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

Chrome logo Add to Chrome

Firefox logo Add to Firefox

"Topic": models, code, and papers

Improving Tweet Representations using Temporal and User Context

Dec 19, 2016
Ganesh J, Manish Gupta, Vasudeva Varma

In this work we propose a novel representation learning model which computes semantic representations for tweets accurately. Our model systematically exploits the chronologically adjacent tweets ('context') from users' Twitter timelines for this task. Further, we make our model user-aware so that it can do well in modeling the target tweet by exploiting the rich knowledge about the user such as the way the user writes the post and also summarizing the topics on which the user writes. We empirically demonstrate that the proposed models outperform the state-of-the-art models in predicting the user profile attributes like spouse, education and job by 19.66%, 2.27% and 2.22% respectively.

* To be presented at European Conference on Information Retrieval (ECIR) 2017 

  Access Paper or Ask Questions

A Surrogate-based Generic Classifier for Chinese TV Series Reviews

Nov 21, 2016
Yufeng Ma, Long Xia, Wenqi Shen, Mi Zhou, Weiguo Fan

With the emerging of various online video platforms like Youtube, Youku and LeTV, online TV series' reviews become more and more important both for viewers and producers. Customers rely heavily on these reviews before selecting TV series, while producers use them to improve the quality. As a result, automatically classifying reviews according to different requirements evolves as a popular research topic and is essential in our daily life. In this paper, we focused on reviews of hot TV series in China and successfully trained generic classifiers based on eight predefined categories. The experimental results showed promising performance and effectiveness of its generalization to different TV series.

* submitted to IDD 

  Access Paper or Ask Questions

Modeling Rich Contexts for Sentiment Classification with LSTM

May 05, 2016
Minlie Huang, Yujie Cao, Chao Dong

Sentiment analysis on social media data such as tweets and weibo has become a very important and challenging task. Due to the intrinsic properties of such data, tweets are short, noisy, and of divergent topics, and sentiment classification on these data requires to modeling various contexts such as the retweet/reply history of a tweet, and the social context about authors and relationships. While few prior study has approached the issue of modeling contexts in tweet, this paper proposes to use a hierarchical LSTM to model rich contexts in tweet, particularly long-range context. Experimental results show that contexts can help us to perform sentiment classification remarkably better.

  Access Paper or Ask Questions

A State of the Art of Word Sense Induction: A Way Towards Word Sense Disambiguation for Under-Resourced Languages

Oct 05, 2013
Mohammad Nasiruddin

Word Sense Disambiguation (WSD), the process of automatically identifying the meaning of a polysemous word in a sentence, is a fundamental task in Natural Language Processing (NLP). Progress in this approach to WSD opens up many promising developments in the field of NLP and its applications. Indeed, improvement over current performance levels could allow us to take a first step towards natural language understanding. Due to the lack of lexical resources it is sometimes difficult to perform WSD for under-resourced languages. This paper is an investigation on how to initiate research in WSD for under-resourced languages by applying Word Sense Induction (WSI) and suggests some interesting topics to focus on.

* 14 pages TALN/RECITAL 2013 

  Access Paper or Ask Questions

ELQA: A Corpus of Questions and Answers about the English Language

May 01, 2022
Shabnam Behzad, Keisuke Sakaguchi, Nathan Schneider, Amir Zeldes

We introduce a community-sourced dataset for English Language Question Answering (ELQA), which consists of more than 180k questions and answers on numerous topics about English language such as grammar, meaning, fluency, and etymology. The ELQA corpus will enable new NLP applications for language learners. We introduce three tasks based on the ELQA corpus: 1) answer quality classification, 2) semantic search for finding similar questions, and 3) answer generation. We present baselines for each task along with analysis, showing the strengths and weaknesses of current transformer-based models. The ELQA corpus and scripts are publicly available for future studies.

  Access Paper or Ask Questions

Exploring Latent Dimensions of Crowd-sourced Creativity

Dec 13, 2021
Umut Kocasari, Alperen Bag, Efehan Atici, Pinar Yanardag

Recently, the discovery of interpretable directions in the latent spaces of pre-trained GANs has become a popular topic. While existing works mostly consider directions for semantic image manipulations, we focus on an abstract property: creativity. Can we manipulate an image to be more or less creative? We build our work on the largest AI-based creativity platform, Artbreeder, where users can generate images using pre-trained GAN models. We explore the latent dimensions of images generated on this platform and present a novel framework for manipulating images to make them more creative. Our code and dataset are available at

* 5th Workshop on Machine Learning for Creativity and Design (NeurIPS 2021), Sydney, Australia 

  Access Paper or Ask Questions

The AI Triplet: Computational, Conceptual, and Mathematical Representations in AI Education

Oct 14, 2021
Maithilee Kunda

Expertise in AI requires integrating computational, conceptual, and mathematical knowledge and representations. We propose this trifecta as an "AI triplet," similar in spirit to the "chemistry triplet" that has influenced the past four decades of chemistry education. We describe a rationale for this triplet and how it maps onto topics commonly taught in AI courses, such as tree search and gradient descent. Also, similar to impacts of the chemistry triplet on chemistry education, we suggest an initial example of how considering the AI triplet may help pinpoint obstacles in AI education, i.e., how student learning might be scaffolded to approach expert-level flexibility in moving between the points of the triplet.

  Access Paper or Ask Questions

Proceedings of ICML 2021 Workshop on Theoretic Foundation, Criticism, and Application Trend of Explainable AI

Jul 26, 2021
Quanshi Zhang, Tian Han, Lixin Fan, Zhanxing Zhu, Hang Su, Ying Nian Wu, Jie Ren, Hao Zhang

This is the Proceedings of ICML 2021 Workshop on Theoretic Foundation, Criticism, and Application Trend of Explainable AI. Deep neural networks (DNNs) have undoubtedly brought great success to a wide range of applications in computer vision, computational linguistics, and AI. However, foundational principles underlying the DNNs' success and their resilience to adversarial attacks are still largely missing. Interpreting and theorizing the internal mechanisms of DNNs becomes a compelling yet controversial topic. This workshop pays a special interest in theoretic foundations, limitations, and new application trends in the scope of XAI. These issues reflect new bottlenecks in the future development of XAI.

  Access Paper or Ask Questions

Zero-Shot Clinical Acronym Expansion with a Hierarchical Metadata-Based Latent Variable Model

Sep 29, 2020
Griffin Adams, Mert Ketenci, Adler Perotte, Noemie Elhadad

We introduce Latent Meaning Cells, a deep latent variable model which learns contextualized representations of words by combining local lexical context and metadata. Metadata can refer to granular context, such as section type, or to more global context, such as unique document ids. Reliance on metadata for contextualized representation learning is apropos in the clinical domain where text is semi-structured and expresses high variation in topics. We evaluate the LMC model on the task of clinical acronym expansion across three datasets. The LMC significantly outperforms a diverse set of baselines at a fraction of the pre-training cost and learns clinically coherent representations.

* 31 pages 

  Access Paper or Ask Questions