Related papers: Adapting predominant and novel sense discovery alg…
Complex Word Identification (CWI) aims to detect words within a text that a reader may find difficult to understand. It has been shown that CWI systems can improve text simplification, readability prediction and vocabulary acquisition…
Word Sense Disambiguation (WSD) aims to identify the correct meaning of polysemous words in the particular context. Lexical resources like WordNet which are proved to be of great help for WSD in the knowledge-based methods. However,…
Topic models are in widespread use in natural language processing and beyond. Here, we propose a new framework for the evaluation of probabilistic topic modeling algorithms based on synthetic corpora containing an unambiguously defined…
Word similarity has many applications to social science and cultural analytics tasks like measuring meaning change over time and making sense of contested terms. Yet traditional similarity methods based on cosine similarity between word…
Text similarity detection aims at measuring the degree of similarity between a pair of texts. Corpora available for text similarity detection are designed to evaluate the algorithms to assess the paraphrase level among documents. In this…
Distributed representations of words as real-valued vectors in a relatively low-dimensional space aim at extracting syntactic and semantic features from large text corpora. A recently introduced neural network, named word2vec (Mikolov et…
Princeton WordNet is one of the most important resources for natural language processing, but is only available for English. While it has been translated using the expand approach to many other languages, this is an expensive manual…
Modern retrieval systems, whether lexical or semantic, expose a corpus through a fixed similarity interface that compresses access into a single top-k retrieval step before reasoning. This abstraction is efficient, but for agentic search,…
We present an algorithm that takes an unannotated corpus as its input, and returns a ranked list of probable morphologically related pairs as its output. The algorithm tries to discover morphologically related pairs by looking for pairs…
Distributional models are derived from co-occurrences in a corpus, where only a small proportion of all possible plausible co-occurrences will be observed. This results in a very sparse vector space, requiring a mechanism for inferring…
Current keyword spotting systems primarily use phoneme-level matching to distinguish confusable words but ignore user-specific pronunciation traits like prosody (intonation, stress, rhythm). This paper presents ProKWS, a novel framework…
Fuzzy string matching and language classification are important tools in Natural Language Processing pipelines, this paper provides advances in both areas. We propose a fast novel approach to string tokenisation for fuzzy language matching…
We share a French-English parallel corpus of Foursquare restaurant reviews (https://europe.naverlabs.com/research/natural-language-processing/machine-translation-of-restaurant-reviews), and define a new task to encourage research on Neural…
The issue of word sense ambiguity poses a significant challenge in natural language processing due to the scarcity of annotated data to feed machine learning models to face the challenge. Therefore, unsupervised word sense disambiguation…
In this paper, we describe our method for the detection of lexical semantic change, i.e., word sense changes over time. We examine semantic differences between specific words in two corpora, chosen from different time periods, for English,…
In recent years, convolutional neural networks (CNNs) took over the field of document analysis and they became the predominant model for word spotting. Especially attribute CNNs, which learn the mapping between a word image and an attribute…
Word embeddings are ubiquitous in NLP and information retrieval, but it is unclear what they represent when the word is polysemous. Here it is shown that multiple word senses reside in linear superposition within the word embedding and…
Two kinds of systems have been defined during the long history of WSD: principled systems that define which knowledge types are useful for WSD, and robust systems that use the information sources at hand, such as, dictionaries, light-weight…
The search of information in large text repositories has been plagued by the so-called document-query vocabulary gap, i.e. the semantic discordance between the contents in the stored document entities on the one hand and the human query on…
Multi-document summarization (MDS) is the task of reflecting key points from any set of documents into a concise text paragraph. In the past, it has been used to aggregate news, tweets, product reviews, etc. from various sources. Owing to…