In this work, we address the open-world classification problem with a method called ODIST, open world classification via distributionally shifted instances.
The accurate representation of fine-detailed cloth wrinkles poses significant challenges in computer graphics.
Evaluating Large Language Models (LLMs) is a complex task, especially considering the intricacies of natural language understanding and the expectations for high-level reasoning.
Parameter Efficient Tuning has been an prominent approach to adapt the Large Language Model to downstream tasks.
In the era of large language models (LLMs), this study explores the ability of LLMs to deliver accurate critiques across various tasks.
Large Language Models (LLMs) have demonstrated impressive capabilities for text rewriting.
Large Language Models (LLMs) have demonstrated impressive zero-shot capabilities in long-form text generation tasks expressed through natural language instructions.
This paper shows that the existing methods are suboptimal and proposes a novel method to perform a more informed adaptation of the knowledge in the LM by (1) soft-masking the attention heads based on their importance to best preserve the general knowledge in the LM and (2) contrasting the representations of the general and the full (both general and domain knowledge) to learn an integrated representation with both general and domain-specific knowledge.
Recent work on applying large language models (LMs) achieves impressive performance in many NLP applications.
Ranked #1 on Continual Pretraining on AG News
In many practical scenarios, this is not the case because there are unknowns or unseen class samples in the test data, which is called the open set scenario, and the unknowns need to be detected.
First, we measure and analyze model update regression in different model update settings.
Aspect-based sentiment analysis (ABSA) typically requires in-domain annotated data for supervised training/fine-tuning.
In this setting, the CL system learns a sequence of SC tasks incrementally in a neural network, where each task builds a classifier to classify the sentiment of reviews of a particular product category or domain.
Ranked #4 on Continual Learning on DSC (10 tasks)
Although several papers have tried to deal with both CF and KT, our experiments show that they suffer from serious CF when the tasks do not have much shared knowledge.
Ranked #1 on Continual Learning on DSC (10 tasks)
The key novelty is a contrastive continual learning method that enables both knowledge transfer across tasks and knowledge distillation from old tasks to the new task, which eliminates the need for task ids in testing.
Masked language models (MLMs) such as BERT and RoBERTa have revolutionized the field of Natural Language Understanding in the past few years.
Tea chrysanthemum detection at its flowering stage is one of the key components for selective chrysanthemum harvesting robot development.
Pre-trained language models have been recently shown to benefit task-oriented dialogue (TOD) systems.
In an out-of-distribution (OOD) detection problem, samples of known classes(also called in-distribution classes) are used to train a special classifier.
Most features in the representation of an aspect are dedicated to the fine-grained semantics of the domain (or product category) and the aspect itself, instead of carrying summarized opinions from its context.
This work introduces Focused-Variation Network (FVN), a novel model to control language generation.
This paper focuses on learning domain-oriented language models driven by end tasks, which aims to combine the worlds of both general-purpose language models (such as ELMo and BERT) and domain-specific language understanding.
Aspect-based sentiment classification (ASC) is an important task in fine-grained sentiment analysis.~Deep supervised ASC approaches typically model this task as a pair-wise classification task that takes an aspect and a sentence containing the aspect and outputs the polarity of the aspect in that sentence.
It is based on a simple and practical yet very effective sequence-to-sequence approach, where language understanding and state tracking tasks are modeled jointly with a structured copy-augmented sequential decoder and a multi-label decoder for each slot.
Since ReviewRC has limited training examples for RRC (and also for aspect-based sentiment analysis), we then explore a novel post-training approach on the popular language model BERT to enhance the performance of fine-tuning of BERT for RRC.
Inspired by conversational reading comprehension (CRC), this paper studies a novel task of leveraging reviews as a source to build an agent that can answer multi-turn questions from potential consumers of online businesses.
Classic supervised learning makes the closed-world assumption, meaning that classes seen in testing must have been seen in training.
Unlike other highly sophisticated supervised deep learning models, this paper proposes a novel and yet simple CNN model employing two types of pre-trained embeddings for aspect extraction: general-purpose embeddings and domain-specific embeddings.
We study the problem of stock related question answering (StockQA): automatically generating answers to stock related questions, just like professional stock analysts providing action recommendations to stocks upon user's requests.
We observe that domains are not isolated and a small domain corpus can leverage the learned knowledge from many past domains to augment that corpus in order to generate high-quality embeddings.
Product compatibility and their functionality are of utmost importance to customers when they purchase products, and to sellers and manufacturers when they sell products.
As learning is used increasingly in dynamic open environments where some new/test documents may not belong to any of the training classes, identifying these novel documents during classification presents an important problem.
Extracting opinion targets is an important task in sentiment analysis on product reviews and complementary entities (products) are one important type of opinion targets that may work together with the reviewed product.
When "screen" appears in a review of a new domain (or product), it is likely to be an aspect too.
In this paper, we address the problem of extracting compatible and incompatible products from yes/no questions in PCQA.
One important product feature is the complementary entity (products) that may potentially work together with the reviewed product.