379 research outputs found
ReferenceNet: a semantic-pragmatic network for capturing reference relations
Full text linkIn this paper, we present ReferenceNet: a semantic-pragmatic network of reference relations between synsets. Synonyms are assumed to be exchangeable in similar contexts and also word embeddings are based on sharing of local contexts represented as vectors. Co-referring words, however, tend to occur in the same topical context but in different local contexts. In addition, they may express different concepts related through topical coherence, and through author framing and perspective. In this paper, we describe how reference relations can be added to WordNet and how they can be acquired. We evaluate two methods of extracting event coreference relations using WordNet relations against a manual annotation of 38 documents within the same topical domain of gun violence. We conclude that precision is reasonable but recall is lower because the Word-Net hierarchy does not sufficiently capture the required coherence and perspective relations
A Deep Dive into Word Sense Disambiguation with LSTM
No full textTrained models for paper:Minh Le, Marten Postma, Jacopo Urbani and Piek Vossen. 2018. A Deep Dive into Word Sense Disambiguation with LSTM. COLING 2018</div
A WordNet View on Crosslingual Transformers
No full textWordNet is a database that represents relations between words and concepts as an abstraction of the contexts in which words are used. Contextualized language models represent words in contexts but leave the underlying concepts implicit. In this paper, we investigate how different layers of a pre-trained language model shape the abstract lexical relationship toward the actual contextual concept. Can we define the amount of contextualized concept forming needed given the abstracted representation of a word? Specifically, we consider samples of words with different polysemy profiles shared across three languages, assuming that words with a different polysemy profile require a different degree of concept shaping by context. We conduct probing experiments to investigate the impact of prior polysemy profiles on the representation in different layers. We analyze how contextualized models can approximate meaning through context and examine crosslingual interference effects
Towards interpretable, data-derived distributional semantic representations for reasoning:A dataset of properties and concepts
Full text linkThis paper proposes a framework for investigating which types of semantic properties are represented by distributional data. The core of our framework consists of relations between concepts and properties. We provide hypotheses on which properties are reflected in distributional data or not based on the type of relation. We outline strategies for creating a dataset of positive and negative examples for various semantic properties, which cannot easily be separated on the basis of general similarity (e.g. fly: seagull, penguin). This way, a distributional model can only distinguish between positive and negative examples through evidence for a target property. Once completed, this dataset can be used to test our hypotheses and work towards data-derived interpretable representations.</p
A Narratology-Based Framework for Storyline Extraction
Full text linkStories are a pervasive phenomenon of human life. They also represent a cognitive tool to understand and make sense of the world and of its happenings. In this contribution we describe a narratology-based framework for modeling stories as a combination of different data structures and to automatically extract them from news articles. We introduce a distinction among three data structures (timelines, causelines, and storylines) that capture different narratological dimensions, respectively chronological ordering, causal connections, and plot structure. We developed the Circumstantial Event Ontology (CEO) for modeling (implicit) circumstantial relations as well as explicit causal relations and create two benchmark corpora: ECB+/CEO, for causelines, and the Event Storyline Corpus (ESC), for storylines. To test our framework and the difficulty in automatically extract causelines and storylines, we develop a series of reasonable baseline system
A WordNet View on Crosslingual Language Models
No full textW. Tufa, W., L. Beinborn, and P. Vossen “A WordNet View on Crosslingual Language Models”, in: Proceedings of the 12th Global Wordnet Conference (GWC2023) San Sebastian, Spain, January 23-27, 202
- …
