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

Discovering Chatbot's Self-Disclosure's Impact on User Trust, Affinity, and Recommendation Effectiveness

Jun 03, 2021
Kai-Hui Liang, Weiyan Shi, Yoojung Oh, Jingwen Zhang, Zhou Yu

In recent years, chatbots have been empowered to engage in social conversations with humans and have the potential to elicit people to disclose their personal experiences, opinions, and emotions. However, how and to what extent people respond to chabots' self-disclosure remain less known. In this work, we designed a social chatbot with three self-disclosure levels that conducted small talks and provided relevant recommendations to people. 372 MTurk participants were randomized to one of the four groups with different self-disclosure levels to converse with the chatbot on two topics, movies, and COVID-19. We found that people's self-disclosure level was strongly reciprocal to a chatbot's self-disclosure level. Chatbots' self-disclosure also positively impacted engagement and users' perception of the bot and led to a more effective recommendation such that participants enjoyed and agreed more with the recommendations.


  Access Paper or Ask Questions

Mitigating Temporal-Drift: A Simple Approach to Keep NER Models Crisp

Apr 20, 2021
Shuguang Chen, Leonardo Neves, Thamar Solorio

Performance of neural models for named entity recognition degrades over time, becoming stale. This degradation is due to temporal drift, the change in our target variables' statistical properties over time. This issue is especially problematic for social media data, where topics change rapidly. In order to mitigate the problem, data annotation and retraining of models is common. Despite its usefulness, this process is expensive and time-consuming, which motivates new research on efficient model updating. In this paper, we propose an intuitive approach to measure the potential trendiness of tweets and use this metric to select the most informative instances to use for training. We conduct experiments on three state-of-the-art models on the Temporal Twitter Dataset. Our approach shows larger increases in prediction accuracy with less training data than the alternatives, making it an attractive, practical solution.

* Accepted to SocialNLP at NAACL 2021 

  Access Paper or Ask Questions

An effective and friendly tool for seed image analysis

Mar 31, 2021
Andrea Loddo, Cecilia Di Ruberto, A. M. P. G. Vale, Mariano Ucchesu, J. M. Soares, Gianluigi Bacchetta

Image analysis is an essential field for several topics of life sciences, such as biology or botany. In particular, seeds analysis (e.g., fossil research) can provide significant information about their evolution, the history of agriculture, the domestication of plants, and the knowledge of diets in ancient times. This work aims to present a software that performs an image analysis by feature extraction and classification starting from images containing seeds through a brand new and unique framework. In detail, we propose two \emph{ImageJ} plugins, one capable of extracting morphological, textural, and colour characteristics from images of seeds, and another one to classify the seeds into categories by using the extracted features. The experimental results demonstrated the correctness and validity both of the extracted features and the classification predictions. The proposed tool is easily extendable to other fields of image analysis.


  Access Paper or Ask Questions

TopicBERT for Energy Efficient Document Classification

Oct 15, 2020
Yatin Chaudhary, Pankaj Gupta, Khushbu Saxena, Vivek Kulkarni, Thomas Runkler, Hinrich Schütze

Prior research notes that BERT's computational cost grows quadratically with sequence length thus leading to longer training times, higher GPU memory constraints and carbon emissions. While recent work seeks to address these scalability issues at pre-training, these issues are also prominent in fine-tuning especially for long sequence tasks like document classification. Our work thus focuses on optimizing the computational cost of fine-tuning for document classification. We achieve this by complementary learning of both topic and language models in a unified framework, named TopicBERT. This significantly reduces the number of self-attention operations - a main performance bottleneck. Consequently, our model achieves a 1.4x ($\sim40\%$) speedup with $\sim40\%$ reduction in $CO_2$ emission while retaining $99.9\%$ performance over 5 datasets.

* EMNLP2020 (Findings): 9 pages, 5 figures, 8 Tables 

  Access Paper or Ask Questions

Transfer Learning and Distant Supervision for Multilingual Transformer Models: A Study on African Languages

Oct 07, 2020
Michael A. Hedderich, David Adelani, Dawei Zhu, Jesujoba Alabi, Udia Markus, Dietrich Klakow

Multilingual transformer models like mBERT and XLM-RoBERTa have obtained great improvements for many NLP tasks on a variety of languages. However, recent works also showed that results from high-resource languages could not be easily transferred to realistic, low-resource scenarios. In this work, we study trends in performance for different amounts of available resources for the three African languages Hausa, isiXhosa and Yor\`ub\'a on both NER and topic classification. We show that in combination with transfer learning or distant supervision, these models can achieve with as little as 10 or 100 labeled sentences the same performance as baselines with much more supervised training data. However, we also find settings where this does not hold. Our discussions and additional experiments on assumptions such as time and hardware restrictions highlight challenges and opportunities in low-resource learning.

* Accepted at EMNLP'20 

  Access Paper or Ask Questions

CoCon: A Self-Supervised Approach for Controlled Text Generation

Jun 05, 2020
Alvin Chan, Yew-Soon Ong, Bill Pung, Aston Zhang, Jie Fu

Pretrained Transformer-based language models (LMs) display remarkable natural language generation capabilities. With their immense potential, controlling text generation of such LMs is getting attention. While there are studies that seek to control high-level attributes (such as sentiment and topic) of generated text, there is still a lack of more precise control over its content at the word- and phrase-level. Here, we propose Content-Conditioner (CoCon) to control an LM's output text with a target content, at a fine-grained level. In our self-supervised approach, the CoCon block learns to help the LM complete a partially-observed text sequence by conditioning with content inputs that are withheld from the LM. Through experiments, we show that CoCon can naturally incorporate target content into generated texts and control high-level text attributes in a zero-shot manner.


  Access Paper or Ask Questions

Unsupervised Injection of Knowledge into Dialogue Generation via Language Models

Apr 30, 2020
Yi-Lin Tuan, Wei Wei, William Yang Wang

Neural conversation models have shown the power to produce more meaningful and engaging responses given external knowledge. Specifically, the knowledge we experiment on is in textual form, for example, a personality description. Despite the success of training and testing with external knowledge, in reality, we do not always have sufficient background knowledge about the discussed topic. Therefore, it is also crucial to have the models generate captivating responses without external knowledge. To achieve this, we propose a unified training method, Decoupling, which induces a knowledge-related sentence and couples it with the dialogue history to generate a response in an unsupervised fashion. Its effect is further analyzed by testing the models with no knowledge, partial and full text of the knowledge. Empirically, we observed that the variance of the performance given different amounts of knowledge is significant. Also, our method performs more closely to the supervised method (the upper bound) than the baselines.


  Access Paper or Ask Questions

Weakly supervised multiple instance learning histopathological tumor segmentation

Apr 21, 2020
Marvin Lerousseau, Maria Vakalopoulou, Marion Classe, Julien Adam, Enzo Battistella, Alexandre Carré, Théo Estienne, Théophraste Henry, Eric Deutsch, Nikos Paragios

Histopathological image segmentation is a challenging and important topic in medical imaging with tremendous potential impact in clinical practice. State of the art methods relying on hand-crafted annotations that reduce the scope of the solutions since digital histology suffers from standardization and samples differ significantly between cancer phenotypes. To this end, in this paper, we propose a weakly supervised framework relying on weak standard clinical practice annotations, available in most medical centers. In particular, we exploit a multiple instance learning scheme providing a label for each instance, establishing a detailed segmentation of whole slide images. The potential of the framework is assessed with multi-centric data experiments using The Cancer Genome Atlas repository and the publicly available PatchCamelyon dataset. Promising results when compared with experts' annotations demonstrate the potentials of our approach.

* 10 pages, 3 figures; added code + results url 

  Access Paper or Ask Questions

Adversarial Genetic Programming for Cyber Security: A Rising Application Domain Where GP Matters

Apr 07, 2020
Una-May O'Reilly, Jamal Toutouh, Marcos Pertierra, Daniel Prado Sanchez, Dennis Garcia, Anthony Erb Luogo, Jonathan Kelly, Erik Hemberg

Cyber security adversaries and engagements are ubiquitous and ceaseless. We delineate Adversarial Genetic Programming for Cyber Security, a research topic that, by means of genetic programming (GP), replicates and studies the behavior of cyber adversaries and the dynamics of their engagements. Adversarial Genetic Programming for Cyber Security encompasses extant and immediate research efforts in a vital problem domain, arguably occupying a position at the frontier where GP matters. Additionally, it prompts research questions around evolving complex behavior by expressing different abstractions with GP and opportunities to reconnect to the Machine Learning, Artificial Life, Agent-Based Modeling and Cyber Security communities. We present a framework called RIVALS which supports the study of network security arms races. Its goal is to elucidate the dynamics of cyber networks under attack by computationally modeling and simulating them.


  Access Paper or Ask Questions

<<
273
274
275
276
277
278
279
280
281
282
283
284
285
>>