Related papers: Enriching a Text by Semantic Disambiguation for In…
Since real-world ubiquitous documents (e.g., invoices, tickets, resumes and leaflets) contain rich information, automatic document image understanding has become a hot topic. Most existing works decouple the problem into two separate tasks,…
Text semantic matching is a fundamental task that has been widely used in various scenarios, such as community question answering, information retrieval, and recommendation. Most state-of-the-art matching models, e.g., BERT, directly…
Search engines perform the task of retrieving information related to the user-supplied query words. This task has two parts; one is finding "featured words" which describe an article best and the other is finding a match among these words…
Named Entity Disambiguation (NED) is the task of linking a named-entity mention to an instance in a knowledge-base, typically Wikipedia. This task is closely related to word-sense disambiguation (WSD), where the supervised word-expert…
The project presented in this article aims to formalize criteria and procedures in order to extract semantic information from parsed dictionary glosses. The actual purpose of the project is the generation of a semantic network (nearly an…
The rapidly increasing number of scientific documents available publicly on the Internet creates the challenge of efficiently organizing and indexing these documents. Due to the time consuming and tedious nature of manual classification and…
Sentence extraction based summarization methods has some limitations as it doesn't go into the semantics of the document. Also, it lacks the capability of sentence generation which is intuitive to humans. Here we present a novel method to…
Citation texts are sometimes not very informative or in some cases inaccurate by themselves; they need the appropriate context from the referenced paper to reflect its exact contributions. To address this problem, we propose an unsupervised…
Many business workflows require extracting important fields from form-like documents (e.g. bank statements, bills of lading, purchase orders, etc.). Recent techniques for automating this task work well only when trained with large datasets.…
Getting relevant information from search engines has been the heart of research works in information retrieval. Query expansion is a retrieval technique that has been studied and proved to yield positive results in relevance. Users are…
The notion of word embedding plays a fundamental role in natural language processing (NLP). However, pre-training word embedding for very large-scale vocabulary is computationally challenging for most existing methods. In this work, we show…
This work presents an unsupervised approach for improving WordNet that builds upon recent advances in document and sense representation via distributional semantics. We apply our methods to construct Wordnets in French and Russian,…
Understanding inferences and answering questions from text requires more than merely recovering surface arguments, adjuncts, or strings associated with the query terms. As humans, we interpret sentences as contextualized components of a…
Sentence compression is the task of creating a shorter version of an input sentence while keeping important information. In this paper, we extend the task of compression by deletion with the use of contextual embeddings. Different from…
Recognizing semantically similar sentences or paragraphs across languages is beneficial for many tasks, ranging from cross-lingual information retrieval and plagiarism detection to machine translation. Recently proposed methods for…
Short-text classification, like all data science, struggles to achieve high performance using limited data. As a solution, a short sentence may be expanded with new and relevant feature words to form an artificially enlarged dataset, and…
Latent semantic representations of words or paragraphs, namely the embeddings, have been widely applied to information retrieval (IR). One of the common approaches of utilizing embeddings for IR is to estimate the document-to-query (D2Q)…
We present an approach to combining distributional semantic representations induced from text corpora with manually constructed lexical-semantic networks. While both kinds of semantic resources are available with high lexical coverage, our…
This paper presents a new model for word sense disambiguation formulated in terms of evolutionary game theory, where each word to be disambiguated is represented as a node on a graph whose edges represent word relations and senses are…
We release to the community six large-scale sense-annotated datasets in multiple language to pave the way for supervised multilingual Word Sense Disambiguation. Our datasets cover all the nouns in the English WordNet and their translations…