Yi-Chen (Howard) Lo
### Summary This paper purposes an approach "Cold Fusion" for leveraging a pre-trained language model **during training** a neural sequence-to-sequence (Seq2Seq) model. In Cold Fusion, the Seq2Seq model is trained...
@ellurunaresh Hi, I am not the author of this paper, so I do not have the code. Please implement by yourself (it seems to be easy by just follow the...
### Motivation to read this paper After I read the paper "Adversarial Contrastive Estimation" (#23), which replaces the original fixed noise generator in noise contrastive estimation (NCE) with the dynamic...
### Summary This paper presents SPIRAL, an adversarially trained RL agent that generates a program which is executed by a graphics engine to interpret and sample images in order to...
### Summary This paper purposed an unsupervised approach to neural machine translation (NMT) using monolingual corpora only. The principle is first use unsupervised word-by-word translation model, iteratively improve this model...
For comparison to the other similar paper: [Unsupervised Neural Machine Translation](https://arxiv.org/pdf/1710.11041.pdf) by Artetex et al. 2017, please refer to the [slides](https://docs.google.com/presentation/d/12yOLpTD7iiNuotJypvpEVvwRTHIDo-t80TXV0othp58/edit?usp=sharing).
### Summary This paper shows that it is possible to infer token-level label based on attention mechanism, despite that the model is only trained on sentence-level classification (binary classification). Evaluation...
### Summary This paper propose a auxiliary bidirectional language modeling objective for neural sequence labeling, and evaluated on error detection in learner texts, name entity recognition (NER), chunking and part-of-speech...
### What is instance co-segmentation?  - Given a set of images jointly covering object instances of a specific category, instance co-segmentation aims to identify all of these instances and...