Through quantitative evaluation of the linguistic quality, we observe that the dialog generation model - DialoGPT (345M) with transfer learning on video data attains scores similar to a human response baseline.
The platform features a fully modular video sentiment analysis framework consisting of data management, feature extraction, model training, and result analysis modules.
On the one hand, the existing methods have limitations in learning robust representations to detect the open intent without any prior knowledge.
Specifically, supervised contrastive learning based on a memory bank is first used to train each new task so that the model can effectively learn the relation representation.
no code implementations • 20 Oct 2021 • Sijia Liu, Andrew Wen, LiWei Wang, Huan He, Sunyang Fu, Robert Miller, Andrew Williams, Daniel Harris, Ramakanth Kavuluru, Mei Liu, Noor Abu-el-rub, Dalton Schutte, Rui Zhang, Masoud Rouhizadeh, John D. Osborne, Yongqun He, Umit Topaloglu, Stephanie S Hong, Joel H Saltz, Thomas Schaffter, Emily Pfaff, Christopher G. Chute, Tim Duong, Melissa A. Haendel, Rafael Fuentes, Peter Szolovits, Hua Xu, Hongfang Liu, Natural Language Processing, Subgroup, National COVID Cohort Collaborative
Although we use COVID-19 as a use case in this effort, our framework is general enough to be applied to other domains of interest in clinical NLP.
As a result, deep learning models developed for sequence modeling, like recurrent neural networks (RNNs) are common architecture for EHR-based clinical events predictive models.
It is composed of two main modules: open intent detection and open intent discovery.
no code implementations • 4 Aug 2021 • Greg M. Silverman, Raymond L. Finzel, Michael V. Heinz, Jake Vasilakes, Jacob C. Solinsky, Reed McEwan, Benjamin C. Knoll, Christopher J. Tignanelli, Hongfang Liu, Hua Xu, Xiaoqian Jiang, Genevieve B. Melton, Serguei VS Pakhomov
Our objective in this study is to investigate the behavior of Boolean operators on combining annotation output from multiple Natural Language Processing (NLP) systems across multiple corpora and to assess how filtering by aggregation of Unified Medical Language System (UMLS) Metathesaurus concepts affects system performance for Named Entity Recognition (NER) of UMLS concepts.
With the rapid growth of qubit numbers and coherence times in quantum hardware technology, implementing shallow neural networks on the so-called Noisy Intermediate-Scale Quantum (NISQ) devices has attracted a lot of interest.
MATERIALS AND METHODS: We created SemRepDS (an extension of SemRep), capable of extracting semantic relations from abstracts by leveraging a DS-specific terminology (iDISK) containing 28, 884 DS terms not found in the UMLS.
Joint entity and relation extraction is an essential task in information extraction, which aims to extract all relational triples from unstructured text.
Ranked #2 on Relation Extraction on SemEval-2010 Task 8
On MOSI and MOSEI datasets, our method surpasses the current state-of-the-art methods.
In this paper, we propose a post-processing method to learn the adaptive decision boundary (ADB) for open intent classification.
Ranked #1 on Open Intent Detection on BANKING77 (25%known)
In this work, we propose an effective method, Deep Aligned Clustering, to discover new intents with the aid of the limited known intent data.
Ranked #1 on Open Intent Discovery on CLINC150
In this paper, we propose the Cross-Modal BERT (CM-BERT), which relies on the interaction of text and audio modality to fine-tune the pre-trained BERT model.
Ranked #1 on Multimodal Sentiment Analysis on MOSI
To this end, this study aims at adapting the existing CLAMP natural language processing tool to quickly build COVID-19 SignSym, which can extract COVID-19 signs/symptoms and their 8 attributes (body location, severity, temporal expression, subject, condition, uncertainty, negation, and course) from clinical text.
Previous studies in multimodal sentiment analysis have used limited datasets, which only contain unified multimodal annotations.
In this paper, we try to give a more visual and detailed definition of structural hole spanner based on the existing work, and propose a novel algorithm to identify structural hole spanner based on community forest model and diminishing marginal utility.
Background: Identifying relationships between clinical events and temporal expressions is a key challenge in meaningfully analyzing clinical text for use in advanced AI applications.
In this paper, we propose SofterMax and deep novelty detection (SMDN), a simple yet effective post-processing method for detecting unknown intent in dialogue systems based on pre-trained deep neural network classifiers.
Identifying new user intents is an essential task in the dialogue system.
Ranked #1 on Open Intent Discovery on SNIPS
Developing high-performance entity normalization algorithms that can alleviate the term variation problem is of great interest to the biomedical community.
With margin loss, we can learn discriminative deep features by forcing the network to maximize inter-class variance and to minimize intra-class variance.
Ranked #1 on Open Intent Detection on SNIPS (25% known)
When developing topic classifiers for real-world applications, we begin by defining a set of meaningful topic labels.
We explore a battery of embedding methods consisting of traditional word embeddings and contextual embeddings, and compare these on four concept extraction corpora: i2b2 2010, i2b2 2012, SemEval 2014, and SemEval 2015.
Ranked #1 on Clinical Concept Extraction on 2010 i2b2/VA