The paper reports on the usage of deep learning methods for improving a Named Entity Recognition (NER) training corpus and for predicting and annotating new types in a test corpus. We show how the annotations in a type-based corpus of named entities (NE) were populated as occurrences within it, thus ensuring density of the training information. A deep learning model was adopted for discovering inconsistencies in the initial annotation and for learning new NE types. The evaluation results get improved after data curation, randomization and deduplication.

Lexical resources such as WordNet (Miller, 1995) and FrameNet (Baker et al., 1998) are organized as graphs, where relationships between words are made explicit via the structure of the resource. This work explores how structural information from these lexical resources can lead to gains in a downstream task, namely frame identification. While much of the current work in frame identification uses various neural architectures to predict frames, those neural architectures only use representations of frames based on annotated corpus data. We demonstrate how incorporating knowledge directly from the FrameNet graph structure improves the performance of a neural network-based frame identification system. Specifically, we construct a bidirectional LSTM with a loss function that incorporates various graph- and corpus-based frame embeddings for learning and ultimately achieves strong performance gains with the graph-based embeddings over corpus-based embeddings alone.

This paper introduces several improvements over the current state of the art in knowledge-based word sense disambiguation. Those innovations are the result of modifying and enriching a knowledge base created originally on the basis of WordNet. They reflect several separate but connected strategies: manipulating the shape and the content of the knowledge base, assigning weights over the relations in the knowledge base, and the addition of new relations to it. The main contribution of the paper is to demonstrate that the previously proposed knowledge bases organize linguistic and world knowledge suboptimally for the task of word sense disambiguation. In doing so, the paper also establishes a new state of the art for knowledge-based approaches. Its best models are competitive in the broader context of supervised systems as well.

In this paper we present an approach for training verb subatom embeddings. For each verb we learn several embeddings rather than only one. These embeddings include the verb itself as well as embeddings for each grammatical role of this verb. To give an example, for the verb ‘to give’ we learn four embeddings: one for the lemma ‘give’, one for the subject, one for the direct object and one for the indirect object. We have exploited these grammatical role embeddings in order to add new syntagmatic relations to WordNet. The evaluation of the new relations quality has been done extrinsically through the Knowledge-based Word Sense Disambiguation task.

This paper presents a neural network architecture for word sense disambiguation (WSD). The architecture employs recurrent neural layers and more specifically LSTM cells, in order to capture information about word order and to easily incorporate distributed word representations (embeddings) as features, without having to use a fixed window of text. The paper demonstrates that the architecture is able to compete with the most successful supervised systems for WSD and that there is an abundance of possible improvements to take it to the current state of the art. In addition, it explores briefly the potential of combining different types of embeddings as input features; it also discusses possible ways for generating “artificial corpora” from knowledge bases – for the purpose of producing training data and in relation to possible applications of embedding lemmas and word senses in the same space.

In this paper we present an analysis of different semantic relations extracted from WordNet, Extended WordNet and SemCor, with respect to their role in the task of knowledge-based word sense disambiguation. The experiments use the same algorithm and the same test sets, but different variants of the knowledge graph. The results show that different sets of relations have different impact on the results: positive or negative. The beneficial ones are discussed with respect to the combination of relations and with respect to the test set. The inclusion of inference has only a modest impact on accuracy, while the addition of syntactic relations produces stable improvement over the baselines.