LSTMEmbed: Learning Word and Sense Representations from a Large Semantically Annotated Corpus with Long Short-Term Memories

Iacobacci, Ignacio; Navigli, Roberto

doi:10.18653/v1/p19-1165

Cited by 17 publications

(23 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This allows the model to learn more accurate semantic relations between the spotted text and its visual. That sense ID can be used to extract any word vector from any pre-trained sense embedding [14,28,31,4,13]. It consists of 1800 images with id senses (e.g.…”

Section: Coco-text With Visual Contextmentioning

confidence: 99%

“…LSTMEmbed [13]: LSTMEmbed is the most recent model in sense embeddings. It utilizes a BiLSTM architecture to learn the word and sense embeddings from annotated corpora.…”

Section: Relational Word Embeddings [3] (Rwe)mentioning

confidence: 99%

“…It utilizes a BiLSTM architecture to learn the word and sense embeddings from annotated corpora. We use the same approach than in [13]: 200-dimension embeddings trained on the English portion of BabelWiki and English Wikipedia.…”

Section: Relational Word Embeddings [3] (Rwe)mentioning

confidence: 99%

See 2 more Smart Citations

Textual Visual Semantic Dataset for Text Spotting

Sabir

Moreno-Noguer

Padró

2020

2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

View full text Add to dashboard Cite

Text Spotting in the wild consists of detecting and recognizing text appearing in images (e.g. signboards, traffic signals or brands in clothing or objects). This is a challenging problem due to the complexity of the context where texts appear (uneven backgrounds, shading, occlusions, perspective distortions, etc.). Only a few approaches try to exploit the relation between text and its surrounding environment to better recognize text in the scene. In this paper, we propose a visual context dataset 1 for Text Spotting in the wild, where the publicly available dataset COCO-text [40] has been extended with information about the scene (such as objects and places appearing in the image) to enable researchers to include semantic relations between texts and scene in their Text Spotting systems, and to offer a common framework for such approaches. For each text in an image, we extract three kinds of context information: objects in the scene, image location label and a textual image description (caption). We use state-of-the-art out-of-the-box available tools to extract this additional information. Since this information has textual form, it can be used to leverage text similarity or semantic relation methods into Text Spotting systems, either as a post-processing or in an end-to-end training strategy.

show abstract

Section: Coco-text With Visual Contextmentioning

confidence: 99%

“…LSTMEmbed [13]: LSTMEmbed is the most recent model in sense embeddings. It utilizes a BiLSTM architecture to learn the word and sense embeddings from annotated corpora.…”

Section: Relational Word Embeddings [3] (Rwe)mentioning

confidence: 99%

See 1 more Smart Citation

Textual Visual Semantic Dataset for Text Spotting

Sabir

Moreno-Noguer

Padró

2020

2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

View full text Add to dashboard Cite

show abstract

“…Such ranking can be computed in all sense embeddings that map both terminological and conceptual representations onto a shared semantic space, which is rather common in recent sense embeddings such as, e.g., [57,65,66,[70][71][72].…”

Section: Ranked Similaritymentioning

confidence: 99%

Novel metrics for computing semantic similarity with sense embeddings

Colla

Mensa

Radicioni

2020

Knowledge-Based Systems

View full text Add to dashboard Cite

In the last years many efforts have been spent to build word embeddings, a representational device in which word meanings are described through dense unit vectors of real numbers over a continuous, high-dimensional Euclidean space, where similarity can be interpreted as a metric. Afterwards, senselevel embeddings have been proposed to describe the meaning of senses, rather than terms. More recently, additional intermediate representations have been designed, providing a vector description for pairs ⟨term, sense⟩, and mapping both term and sense descriptions onto a shared semantic space. However, surprisingly enough, this wealth of approaches and resources has not been supported by a parallel refinement in the metrics used to compute semantic similarity: to date, the semantic similarity featuring two input entities is mostly computed as the maximization of some angular distance intervening between vector pairs, typically cosine similarity. In this work we introduce two novel similarity metrics to compare sense-level representations, and show that by exploiting the features of sense-embeddings it is possible to substantially improve on existing strategies, by obtaining enhanced correlation with human similarity ratings. Additionally, we argue that semantic similarity needs to be complemented by another task, involving the identification of the senses at the base of the similarity rating. We experimentally verified that the proposed metrics are beneficial when dealing with both semantic similarity task and sense identification task. The experimentation also provides a detailed how-to illustrating how six important sets of sense embeddings can be used to implement the proposed similarity metrics.

show abstract

“…Cognitive strategies, algorithms and systems dealing with semantic similarity, sense embeddings and new similarity metrics should be tested on the SID dataset. Their performances in both tasks can be compared against those provided in [1] , obtained by experimenting with six recent and influential sets of embeddings, namely LessLex [1] , NASARI [7] , DeConf [8] , SenseEmbed [9] , SW2V [10] , and LSTMEmbed [11] .…”

Section: Value Of the Datamentioning

confidence: 99%

Sense identification data: A dataset for lexical semantics

2020

View full text Add to dashboard Cite

Sense Identification is a newly proposed task; in considering a pair of terms to assess their conceptual similarity, human raters are postulated to preliminarily select a sense pair. Senses involved in this pair are those actually subject to similarity rating. The sense identification task is searching for the sense selected during the similarity rating. The sense individuation task is important to investigate strategies and sense inventories underlying human lexical access and, moreover, it is a relevant complement to the semantic similarity task. Individuating which senses are involved in the similarity rating is also crucial in order to fully assess those ratings: if we have no idea of which two senses were retrieved, on which base can we assess the score expressing their semantic proximity? The Sense Identification Dataset (SID) dataset has been built to provide a common experimental ground to systems and approaches dealing with the sense identification task. It is the first dataset specifically designed for experimenting on the mentioned task. The SID dataset was created by manually annotating with sense identifiers the term pairs from an existing dataset, the SemEval-2017 Task 2 English dataset. The original dataset was originally conceived for experimenting on the semantic similarity task, and it contains a score expressing the human similarity rating for each term pair. For each such term pair we added a pair of annotated senses: in particular, senses were annotated such that they are compatible (explicative of) with the existing similarity ratings. The SID dataset contains BabelNet sense identifiers. This sense inventory is a broadly adopted ‘naming convention’ for word senses, and such identifiers can be easily mapped onto further resources such as WordNet and WikiData, thereby enabling further processing tasks and usages in the Natural Language Processing pipeline.

show abstract

LSTMEmbed: Learning Word and Sense Representations from a Large Semantically Annotated Corpus with Long Short-Term Memories

Cited by 17 publications

References 47 publications

Textual Visual Semantic Dataset for Text Spotting

Textual Visual Semantic Dataset for Text Spotting

Novel metrics for computing semantic similarity with sense embeddings

Sense identification data: A dataset for lexical semantics

Contact Info

Product

Resources

About