such as word segments, characters, and/or character n-grams. While such representations are effective and may capture the morphological regularities …...

AbstractWe present in this paper a novel framework for morpheme segmentation which uses the morpho-syntactic regularities preserved by word representations, in addition to orthographic features, to segment words into morphemes. …...

AbstractEfficient word representations play an important role in solving various problems related to Natural Language Processing (NLP), data mining, text mining etc. The issue of data sparsity poses a great …...

AbstractThe use of subword-level information (e.g., characters, character n-grams, morphemes) has become ubiquitous in modern word representation learning. Its importance is attested especially for morphologically rich languages which generate a …...

AbstractLanguage is used to describe concepts, and many of these concepts are hierarchical. Moreover, this hierarchy should be compatible with forming phrases and sentences. We use linear-algebraic methods that allow …...

AbstractIn transductive learning, an unlabeled test set is used for model training. Although this setting deviates from the common assumption of a completely unseen test set, it is applicable in …...

AbstractNeural word representations are at the core of many state-of-the-art natural language processing models. A widely used approach is to pre-train, store and look up word or character embedding matrices. …...

AbstractWord representations trained on text reproduce human implicit bias related to gender, race and age. Methods have been developed to remove such bias. Here, we present results that show that …...

AbstractAdvances in word representations have shown tremendous improvements in downstream NLP tasks, but lack semantic interpretability. In this paper, we introduce Definition Frames (DF), a matrix distributed representation extracted from …...

AbstractText classification is fundamental in natural language processing (NLP) and Graph Neural Networks (GNN) are recently applied in this task. However, the existing graph-based works can neither capture the contextual …...

AbstractThis paper is about learning word representations using grammatical type information. We use the syntactic types of Combinatory Categorial Grammar to develop multilinear representations, i.e. maps with n arguments, for …...

AbstractWord representations empowered with additional linguistic information have been widely studied and proved to outperform traditional embeddings. Current methods mainly focus on learning embeddings for words while embeddings of linguistic …...

AbstractThis study carries out a systematic intrinsic evaluation of the semantic representations learned by state-of-the-art pre-trained multimodal Transformers. These representations are claimed to be task-agnostic and shown to help on …...

AbstractNatural language processing models learn word representations based on the distributional hypothesis, which asserts that word context (e.g., co-occurrence) correlates with meaning. We propose that n-grams composed of random character …...