Related papers: Stack-propagation: Improved Representation Learnin…
This paper introduces LatinCy, a set of trained general purpose Latin-language "core" pipelines for use with the spaCy natural language processing framework. The models are trained on a large amount of available Latin data, including all…
Considering the large amount of content created online by the minute, slang-aware automatic tools are critically needed to promote social good, and assist policymakers and moderators in restricting the spread of offensive language, abuse,…
We propose a novel stacked generalization (stacking) method as a dynamic ensemble technique using a pool of heterogeneous classifiers for node label classification on networks. The proposed method assigns component models a set of…
We use a Dynamic Bayesian Network to represent compactly a variety of sublexical and contextual features relevant to Part-of-Speech (PoS) tagging. The outcome is a flexible tagger (LegoTag) with state-of-the-art performance (3.6% error on a…
I introduce a formalism for representing the syntax of recursively structured graph-like patterns. It does not use production rules, like a conventional graph grammar, but represents the syntactic structure in a more direct and declarative…
We propose a unified neural network architecture and learning algorithm that can be applied to various natural language processing tasks including: part-of-speech tagging, chunking, named entity recognition, and semantic role labeling. This…
Singlish, or Colloquial Singapore English, is a language formed from oral and social communication within multicultural Singapore. In this work, we work on a fundamental Natural Language Processing (NLP) task: Parts-Of-Speech (POS) tagging…
Many natural language processing tasks, e.g., coreference resolution and semantic role labeling, require selecting text spans and making decisions about them. A typical approach to such tasks is to score all possible spans and greedily…
Automatic text tagging is an important component in higher level analysis of text corpora, and its output can be used in many natural language processing applications. In languages like Turkish or Finnish, with agglutinative morphology,…
We introduce Transformer Grammars (TGs), a novel class of Transformer language models that combine (i) the expressive power, scalability, and strong performance of Transformers and (ii) recursive syntactic compositions, which here are…
In neural Information Retrieval, ongoing research is directed towards improving the first retriever in ranking pipelines. Learning dense embeddings to conduct retrieval using efficient approximate nearest neighbors methods has proven to…
Direct dependency parsing of the speech signal -- as opposed to parsing speech transcriptions -- has recently been proposed as a task (Pupier et al. 2022), as a way of incorporating prosodic information in the parsing system and bypassing…
Network representation learning has exploded recently. However, existing studies usually reconstruct networks as sequences or matrices, which may cause information bias or sparsity problem during model training. Inspired by a cognitive…
Word segmentation plays a pivotal role in improving any Arabic NLP application. Therefore, a lot of research has been spent in improving its accuracy. Off-the-shelf tools, however, are: i) complicated to use and ii) domain/dialect…
We present an empirical study on methods for span finding, the selection of consecutive tokens in text for some downstream tasks. We focus on approaches that can be employed in training end-to-end information extraction systems, and find…
Recent advances in linguistic steganalysis have successively applied CNN, RNN, GNN and other efficient deep models for detecting secret information in generative texts. These methods tend to seek stronger feature extractors to achieve…
Recursion is a prominent feature of human language, and fundamentally challenging for self-attention due to the lack of an explicit recursive-state tracking mechanism. Consequently, Transformer language models poorly capture long-tail…
Many words are ambiguous in terms of their part of speech (POS). However, when a word appears in a text, this ambiguity is generally much reduced. Disambiguating POS involves using context to reduce the number of POS associated with words,…
Phonetic representations are used when recording spoken languages, but no equivalent exists for recording signed languages. As a result, linguists have proposed several annotation systems that operate on the gloss or sub-unit level;…
Morphologically rich languages often lack the annotated linguistic resources required to develop accurate natural language processing tools. We propose models suitable for training morphological taggers with rich tagsets for low-resource…