What’s Hot in Human Language Technology: Highlights from NAACL HLT 2015

Authors: Joyce Chai, Anoop Sarkar, Rada Mihalcea

AAAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental An approach based on HMM, together with a deep convolutional neural network (CNN) classifier for food detection, was developed and evaluated in a cooking domain (Malmaud et al. 2015). As alignment is often the first step in many problems involving language and vision, these approaches and empirical results provide important baselines for future work on this topic. They have incorporated models learned from a large scale image data to the video domain and resulted in state-of-the-art performance on a benchmark dataset for video to text generation. The results have shown the method is more effective than joint training across a number of common tasks. The evaluations of this method have shown significant improvements across six different languages.
Researcher Affiliation Academia Joyce Y. Chai Computer Science and Engineering Michigan State University East Lansing, MI 48824, USA jchai@cse.msu.edu Anoop Sarkar Computer Science Simon Fraser University Burnaby, BC V5A 1S6, Canada anoop@sfu.ca Rada Mihalcea Computer Science and Engineering University of Michigan Ann Arbor, MI 48109, USA mihalcea@umich.edu
Pseudocode No This paper is a conference highlights summary and does not contain any pseudocode or algorithm blocks.
Open Source Code No This paper is a conference highlights summary and does not present its own methodology or provide concrete access to source code for it. It mentions
Open Datasets No This paper is a conference highlights summary and does not conduct its own experiments or use a specific dataset that it makes publicly available. It mentions other papers using
Dataset Splits No This paper is a conference highlights summary and does not conduct its own experiments; therefore, it does not provide training/test/validation dataset splits.
Hardware Specification No This paper is a conference highlights summary and does not conduct its own experiments; therefore, it does not specify any hardware used for running experiments.
Software Dependencies No This paper is a conference highlights summary and does not conduct its own experiments; therefore, it does not list any specific software dependencies with version numbers needed for replication.
Experiment Setup No This paper is a conference highlights summary and does not conduct its own experiments; therefore, it does not provide details about experimental setup or hyperparameters.