Search Results for author:
Found 10 papers, 3 papers with code
TalkSumm: A Dataset and Scalable Annotation Method for Scientific Paper Summarization Based on Conference Talks
We collected 1716 papers and their corresponding videos, and created a dataset of paper summaries.
HowSumm: A Multi-Document Summarization Dataset Derived from WikiHow Articles
We present HowSumm, a novel large-scale dataset for the task of query-focused multi-document summarization (qMDS), which targets the use-case of generating actionable instructions from a set of sources.
Ranked #1 on
Document Summarization
on HowSumm-Step
Detector-Free Weakly Supervised Grounding by Separation
In this work, we focus on the task of Detector-Free WSG (DF-WSG) to solve WSG without relying on a pre-trained detector.
Ranked #1 on
Phrase Grounding
on Visual Genome
Joint Learning of Correlated Sequence Labelling Tasks Using Bidirectional Recurrent Neural Networks
The stream of words produced by Automatic Speech Recognition (ASR) systems is typically devoid of punctuations and formatting.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
RNN Fisher Vectors for Action Recognition and Image Annotation
Recurrent Neural Networks (RNNs) have had considerable success in classifying and predicting sequences.
Fisher Vectors Derived from Hybrid Gaussian-Laplacian Mixture Models for Image Annotation
The second Mixture Model presented is a Hybrid Gaussian-Laplacian Mixture Model (HGLMM) which is based on a weighted geometric mean of the Gaussian and Laplacian distribution.
Associating Neural Word Embeddings With Deep Image Representations Using Fisher Vectors
In this work, we are using the Fisher Vector as a sentence representation by pooling the word2vec embedding of each word in the sentence.
Ranked #14 on
Video Retrieval
on YouCook2
A Summarization System for Scientific Documents
We present a novel system providing summaries for Computer Science publications.
orgFAQ: A New Dataset and Analysis on Organizational FAQs and User Questions
Thus, we release orgFAQ, a new dataset composed of $6988$ user questions and $1579$ corresponding FAQs that were extracted from organizations' FAQ webpages in the Jobs domain.
Heuristic-based Inter-training to Improve Few-shot Multi-perspective Dialog Summarization
We observe that there are different heuristics that are associated with summaries of different perspectives, and explore these heuristics to create weak-labeled data for intermediate training of the models before fine-tuning with scarce human annotated summaries.
