Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

"Text": models, code, and papers

Parsing Early Modern English for Linguistic Search

Feb 24, 2020
Seth Kulick, Neville Ryant

We investigate the question of whether advances in NLP over the last few years make it possible to vastly increase the size of data usable for research in historical syntax. This brings together many of the usual tools in NLP - word embeddings, tagging, and parsing - in the service of linguistic queries over automatically annotated corpora. We train a part-of-speech (POS) tagger and parser on a corpus of historical English, using ELMo embeddings trained over a billion words of similar text. The evaluation is based on the standard metrics, as well as on the accuracy of the query searches using the parsed data.

  Access Paper or Ask Questions

Automated Labelling using an Attention model for Radiology reports of MRI scans (ALARM)

Feb 16, 2020
David A. Wood, Jeremy Lynch, Sina Kafiabadi, Emily Guilhem, Aisha Al Busaidi, Antanas Montvila, Thomas Varsavsky, Juveria Siddiqui, Naveen Gadapa, Matthew Townend, Martin Kiik, Keena Patel, Gareth Barker, Sebastian Ourselin, James H. Cole, Thomas C. Booth

Labelling large datasets for training high-capacity neural networks is a major obstacle to the development of deep learning-based medical imaging applications. Here we present a transformer-based network for magnetic resonance imaging (MRI) radiology report classification which automates this task by assigning image labels on the basis of free-text expert radiology reports. Our model's performance is comparable to that of an expert radiologist, and better than that of an expert physician, demonstrating the feasibility of this approach. We make code available online for researchers to label their own MRI datasets for medical imaging applications.

  Access Paper or Ask Questions

Irony Detection in a Multilingual Context

Feb 06, 2020
Bilal Ghanem, Jihen Karoui, Farah Benamara, Paolo Rosso, Véronique Moriceau

This paper proposes the first multilingual (French, English and Arabic) and multicultural (Indo-European languages vs. less culturally close languages) irony detection system. We employ both feature-based models and neural architectures using monolingual word representation. We compare the performance of these systems with state-of-the-art systems to identify their capabilities. We show that these monolingual models trained separately on different languages using multilingual word representation or text-based features can open the door to irony detection in languages that lack of annotated data for irony.

  Access Paper or Ask Questions

Breaking Speech Recognizers to Imagine Lyrics

Dec 15, 2019
Jon Gillick, David Bamman

We introduce a new method for generating text, and in particular song lyrics, based on the speech-like acoustic qualities of a given audio file. We repurpose a vocal source separation algorithm and an acoustic model trained to recognize isolated speech, instead inputting instrumental music or environmental sounds. Feeding the "mistakes" of the vocal separator into the recognizer, we obtain a transcription of words \emph{imagined} to be spoken in the input audio. We describe the key components of our approach, present initial analysis, and discuss the potential of the method for machine-in-the-loop collaboration in creative applications.

* NeurIPS 2019 Workshop on Machine Learning for Creativity and Design 
* 3 pages 

  Access Paper or Ask Questions

Focal Loss based Residual Convolutional Neural Network for Speech Emotion Recognition

Jun 11, 2019
Suraj Tripathi, Abhay Kumar, Abhiram Ramesh, Chirag Singh, Promod Yenigalla

This paper proposes a Residual Convolutional Neural Network (ResNet) based on speech features and trained under Focal Loss to recognize emotion in speech. Speech features such as Spectrogram and Mel-frequency Cepstral Coefficients (MFCCs) have shown the ability to characterize emotion better than just plain text. Further Focal Loss, first used in One-Stage Object Detectors, has shown the ability to focus the training process more towards hard-examples and down-weight the loss assigned to well-classified examples, thus preventing the model from being overwhelmed by easily classifiable examples.

* Accepted in CICLing 2019 

  Access Paper or Ask Questions

Improving End-to-end Speech Recognition with Pronunciation-assisted Sub-word Modeling

Nov 10, 2018
Hainan Xu, Shuoyang Ding, Shinji Watanabe

In recent years, end-to-end models have become popular for application in automatic speech recognition. Compared to hybrid approaches, which perform the phone-sequence to word conversion based on a lexicon, an end-to-end system models text directly, usually as a sequence of characters or sub-word features. We propose a sub-word modeling method that leverages the pronunciation information of a word. Experiments show that the proposed method can greatly improve upon the character-based baseline, and also outperform commonly used byte-pair encoding methods.

  Access Paper or Ask Questions

Linguistic Legal Concept Extraction in Portuguese

Oct 22, 2018
Alessandra Cid, Alexandre Rademaker, Bruno Cuconato, Valeria de Paiva

This work investigates legal concepts and their expression in Portuguese, concentrating on the "Order of Attorneys of Brazil" Bar exam. Using a corpus formed by a collection of multiple-choice questions, three norms related to the Ethics part of the OAB exam, language resources (Princeton WordNet and OpenWordNet-PT) and tools (AntConc and Freeling), we began to investigate the concepts and words missing from our repertory of concepts and words in Portuguese, the knowledge base OpenWordNet-PT. We add these concepts and words to OpenWordNet-PT and hence obtain a representation of these texts that is "contained" in the lexical knowledge base.

* This work was accepted for publication in the JURIX 2018 ( in a short 5-pages version 

  Access Paper or Ask Questions

Extractive Adversarial Networks: High-Recall Explanations for Identifying Personal Attacks in Social Media Posts

Oct 19, 2018
Samuel Carton, Qiaozhu Mei, Paul Resnick

We introduce an adversarial method for producing high-recall explanations of neural text classifier decisions. Building on an existing architecture for extractive explanations via hard attention, we add an adversarial layer which scans the residual of the attention for remaining predictive signal. Motivated by the important domain of detecting personal attacks in social media comments, we additionally demonstrate the importance of manually setting a semantically appropriate `default' behavior for the model by explicitly manipulating its bias term. We develop a validation set of human-annotated personal attacks to evaluate the impact of these changes.

* Accepted to EMNLP 2018 Code and data available at 

  Access Paper or Ask Questions

A Lightweight Music Texture Transfer System

Sep 27, 2018
Xutan Peng, Chen Li, Zhi Cai, Faqiang Shi, Yidan Liu, Jianxin Li

Deep learning researches on the transformation problems for image and text have raised great attention. However, present methods for music feature transfer using neural networks are far from practical application. In this paper, we initiate a novel system for transferring the texture of music, and release it as an open source project. Its core algorithm is composed of a converter which represents sounds as texture spectra, a corresponding reconstructor and a feed-forward transfer network. We evaluate this system from multiple perspectives, and experimental results reveal that it achieves convincing results in both sound effects and computational performance.

* 12 pages 

  Access Paper or Ask Questions

jLDADMM: A Java package for the LDA and DMM topic models

Aug 11, 2018
Dat Quoc Nguyen

In this technical report, we present jLDADMM---an easy-to-use Java toolkit for conventional topic models. jLDADMM is released to provide alternatives for topic modeling on normal or short texts. It provides implementations of the Latent Dirichlet Allocation topic model and the one-topic-per-document Dirichlet Multinomial Mixture model (i.e. mixture of unigrams), using collapsed Gibbs sampling. In addition, jLDADMM supplies a document clustering evaluation to compare topic models. jLDADMM is open-source and available to download at:

  Access Paper or Ask Questions