CS224n Final Project

نویسنده

  • Trevor Standley
چکیده

I introduce a novel method for disambiguating word senses using a semisupervised approach. I contrast this method with the current state-of-the-art approaches and show that my approach performs well and could potentially lead to fully unsupervised approaches with high accuracy.1

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

CS224N Final Project: QA

We extend existing question answering (QA) system to deal with words that are unseen or do not have enough examples during training. Instead of learning word embedding from scratch for a specific QA dataset, we decompose the embedding into two components: The first captures the general semantic meaning of a word and can be trained using readily available large corpuses. The second component rew...

متن کامل

CS224n Final Project Stock Price Prediction Using News Articles

The basic form of efficient market hypothesis postulates that publicly available information is incorporated into stock prices. The stronger form of the hypothesis asserts that all information are immediately reflected in the market as soon as they become available; whereas the weaker form allows a certain lag period in which the information is digested by the public and stock prices move gradu...

متن کامل

Awkwardly: A Response Suggester CS224N Final Project

Replying to emails can be a daunting task especially if users are bombarded with hundreds of emails per day, or if they struggle with constructing well-formed socially acceptable replies. We present Awkwardly, a novel response suggester that generates top replies shown to a user in real-time. These short responses can be selected as a reply in a chat or email context. In this paper, we introduc...

متن کامل

CS224N Final Project: Exploiting the Redundancy in Neural Machine Translation

Neural Machine Translation (NMT) has enjoyed success in recent years, but like many other deep learning domains, typically suffers from over-parameterization, resulting in overfitting and large storage size. We demonstrate the efficacy of weight pruning as a compression and regularization technique. In particular we find that our baseline model can be immediately compressed to 40% of its previo...

متن کامل

Cool-to-Hot Pivoting for Improved Machine Translation

Note: This project presents work in progress with Daniel Cer and Dan Jurafsky; however, all associated code, annotation, linguistic and error analysis, and writing thus far has been done by me alone. Their contribution to this point has been through weekly progress meetings and group brainstorming. Also, since we are planning to submit a later version of this research to ACL in February, I ask ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2015