Search Results for author:
Found 9 papers, 3 papers with code
Unsupervised Adaptation of Question Answering Systems via Generative Self-training
Nevertheless, additional pre-training closer to the end-task, such as training on synthetic QA pairs, has been shown to improve performance.
CNNBiF: CNN-based Bigram Features for Named Entity Recognition
More importantly our fine-tuned CoNLL2003 model displays significant gains in generalization to out of domain datasets: on the OntoNotes subset we achieve an F1 of 72. 67 which is 0. 49 points absolute better than the baseline, and on the WNUT16 set an F1 of 68. 22 which is a gain of 0. 48 points.
Fashion IQ: A New Dataset Towards Retrieving Images by Natural Language Feedback
We provide a detailed analysis of the characteristics of the Fashion IQ data, and present a transformer-based user simulator and interactive image retriever that can seamlessly integrate visual attributes with image features, user feedback, and dialog history, leading to improved performance over the state of the art in dialog-based image retrieval.
Dialog-based Interactive Image Retrieval
Experiments on both simulated and real-world data show that 1) our proposed learning framework achieves better accuracy than other supervised and reinforcement learning baselines and 2) user feedback based on natural language rather than pre-specified attributes leads to more effective retrieval results, and a more natural and expressive communication interface.
BlockDrop: Dynamic Inference Paths in Residual Networks
Very deep convolutional neural networks offer excellent recognition results, yet their computational expense limits their impact for many real-world applications.
The IBM 2016 English Conversational Telephone Speech Recognition System
We describe a collection of acoustic and language modeling techniques that lowered the word error rate of our English conversational telephone LVCSR system to a record 6. 6% on the Switchboard subset of the Hub5 2000 evaluation testset.
Ranked #5 on
Speech Recognition
on swb_hub_500 WER fullSWBCH
Random Maxout Features
In this paper, we propose and study random maxout features, which are constructed by first projecting the input data onto sets of randomly generated vectors with Gaussian elements, and then outputing the maximum projection value for each set.
The IBM 2015 English Conversational Telephone Speech Recognition System
We describe the latest improvements to the IBM English conversational telephone speech recognition system.
Ranked #11 on
Speech Recognition
on Switchboard + Hub500
Newton-Like Methods for Sparse Inverse Covariance Estimation
The second approach, which we call the Orthant-Based Newton method, is a two-phase algorithm that first identifies an orthant face and then minimizes a smooth quadratic approximation of the objective function using the conjugate gradient method.
