Related papers: ner and pos when nothing is capitalized

Many of the kinds of language model used in speech understanding suffer from imperfect modeling of intra-sentential contextual influences. I argue that this problem can be addressed by clustering the sentences in a training corpus…

Text classification is the task of assigning a document to a predefined class. However, it is expensive to acquire enough labeled documents or to label them. In this paper, we study the regularization methods' effects on various…

The currently most prominent algorithm to train keyword spotting (KWS) models with deep neural networks (DNNs) requires strong supervision i.e., precise knowledge of the spoken keyword location in time. Thus, most KWS approaches treat the…

Deep neural network models have recently achieved state-of-the-art performance gains in a variety of natural language processing (NLP) tasks (Young, Hazarika, Poria, & Cambria, 2017). However, these gains rely on the availability of large…

Bidirectional long short-term memory (bi-LSTM) networks have recently proven successful for various NLP sequence modeling tasks, but little is known about their reliance to input representations, target languages, data set size, and label…

Dialectal data are characterized by linguistic variation that appears small to humans but has a significant impact on the performance of models. This dialect gap has been related to various factors (e.g., data size, economic and social…

Current benchmark tasks for natural language processing contain text that is qualitatively different from the text used in informal day to day digital communication. This discrepancy has led to severe performance degradation of…

Over the last few years, deep learning has grown in popularity for speaker verification, identification, and diarization. Inarguably, a significant part of this success is due to the demonstrated effectiveness of their speaker…

Named entity recognition (NER) is a well-established task of information extraction which has been studied for decades. More recently, studies reporting NER experiments on social media texts have emerged. On the other hand, stance detection…

Text from social media provides a set of challenges that can cause traditional NLP approaches to fail. Informal language, spelling errors, abbreviations, and special characters are all commonplace in these posts, leading to a prohibitively…

Choosing an appropriate tokenization scheme is often a bottleneck in low-resource cross-lingual transfer. To understand the downstream implications of text representation choices, we perform a comparative analysis on language models having…

Existing relation classification methods that rely on distant supervision assume that a bag of sentences mentioning an entity pair are all describing a relation for the entity pair. Such methods, performing classification at the bag level,…

Named Entity Recognition (NER) models trained on clean, high-resource corpora exhibit catastrophic performance collapse when deployed on noisy, sparse User-Generated Content (UGC), such as social media. Prior research has predominantly…

Sarcasm, as defined by Merriam-Webster, is the use of words by someone who means the opposite of what he is trying to say. In the field of sentimental analysis of Natural Language Processing, the ability to correctly identify sarcasm is…

With the increased use of social media platforms by people across the world, many new interesting NLP problems have come into existence. One such being the detection of sarcasm in the social media texts. We present a corpus of tweets for…

Large-scale cross-modal pre-training paradigms have recently shown ubiquitous success on a wide range of downstream tasks, e.g., zero-shot classification, retrieval and image captioning. However, their successes highly rely on the scale and…

Fine-tuning neural networks is widely used to transfer valuable knowledge from high-resource to low-resource domains. In a standard fine-tuning scheme, source and target problems are trained using the same architecture. Although capable of…

In this work, we explore the way to perform named entity recognition (NER) using only unlabeled data and named entity dictionaries. To this end, we formulate the task as a positive-unlabeled (PU) learning problem and accordingly propose a…

Despite the huge and continuous advances in computational linguistics, the lack of annotated data for Named Entity Recognition (NER) is still a challenging issue, especially in low-resource languages and when domain knowledge is required…

Name tagging in low-resource languages or domains suffers from inadequate training data. Existing work heavily relies on additional information, while leaving those noisy annotations unexplored that extensively exist on the web. In this…