Synthetic biologists and molecular programmers design novel nucleic acid reactions, with many potential applications.
Visualization tools can help synthetic biologists and molecular programmers understand the complex reactive pathways of nucleic acid reactions, which can be designed for many potential applications and can be modelled using a continuous-time Markov chain (CTMC).
Aligning EM density maps and fitting atomic models are essential steps in single particle cryogenic electron microscopy (cryo-EM), with recent methods leveraging various algorithms and machine learning tools.
While Chain-of-Thought prompting is popular in reasoning tasks, its application to Large Language Models (LLMs) in Natural Language Understanding (NLU) is under-explored.
Recent advanced methods in Natural Language Understanding for Task-oriented Dialogue (TOD) Systems (e. g., intent detection and slot filling) require a large amount of annotated data to achieve competitive performance.
Particularly, we propose unsupervised alignment objectives to capture (1) local one-to-one alignment between the two different modalities, (2) alignment via multi-modality contexts to leverage information from additional modalities, and (3) alignment via multilingual contexts where additional bilingual dictionaries are incorporated.
We propose Concept2Box, a novel approach that jointly embeds the two views of a KG using dual geometric representations.
Information extraction, e. g., attribute value extraction, has been extensively studied and formulated based only on text.
These techniques neither preserve the semantic consistency of the original sentences when rule-based augmentations are adopted, nor preserve the syntax structure of sentences when expressing relations using seq2seq models, resulting in less diverse augmentations.
We present a new task setting for attribute mining on e-commerce products, serving as a practical solution to extract open-world attributes without extensive human intervention.
Relation extraction (RE) aims to extract potential relations according to the context of two entities, thus, deriving rational contexts from sentences plays an important role.
Low-Resource Information Extraction (LRIE) strives to use unsupervised data, reducing the required resources and human annotation.
Unsupervised relation extraction aims to extract the relationship between entities from natural language sentences without prior information on relational scope or distribution.
Most prior works on this matter mine new values for a set of known attributes but cannot handle new attributes that arose from constantly changing data.
Low-resource Relation Extraction (LRE) aims to extract relation facts from limited labeled corpora when human annotation is scarce.
In Science of Science, few studies have looked at scientific collaboration from the perspective of team power dynamics.
Specifically, we jointly train two modules with different inductive biases -- a text analysis module for text understanding and a network learning module for class-discriminative, scalable network learning.
Although recent works demonstrate that multi-level matching plays an important role in transferring learned knowledge from seen training classes to novel testing classes, they rely on a static similarity measure and overly fine-grained matching components.
To alleviate human efforts from obtaining large-scale annotations, Semi-Supervised Relation Extraction methods aim to leverage unlabeled data in addition to learning from limited samples.
Unlike most other QA tasks that focus on linguistic understanding, HeadQA requires deeper reasoning involving not only knowledge extraction, but also complex reasoning with healthcare knowledge.
no code implementations • 24 Jun 2020 • Xin Luna Dong, Xiang He, Andrey Kan, Xi-An Li, Yan Liang, Jun Ma, Yifan Ethan Xu, Chenwei Zhang, Tong Zhao, Gabriel Blanco Saldana, Saurabh Deshpande, Alexandre Michetti Manduca, Jay Ren, Surender Pal Singh, Fan Xiao, Haw-Shiuan Chang, Giannis Karamanolakis, Yuning Mao, Yaqing Wang, Christos Faloutsos, Andrew McCallum, Jiawei Han
Can one build a knowledge graph (KG) for all products in the world?
We propose to distantly train a sequence labeling model for term extraction and employ graph neural networks (GNNs) to capture the taxonomy structure as well as the query-item-taxonomy interactions for term attachment.
Open relation extraction is the task of extracting open-domain relation facts from natural language sentences.
In this paper, we formulate a more realistic and difficult problem setup for the intent detection task in natural language understanding, namely Generalized Few-Shot Intent Detection (GFSID).
We present a multi-filtering Graph Convolution Neural Network (GCN) framework for network embedding task.
Distributed representations of medical concepts have been used to support downstream clinical tasks recently.
We formalize networks with evolving structures as temporal networks and propose a generative link prediction model, Generative Link Sequence Modeling (GLSM), to predict future links for temporal networks.
Predicting patient mortality is an important and challenging problem in the healthcare domain, especially for intensive care unit (ICU) patients.
Distributed representations have been used to support downstream tasks in healthcare recently.
During the iterations, our model updates the parallel policies and the corresponding scenario-based regrets for agents simultaneously.
To improve the quality and retrieval performance of the generated questions, we make two major improvements: 1) To better encode the semantics of ill-formed questions, we enrich the representation of questions with character embedding and the recent proposed contextual word embedding such as BERT, besides the traditional context-free word embeddings; 2) To make it capable to generate desired questions, we train the model with deep reinforcement learning techniques that considers an appropriate wording of the generation as an immediate reward and the correlation between generated question and answer as time-delayed long-term rewards.
In particular, four problems are studied in this dissertation: Structured Intent Detection for Natural Language Understanding, Structure-aware Natural Language Modeling, Generative Structured Knowledge Expansion, and Synonym Refinement on Structured Knowledge.
This paper presents a novel framework, MGNER, for Multi-Grained Named Entity Recognition where multiple entities or entity mentions in a sentence could be non-overlapping or totally nested.
Ranked #5 on Nested Mention Recognition on ACE 2005
Online knowledge libraries refer to the online data warehouses that systematically organize and categorize the knowledge-based information about different kinds of concepts and entities.
Being able to automatically discover synonymous entities in an open-world setting benefits various tasks such as entity disambiguation or knowledge graph canonicalization.
Being able to recognize words as slots and detect the intent of an utterance has been a keen issue in natural language understanding.
Ranked #7 on Slot Filling on ATIS
After a thorough investigation of an online movie knowledge library, a novel movie planning framework "Blockbuster Planning with Maximized Movie Configuration Acquaintance" (BigMovie) is introduced in this paper.
Patients who have medical information demands tend to post questions about their health conditions on these crowdsourced Q&A websites and get answers from other users.
Being able to automatically discover synonymous entities from a large free-text corpus has transformative effects on structured knowledge discovery.
In this paper, we focus on a new Named Entity Recognition (NER) task, i. e., the Multi-grained NER task.
The increasing use of electronic forms of communication presents new opportunities in the study of mental health, including the ability to investigate the manifestations of psychiatric diseases unobtrusively and in the setting of patients' daily lives.
Social media has grown to be a crucial information source for pharmacovigilance studies where an increasing number of people post adverse reactions to medical drugs that are previously unreported.
Online healthcare services can provide the general public with ubiquitous access to medical knowledge and reduce the information access cost for both individuals and societies.
The closeness among users in the networks are defined as the meta proximity scores, which will be fed into DIME to learn the embedding vectors of users in the emerging network.
Social and Information Networks Databases
The healthcare status, complex medical information needs of patients are expressed diversely and implicitly in their medical text queries.
We propose a novel multi-source hierarchical prediction consolidation method to effectively exploits the complicated hierarchical label structures to resolve the noisy and conflicting information that inherently originates from multiple imperfect sources.