WS 2019

BERT has a Mouth, and It Must Speak: BERT as a Markov Random Field Language Model

WS 2019 nyu-dl/bert-gen

We show that BERT (Devlin et al., 2018) is a Markov random field language model.

LANGUAGE MODELLING

Publicly Available Clinical BERT Embeddings

WS 2019 EmilyAlsentzer/clinicalBERT

Contextual word embedding models such as ELMo (Peters et al., 2018) and BERT (Devlin et al., 2018) have dramatically improved performance for many natural language processing (NLP) tasks in recent months.

Probing Biomedical Embeddings from Language Models

WS 2019 Andy-jqa/bioelmo

For this we use the pre-trained LMs as fixed feature extractors and restrict the downstream task models to not have additional sequence modeling layers.

WORD EMBEDDINGS

A Discourse Signal Annotation System for RST Trees

WS 2019 amir-zeldes/rstweb

This paper presents a new system for open-ended discourse relation signal annotation in the framework of Rhetorical Structure Theory (RST), implemented on top of an online tool for RST annotation.

Identification, Interpretability, and Bayesian Word Embeddings

WS 2019 adamlauretig/bwe

Social scientists have recently turned to analyzing text using tools from natural language processing like word embeddings to measure concepts like ideology, bias, and affinity.

LATENT VARIABLE MODELS WORD EMBEDDINGS

Revisiting NMT for Normalization of Early English Letters

WS 2019 mikahama/natas

This paper studies the use of NMT (neural machine translation) as a normalization method for an early English letter corpus.

LEMMATIZATION MACHINE TRANSLATION

Parallelizable Stack Long Short-Term Memory

WS 2019 shuoyangd/hoolock

Stack Long Short-Term Memory (StackLSTM) is useful for various applications such as parsing and string-to-tree neural machine translation, but it is also known to be notoriously difficult to parallelize for GPU training due to the fact that the computations are dependent on discrete operations.

MACHINE TRANSLATION

Clustering-Based Article Identification in Historical Newspapers

WS 2019 riedlma/cluster_identification

This article focuses on the problem of identifying articles and recovering their text from within and across newspaper pages when OCR just delivers one text file per page.

OPTICAL CHARACTER RECOGNITION WORD EMBEDDINGS

Neural Vector Conceptualization for Word Vector Space Interpretation

WS 2019 dfki-nlp/nvc

Distributed word vector spaces are considered hard to interpret which hinders the understanding of natural language processing (NLP) models.

Jointly Measuring Diversity and Quality in Text Generation Models

WS 2019 Ehsan-MAE/TextGenerationEvaluationMetrics

In this paper, we propose metrics to evaluate both the quality and diversity simultaneously by approximating the distance of the learned generative model and the real data distribution.

TEXT GENERATION