In this paper, we investigate the unified ABSA task from the perspective of Machine Reading Comprehension (MRC) by observing that the aspect and the opinion terms can serve as the query and answer in MRC interchangeably.
It has been widely recognized that syntax information can help end-to-end neural machine translation (NMT) systems to achieve better translation.
In practice, a set of formulaic alphas is often used together for better modeling precision, so we need to find synergistic formulaic alpha sets that work well together.
Recently, a series of pioneer studies have shown the potency of pre-trained models in sequential recommendation, illuminating the path of building an omniscient unified pre-trained recommendation model for different downstream recommendation tasks.
A singing voice conversion model converts a song in the voice of an arbitrary source singer to the voice of a target singer.
In this work, we improve an accent-conversion model (ACM) which transforms native US-English speech into accented pronunciation.
Most people who have tried to learn a foreign language would have experienced difficulties understanding or speaking with a native speaker's accent.
Text-based voice editing (TBVE) uses synthetic output from text-to-speech (TTS) systems to replace words in an original recording.
This framework integrates engineering dynamics and deep learning technologies and may reveal a new concept for CDEs solving and uncertainty propagation.
In this paper, we propose two key points for CRS to improve the user experience: (1) Speaking like a human, human can speak with different styles according to the current dialogue context.
However, both strategies are faced with some immediate problems: raw features cannot represent various properties of nodes (e. g., structure information), and representations learned by supervised GNN may suffer from the poor performance of the classifier on the poisoned graph.
Specifically, we build the personalized soft prefix prompt via a prompt generator based on user profiles and enable a sufficient training of prompts via a prompt-oriented contrastive learning with both prompt- and behavior-based augmentations.
In this work, we define the selective fairness task, where users can flexibly choose which sensitive attributes should the recommendation model be bias-free.
In this work, we highlight that the user's historical dialogue sessions and look-alike users are essential sources of user preferences besides the current dialogue session in CRS.
Ranked #3 on Recommendation Systems on ReDial
In this work, we propose a novel network structure that combines CNN and Transformer for the segmentation of COVID-19 lesions.
We argue that MBR models should: (1) model the coarse-grained commonalities between different behaviors of a user, (2) consider both individual sequence view and global graph view in multi-behavior modeling, and (3) capture the fine-grained differences between multiple behaviors of a user.
Based on this, we present Multi-Representation Adaptation Network (MRAN) to accomplish the cross-domain image classification task via multi-representation alignment which can capture the information from different aspects.
Thus, in this paper, we further propose a transfer framework to tackle the cross-domain fraud detection problem, which aims to transfer knowledge from existing domains (source domains) with enough and mature data to improve the performance in the new domain (target domain).
Many prediction tasks of real-world applications need to model multi-order feature interactions in user's event sequence for better detection performance.
To this end, in this paper, we propose a novel neural network approach to identify the missing POI categories by integrating both bi-directional global non-personal transition patterns and personal preferences of users.
Then, target temporal pattern in combination with user and POI information are fed into a multi-layer network to capture users' dynamic preferences.
Domain adaptation tasks such as cross-domain sentiment classification aim to utilize existing labeled data in the source domain and unlabeled or few labeled data in the target domain to improve the performance in the target domain via reducing the shift between the data distributions.
The proposed model encodes the textual information in queries, documents and the KG with multilingual BERT, and incorporates the KG information in the query-document matching process with a hierarchical information fusion mechanism.
We perform a subjective and objective evaluation to compare the performance of each vocoder along a different axis.
To this end, in this paper, we aim to discern the decision-making processes of neural networks through a hierarchical voting strategy by developing an explainable deep learning model, namely Voting Transformation-based Explainable Neural Network (VOTEN).
This will lead to low-quality and unreliable representations of KGs.
Specifically, a meta network fed with users' characteristic embeddings is learned to generate personalized bridge functions to achieve personalized transfer of preferences for each user.
Constrained Reinforcement Learning (CRL) burgeons broad interest in recent years, which pursues both goals of maximizing long-term returns and constraining costs.
A long-standing issue with paraphrase generation is how to obtain reliable supervision signals.
The delayed feedback problem is one of the imperative challenges in online advertising, which is caused by the highly diversified feedback delay of a conversion varying from a few minutes to several days.
To build up a benchmark for this problem, we publicize a large-scale dataset named PENS (PErsonalized News headlineS).
The proposed method is efficient as it can make decisions on-the-fly by utilizing only one randomly chosen model, but is also effective as we show that it can be viewed as a non-Bayesian approximation of Thompson sampling.
When target text transcripts are available, we design a joint speech and text training framework that enables the model to generate dual modality output (speech and text) simultaneously in the same inference pass.
Recent pretraining models in Chinese neglect two important aspects specific to the Chinese language: glyph and pinyin, which carry significant syntax and semantic information for language understanding.
The adaptation can be achieved easily with most feed-forward network models by extending them with LMMD loss, which can be trained efficiently via back-propagation.
The encoder can automatically construct the population graph using phenotypic measures which have a positive impact on the final results, and further realizes the fusion of multimodal information.
With the advantage of meta learning which has good generalization ability to novel tasks, we propose a transfer-meta framework for CDR (TMCDR) which has a transfer stage and a meta stage.
Graph-based fraud detection approaches have escalated lots of attention recently due to the abundant relational information of graph-structured data, which may be beneficial for the detection of fraudsters.
Ranked #4 on Fraud Detection on Amazon-Fraud
Typical high quality text-to-speech (TTS) systems today use a two-stage architecture, with a spectrum model stage that generates spectral frames and a vocoder stage that generates the actual audio.
However, in real-world applications, few-shot learning paradigm often suffers from data shift, i. e., samples in different tasks, even in the same task, could be drawn from various data distributions.
More efficient variants of FBWave can achieve up to 109x fewer MACs while still delivering acceptable audio quality.
In complex and noisy settings, model-based RL tends to have trouble using the model if it does not know when to trust the model.
In this paper, we propose the Dual Importance-aware Factorization Machines (DIFM), which exploits the internal field information among users' behavior sequence from dual perspectives, i. e., field value variations and field interactions simultaneously for fraud detection.
In this paper, we propose a Graph Factorization Machine (GFM) which utilizes the popular Factorization Machine to aggregate multi-order interactions from neighborhood for recommendation.
On the one hand, we investigate the proposed algorithms by focusing on how the papers utilize the knowledge graph for accurate and explainable recommendation.
The transfer learning toolkit wraps the codes of 17 transfer learning models and provides integrated interfaces, allowing users to use those models by calling a simple function.
In order to show the performance of different transfer learning models, over twenty representative transfer learning models are used for experiments.
In this work, we re-examine the problem of extractive text summarization for long documents.
Ranked #8 on Extractive Text Summarization on CNN / Daily Mail
Existing multi-view learning methods based on kernel function either require the user to select and tune a single predefined kernel or have to compute and store many Gram matrices to perform multiple kernel learning.
In real world machine learning applications, testing data may contain some meaningful new categories that have not been seen in labeled training data.
Aspect extraction relies on identifying aspects by discovering coherence among words, which is challenging when word meanings are diversified and processing on short texts.
Detecting inaccurate smart meters and targeting them for replacement can save significant resources.
It is often observed that the probabilistic predictions given by a machine learning model can disagree with averaged actual outcomes on specific subsets of data, which is also known as the issue of miscalibration.
To enrich the generated responses, ARM introduces a large number of molecule-mechanisms as various responding styles, which are conducted by taking different combinations from a few atom-mechanisms.
We propose Meta-Embedding, a meta-learning-based approach that learns to generate desirable initial embeddings for new ad IDs.
Medical image segmentation has become an essential technique in clinical and research-oriented applications.
Model-free reinforcement learning methods such as the Proximal Policy Optimization algorithm (PPO) have successfully applied in complex decision-making problems such as Atari games.
To this end, in this paper, we extend existing KGE models TransE, TransH and DistMult, to learn knowledge representations by leveraging the information from the HRS.
Additionally, a "low-level sharing, high-level splitting" structure of CNN is designed to handle the documents from different content domains.
An effective technique for filtering free-rider episodes is using a partition model to divide an episode into two consecutive subepisodes and comparing the observed support of such episode with its expected support under the assumption that these two subepisodes occur independently.
We evaluate PGCR on toy datasets as well as a real-world dataset of personalized music recommendations.
Then, with a proposed tree-structured search method, the model is able to generate the most probable responses in the form of dependency trees, which are finally flattened into sequences as the system output.