WS 2017

Explaining Recurrent Neural Network Predictions in Sentiment Analysis

WS 2017 ArrasL/LRP_for_LSTM

Recently, a technique called Layer-wise Relevance Propagation (LRP) was shown to deliver insightful explanations in the form of input space relevances for understanding feed-forward neural network classification decisions.

INTERPRETABLE MACHINE LEARNING SENTIMENT ANALYSIS

Arc-Hybrid Non-Projective Dependency Parsing with a Static-Dynamic Oracle

WS 2017 UppsalaNLP/uuparser

In this paper, we extend the arc-hybrid system for transition-based parsing with a swap transition that enables reordering of the words and construction of non-projective trees.

DEPENDENCY PARSING

A Multi-task Approach for Named Entity Recognition in Social Media Data

WS 2017 tavo91/NER-WNUT17

Named Entity Recognition for social media data is challenging because of its inherent noisiness.

NAMED ENTITY RECOGNITION

Shakespearizing Modern Language Using Copy-Enriched Sequence to Sequence Models

WS 2017 harsh19/Shakespearizing-Modern-English

Variations in writing styles are commonly used to adapt the content to a specific context, audience, or purpose.

End-to-End Information Extraction without Token-Level Supervision

WS 2017 rasmusbergpalm/e2e-ie-release

End-to-end (E2E) models, which take raw text as input and produce the desired output directly, need not depend on token-level labels.

Seernet at EmoInt-2017: Tweet Emotion Intensity Estimator

WS 2017 SEERNET/EmoInt

The paper describes experiments on estimating emotion intensity in tweets using a generalized regressor system.

Massively Multilingual Neural Grapheme-to-Phoneme Conversion

WS 2017 bpopeters/mg2p

Grapheme-to-phoneme conversion (g2p) is necessary for text-to-speech and automatic speech recognition systems.

SPEECH RECOGNITION

What is the Role of Recurrent Neural Networks (RNNs) in an Image Caption Generator?

WS 2017 mtanti/rnn-role

This view suggests that the RNN should only be used to encode linguistic features and that only the final representation should be `merged' with the image features at a later stage.

IMAGE CAPTIONING