shagunsodhani

NewsQA: A Machine Comprehension Dataset

Introduction

• The paper presents NewsQA, a machine comprehension dataset of 119,633 natural language questions obtained from 12,744 CNN articles.
• Link to the paper

Issues With Existing Datasets

• Too small - eg MCTest

shagunsodhani

A Persona-Based Neural Conversation Model

Introduction

• The paper presents persona-based models which add coherency to the response generated by sequence-to-senquence models like Neural Conversational Model.
• Link to the paper

Persona

• Defined as the character that an agent performs during conversational interactions.

shagunsodhani

"Why Should I Trust You?": Explaining the Predictions of Any Classifier

Introduction

• The paper introduces a novel technique to explain the predictions of any classifier in an interpretable and faithful manner.
• It also proposes a method to explain models by obtaining representative individual predictions and their explanations.
• Link to the paper
• Demo

Desired Characteristics for Explanations

shagunsodhani

Conditional Generative Adversarial Nets

Introduction

• Conditional version of Generative Adversarial Nets (GAN) where both generator and discriminator are conditioned on some data y (class label or data from some other modality).
• Link to the paper

Architecture

• Feed y into both the generator and discriminator as additional input layers such that y and input are combined in a joint hidden representation.

shagunsodhani

Addressing the Rare Word Problem in Neural Machine Translation

Introduction

• NMT(Neural Machine Translation) systems perform poorly with respect to OOV(out-of-vocabulary) words or rare words.
• The paper presents a word-alignment based technique for translating such rare words.
• Link to the paper

Technique

shagunsodhani

Achieving Open Vocabulary Neural Machine Translation with Hybrid Word-Character Models

Introduction

• The paper presents a novel open vocabulary NMT(Neural Machine Translation) system that translates mostly at word level and falls back to character level models for rare words.
• Advantages:
  • Faster and easier to train as compared to character models.
  • Does not produce unknown words in the translations which need to be removed using unk replacement techniques.
• Link to the paper

shagunsodhani

Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank

Introduction

• The paper introduces:
  • Sentiment Sentiment Treebank - A dataset containing 215,154 phrases with fine-grained sentiment labels (5 classes).
  • Recursive Neural Tensor Network - Model to learn these fine-grained sentiment labels.
• Link to the paper

Sentiment Sentiment Treebank

shagunsodhani

Improving Word Representations via Global Context and Multiple Word Prototypes

Introduction

• This paper pre-dated papers like Glove and Word2Vec and proposed an architecture that
  • combines local and global context while learning word embeddings to capture the word semantics.
  • learns multiple embeddings per word to account for homonymy and polysemy.
• Link to the paper

Global Context-Aware Neural Language Model

shagunsodhani

Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation

Introduction

• The paper proposes a new RNN Encoder-Decoder architecture that can improve the performance of statistical machine translation (SMT) systems.
• Link to the paper

RNN Encoder-Decoder

• Model consists of two RNNs

shagunsodhani

Skip-Thought Vectors

Introduction

• The paper describes an unsupervised approach to train a generic, distributed sentence encoder.
• It also describes a vocabulary expansion method to encode words not seen at training time.
• Link to the paper

Skip-Thoughts