Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

"Text": models, code, and papers

Recursive Recurrent Nets with Attention Modeling for OCR in the Wild

Mar 09, 2016
Chen-Yu Lee, Simon Osindero

We present recursive recurrent neural networks with attention modeling (R$^2$AM) for lexicon-free optical character recognition in natural scene images. The primary advantages of the proposed method are: (1) use of recursive convolutional neural networks (CNNs), which allow for parametrically efficient and effective image feature extraction; (2) an implicitly learned character-level language model, embodied in a recurrent neural network which avoids the need to use N-grams; and (3) the use of a soft-attention mechanism, allowing the model to selectively exploit image features in a coordinated way, and allowing for end-to-end training within a standard backpropagation framework. We validate our method with state-of-the-art performance on challenging benchmark datasets: Street View Text, IIIT5k, ICDAR and Synth90k.

* accepted at CVPR 2016 

  Access Paper or Ask Questions

Combine CRF and MMSEG to Boost Chinese Word Segmentation in Social Media

Oct 24, 2015
Yao Yushi, Huang Zheng

In this paper, we propose a joint algorithm for the word segmentation on Chinese social media. Previous work mainly focus on word segmentation for plain Chinese text, in order to develop a Chinese social media processing tool, we need to take the main features of social media into account, whose grammatical structure is not rigorous, and the tendency of using colloquial and Internet terms makes the existing Chinese-processing tools inefficient to obtain good performance on social media. In our approach, we combine CRF and MMSEG algorithm and extend features of traditional CRF algorithm to train the model for word segmentation, We use Internet lexicon in order to improve the performance of our model on Chinese social media. Our experimental result on Sina Weibo shows that our approach outperforms the state-of-the-art model.

* 5 pages, 5 tables 

  Access Paper or Ask Questions

Studying the Wikipedia Hyperlink Graph for Relatedness and Disambiguation

Mar 12, 2015
Eneko Agirre, Ander Barrena, Aitor Soroa

Hyperlinks and other relations in Wikipedia are a extraordinary resource which is still not fully understood. In this paper we study the different types of links in Wikipedia, and contrast the use of the full graph with respect to just direct links. We apply a well-known random walk algorithm on two tasks, word relatedness and named-entity disambiguation. We show that using the full graph is more effective than just direct links by a large margin, that non-reciprocal links harm performance, and that there is no benefit from categories and infoboxes, with coherent results on both tasks. We set new state-of-the-art figures for systems based on Wikipedia links, comparable to systems exploiting several information sources and/or supervised machine learning. Our approach is open source, with instruction to reproduce results, and amenable to be integrated with complementary text-based methods.

  Access Paper or Ask Questions

Opinion mining of movie reviews at document level

Aug 17, 2014
Richa Sharma, Shweta Nigam, Rekha Jain

The whole world is changed rapidly and using the current technologies Internet becomes an essential need for everyone. Web is used in every field. Most of the people use web for a common purpose like online shopping, chatting etc. During an online shopping large number of reviews/opinions are given by the users that reflect whether the product is good or bad. These reviews need to be explored, analyse and organized for better decision making. Opinion Mining is a natural language processing task that deals with finding orientation of opinion in a piece of text with respect to a topic. In this paper a document based opinion mining system is proposed that classify the documents as positive, negative and neutral. Negation is also handled in the proposed system. Experimental results using reviews of movies show the effectiveness of the system.

* International Journal on Information Theory (IJIT), Vol.3, No.3, July 2014 

  Access Paper or Ask Questions

Generating Extractive Summaries of Scientific Paradigms

Feb 04, 2014
Vahed Qazvinian, Dragomir R. Radev, Saif M. Mohammad, Bonnie Dorr, David Zajic, Michael Whidby, Taesun Moon

Researchers and scientists increasingly find themselves in the position of having to quickly understand large amounts of technical material. Our goal is to effectively serve this need by using bibliometric text mining and summarization techniques to generate summaries of scientific literature. We show how we can use citations to produce automatically generated, readily consumable, technical extractive summaries. We first propose C-LexRank, a model for summarizing single scientific articles based on citations, which employs community detection and extracts salient information-rich sentences. Next, we further extend our experiments to summarize a set of papers, which cover the same scientific topic. We generate extractive summaries of a set of Question Answering (QA) and Dependency Parsing (DP) papers, their abstracts, and their citation sentences and show that citations have unique information amenable to creating a summary.

* Journal Of Artificial Intelligence Research, Volume 46, pages 165-201, 2013 

  Access Paper or Ask Questions

Design of an Agent for Answering Back in Smart Phones

Jan 01, 2014
Sandeep Venkatesh, Meera V Patil, Nanditha Swamy

The objective of the paper is to design an agent which provides efficient response to the caller when a call goes unanswered in smartphones. The agent provides responses through text messages, email etc stating the most likely reason as to why the callee is unable to answer a call. Responses are composed taking into consideration the importance of the present call and the situation the callee is in at the moment like driving, sleeping, at work etc. The agent makes decisons in the compostion of response messages based on the patterns it has come across in the learning environment. Initially the user helps the agent to compose response messages. The agent associates this message to the percept it recieves with respect to the environment the callee is in. The user may thereafter either choose to make to response system automatic or choose to recieve suggestions from the agent for responses messages and confirm what is to be sent to the caller.

* This paper has been withdrawn by the author due to a crucial sign erro 

  Access Paper or Ask Questions

Summarizing Reviews with Variable-length Syntactic Patterns and Topic Models

Nov 21, 2012
Trung V. Nguyen, Alice H. Oh

We present a novel summarization framework for reviews of products and services by selecting informative and concise text segments from the reviews. Our method consists of two major steps. First, we identify five frequently occurring variable-length syntactic patterns and use them to extract candidate segments. Then we use the output of a joint generative sentiment topic model to filter out the non-informative segments. We verify the proposed method with quantitative and qualitative experiments. In a quantitative study, our approach outperforms previous methods in producing informative segments and summaries that capture aspects of products and services as expressed in the user-generated pros and cons lists. Our user study with ninety users resonates with this result: individual segments extracted and filtered by our method are rated as more useful by users compared to previous approaches by users.

  Access Paper or Ask Questions

A Split-Merge MCMC Algorithm for the Hierarchical Dirichlet Process

Jan 08, 2012
Chong Wang, David M. Blei

The hierarchical Dirichlet process (HDP) has become an important Bayesian nonparametric model for grouped data, such as document collections. The HDP is used to construct a flexible mixed-membership model where the number of components is determined by the data. As for most Bayesian nonparametric models, exact posterior inference is intractable---practitioners use Markov chain Monte Carlo (MCMC) or variational inference. Inspired by the split-merge MCMC algorithm for the Dirichlet process (DP) mixture model, we describe a novel split-merge MCMC sampling algorithm for posterior inference in the HDP. We study its properties on both synthetic data and text corpora. We find that split-merge MCMC for the HDP can provide significant improvements over traditional Gibbs sampling, and we give some understanding of the data properties that give rise to larger improvements.

  Access Paper or Ask Questions

User Guide for KOTE: Korean Online Comments Emotions Dataset

May 11, 2022
Duyoung Jeon, Junho Lee, Cheongtag Kim

Sentiment analysis that classifies data into positive or negative has been dominantly used to recognize emotional aspects of texts, despite the deficit of thorough examination of emotional meanings. Recently, corpora labeled with more than just valence are built to exceed this limit. However, most Korean emotion corpora are small in the number of instances and cover a limited range of emotions. We introduce KOTE dataset. KOTE contains 50k (250k cases) Korean online comments, each of which is manually labeled for 43 emotion labels or one special label (NO EMOTION) by crowdsourcing (Ps = 3,048). The emotion taxonomy of the 43 emotions is systematically established by cluster analysis of Korean emotion concepts expressed on word embedding space. After explaining how KOTE is developed, we also discuss the results of finetuning and analysis for social discrimination in the corpus.

* 16 pages, 4 figures 

  Access Paper or Ask Questions

Music Generation Using an LSTM

Mar 23, 2022
Michael Conner, Lucas Gral, Kevin Adams, David Hunger, Reagan Strelow, Alexander Neuwirth

Over the past several years, deep learning for sequence modeling has grown in popularity. To achieve this goal, LSTM network structures have proven to be very useful for making predictions for the next output in a series. For instance, a smartphone predicting the next word of a text message could use an LSTM. We sought to demonstrate an approach of music generation using Recurrent Neural Networks (RNN). More specifically, a Long Short-Term Memory (LSTM) neural network. Generating music is a notoriously complicated task, whether handmade or generated, as there are a myriad of components involved. Taking this into account, we provide a brief synopsis of the intuition, theory, and application of LSTMs in music generation, develop and present the network we found to best achieve this goal, identify and address issues and challenges faced, and include potential future improvements for our network.

* Published in MICS 2022 

  Access Paper or Ask Questions