Related papers: SEE: Syntax-aware Entity Embedding for Neural Rela…
Discourse relations bind smaller linguistic elements into coherent texts. However, automatically identifying discourse relations is difficult, because it requires understanding the semantics of the linked sentences. A more subtle challenge…
Models based on large-pretrained language models, such as S(entence)BERT, provide effective and efficient sentence embeddings that show high correlation to human similarity ratings, but lack interpretability. On the other hand, graph…
Extracting entities and relations for types of interest from text is important for understanding massive text corpora. Traditionally, systems of entity relation extraction have relied on human-annotated corpora for training and adopted an…
Distant Supervised Relation Extraction (DSRE) is usually formulated as a problem of classifying a bag of sentences that contain two query entities, into the predefined relation classes. Most existing methods consider those relation classes…
Word embeddings have gained significant attention as learnable representations of semantic relations between words, and have been shown to improve upon the results of traditional word representations. However, little effort has been devoted…
We consider the problem of embedding entities and relations of knowledge bases in low-dimensional vector spaces. Unlike most existing approaches, which are primarily efficient for modeling equivalence relations, our approach is designed to…
The performance of relation extraction models has increased considerably with the rise of neural networks. However, a key issue of neural relation extraction is robustness: the models do not scale well to long sentences with multiple…
Keyphrase extraction is the task of finding several interesting phrases in a text document, which provide a list of the main topics within the document. Most existing graph-based models use co-occurrence links as cohesion indicators to…
In the last few years, neural networks have been intensively used to develop meaningful distributed representations of words and contexts around them. When these representations, also known as "embeddings", are learned from unsupervised…
In sentence modeling and classification, convolutional neural network approaches have recently achieved state-of-the-art results, but all such efforts process word vectors sequentially and neglect long-distance dependencies. To exploit both…
Relation extraction (RE) aims to extract the relations between entity names from the textual context. In principle, textual context determines the ground-truth relation and the RE models should be able to correctly identify the relations…
We present models for embedding words in the context of surrounding words. Such models, which we refer to as token embeddings, represent the characteristics of a word that are specific to a given context, such as word sense, syntactic…
Current neural network-based methods to the problem of document summarisation struggle when applied to datasets containing large inputs. In this paper we propose a new approach to the challenge of content-selection when dealing with…
In this paper, we use the framework of neural machine translation to learn joint sentence representations across six very different languages. Our aim is that a representation which is independent of the language, is likely to capture the…
The meaning of a sentence is a function of the relations that hold between its words. We instantiate this relational view of semantics in a series of neural models based on variants of relation networks (RNs) which represent a set of…
A plethora of approaches have been proposed for joint entity-relation (ER) extraction. Most of these methods largely depend on a large amount of manually annotated training data. However, manual data annotation is time consuming, labor…
Sentence embedding is a significant research topic in the field of natural language processing (NLP). Generating sentence embedding vectors reflecting the intrinsic meaning of a sentence is a key factor to achieve an enhanced performance in…
Pre-trained transformer models shine in many natural language processing tasks and therefore are expected to bear the representation of the input sentence or text meaning. These sentence-level embeddings are also important in…
Entity extraction is a key technology for obtaining information from massive texts in natural language processing. The further interaction between them does not meet the standards of human reading comprehension, thus limiting the…
Sentence embeddings can be decoded to give approximations of the original texts used to create them. We explore this effect in the context of text simplification, demonstrating that reconstructed text embeddings preserve complexity levels.…