Search Results for author:
Found 69 papers, 35 papers with code
When does Further Pre-training MLM Help? An Empirical Study on Task-Oriented Dialog Pre-training
Further pre-training language models on in-domain data (domain-adaptive pre-training, DAPT) or task-relevant data (task-adaptive pre-training, TAPT) before fine-tuning has been shown to improve downstream tasks’ performances.
EARL: Informative Knowledge-Grounded Conversation Generation with Entity-Agnostic Representation Learning
Generating informative and appropriate responses is challenging but important for building human-like dialogue systems.
DecompEval: Evaluating Generated Texts as Unsupervised Decomposed Question Answering
Existing evaluation metrics for natural language generation (NLG) tasks face the challenges on generalization ability and interpretability.
SoK: Comparing Different Membership Inference Attacks with a Comprehensive Benchmark
We have identified three principles for the proposed "comparing different MI attacks" methodology, and we have designed and implemented the MIBench benchmark with 84 evaluation scenarios for each dataset.
KPT: Keyword-guided Pre-training for Grounded Dialog Generation
For the former, the grounding knowledge consists of keywords extracted from the response.
Learning Instructions with Unlabeled Data for Zero-Shot Cross-Task Generalization
Recently, instruction tuning (IT), which fine-tunes a pre-trained language model on a massive collection of tasks described via human-craft instructions, has been shown effective in instruction learning for unseen tasks.
Curriculum-Based Self-Training Makes Better Few-Shot Learners for Data-to-Text Generation
Despite the success of text-to-text pre-trained models in various natural language generation (NLG) tasks, the generation performance is largely restricted by the number of labeled data in downstream tasks, particularly in data-to-text generation tasks.
CTRLEval: An Unsupervised Reference-Free Metric for Evaluating Controlled Text Generation
Existing reference-free metrics have obvious limitations for evaluating controlled text generation models.
EVA2.0: Investigating Open-Domain Chinese Dialogue Systems with Large-Scale Pre-Training
Large-scale pre-training has shown remarkable performance in building open-domain dialogue systems.
Continual Prompt Tuning for Dialog State Tracking
A desirable dialog system should be able to continually learn new skills without forgetting old ones, and thereby adapt to new domains or tasks in its life cycle.
Rethinking and Refining the Distinct Metric
We provide both empirical and theoretical evidence to show that our method effectively removes the biases existing in the original distinct score.
On the Safety of Conversational Models: Taxonomy, Dataset, and Benchmark
We propose a taxonomy for dialogue safety specifically designed to capture unsafe behaviors in human-bot dialogue settings, with focuses on context-sensitive unsafety, which is under-explored in prior works.
EVA: An Open-Domain Chinese Dialogue System with Large-Scale Generative Pre-Training
Although pre-trained language models have remarkably enhanced the generation ability of dialogue systems, open-domain Chinese dialogue systems are still limited by the dialogue data and the model size compared with English ones.
CPM-2: Large-scale Cost-effective Pre-trained Language Models
We present a suite of cost-effective techniques for the use of PLMs to deal with the efficiency issues of pre-training, fine-tuning, and inference.
JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs
Existing pre-trained models for knowledge-graph-to-text (KG-to-text) generation simply fine-tune text-to-text pre-trained models such as BART or T5 on KG-to-text datasets, which largely ignore the graph structure during encoding and lack elaborate pre-training tasks to explicitly model graph-text alignments.
Ranked #1 on
KG-to-Text Generation
on WebQuestions
NAST: A Non-Autoregressive Generator with Word Alignment for Unsupervised Text Style Transfer
First, we observe that most words in the transferred sentence can be aligned with related words in the source sentence, so we explicitly model word alignments to suppress irrelevant words.
A Semantic-based Method for Unsupervised Commonsense Question Answering
In this paper, we present a novel SEmantic-based Question Answering method (SEQA) for unsupervised commonsense question answering.
Ensemble Learning Based Classification Algorithm Recommendation
Recommending appropriate algorithms to a classification problem is one of the most challenging issues in the field of data mining.
A Text GAN for Language Generation with Non-Autoregressive Generator
Despite the great success of Generative Adversarial Networks (GANs) in generating high-quality images, GANs for text generation still face two major challenges: first, most text GANs are unstable in training mainly due to ineffective optimization of the generator, and they heavily rely on maximum likelihood pretraining; second, most text GANs adopt autoregressive generators without latent variables, which largely limits the ability to learn latent representations for natural language text.
CPM: A Large-scale Generative Chinese Pre-trained Language Model
However, applying GPT-3 to address Chinese NLP tasks is still challenging, as the training corpus of GPT-3 is primarily English, and the parameters are not publicly available.
Language Generation with Multi-Hop Reasoning on Commonsense Knowledge Graph
Despite the success of generative pre-trained language models on a series of text generation tasks, they still suffer in cases where reasoning over underlying commonsense knowledge is required during generation.
A Large-Scale Chinese Short-Text Conversation Dataset
The cleaned dataset and the pre-training models will facilitate the research of short-text conversation modeling.
Knowledge-Aided Open-Domain Question Answering
During document retrieval, a candidate document is scored by considering its relationship to the question and other documents.
Learning Goal-oriented Dialogue Policy with Opposite Agent Awareness
Most existing approaches for goal-oriented dialogue policy learning used reinforcement learning, which focuses on the target agent policy and simply treat the opposite agent policy as part of the environment.
KdConv: A Chinese Multi-domain Dialogue Dataset Towards Multi-turn Knowledge-driven Conversation
The research of knowledge-driven conversational systems is largely limited due to the lack of dialog data which consist of multi-turn conversations on multiple topics and with knowledge annotations.
Recent Advances and Challenges in Task-oriented Dialog System
Due to the significance and value in human-computer interaction and natural language processing, task-oriented dialog systems are attracting more and more attention in both academic and industrial communities.
CrossWOZ: A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue Dataset
To advance multi-domain (cross-domain) dialogue modeling as well as alleviate the shortage of Chinese task-oriented datasets, we propose CrossWOZ, the first large-scale Chinese Cross-Domain Wizard-of-Oz task-oriented dataset.
ConvLab-2: An Open-Source Toolkit for Building, Evaluating, and Diagnosing Dialogue Systems
We present ConvLab-2, an open-source toolkit that enables researchers to build task-oriented dialogue systems with state-of-the-art models, perform an end-to-end evaluation, and diagnose the weakness of systems.
CoTK: An Open-Source Toolkit for Fast Development and Fair Evaluation of Text Generation
In text generation evaluation, many practical issues, such as inconsistent experimental settings and metric implementations, are often ignored but lead to unfair evaluation and untenable conclusions.
A Knowledge-Enhanced Pretraining Model for Commonsense Story Generation
To further capture the causal and temporal dependencies between the sentences in a reasonable story, we employ multi-task learning which combines a discriminative objective to distinguish true and fake stories during fine-tuning.
Robust Reading Comprehension with Linguistic Constraints via Posterior Regularization
In this paper, we address the over-confidence issue and the over-sensitivity issue existing in current RC models simultaneously with the help of external linguistic knowledge.
SentiLARE: Sentiment-Aware Language Representation Learning with Linguistic Knowledge
To benefit the downstream tasks in sentiment analysis, we propose a novel language representation model called SentiLARE, which introduces word-level linguistic knowledge including part-of-speech tag and sentiment polarity (inferred from SentiWordNet) into pre-trained models.
Recognition Of Surface Defects On Steel Sheet Using Transfer Learning
Automatic defect recognition is one of the research hotspots in steel production, but most of the current methods mainly extract features manually and use machine learning classifiers to recognize defects, which cannot tackle the situation, where there are few data available to train and confine to a certain scene.
ARAML: A Stable Adversarial Training Framework for Text Generation
The generator is optimized with maximum likelihood estimation augmented by the discriminator's rewards instead of policy gradient.
Long and Diverse Text Generation with Planning-based Hierarchical Variational Model
Existing neural methods for data-to-text generation are still struggling to produce long and diverse texts: they are insufficient to model input data dynamically during generation, to capture inter-sentence coherence, or to generate diversified expressions.
Challenges in Building Intelligent Open-domain Dialog Systems
This paper reviews the recent works on neural approaches that are devoted to addressing three challenges in developing such systems: semantics, consistency, and interactiveness.
Domain-Constrained Advertising Keyword Generation
Second, the inefficient ad impression issue: a large proportion of search queries, which are unpopular yet relevant to many ad keywords, have no ads presented on their search result pages.
Verification Code Recognition Based on Active and Deep Learning
However, the advantages of convolutional neural networks depend on the data used by the training classifier, particularly the size of the training set.
Relation Mention Extraction from Noisy Data with Hierarchical Reinforcement Learning
Experimental results show that our model is effective to extract relation mentions from noisy data.
Learning to Collaborate: Multi-Scenario Ranking via Multi-Agent Reinforcement Learning
The first one is lack of collaboration between scenarios meaning that each strategy maximizes its own objective but ignores the goals of other strategies, leading to a sub-optimal overall performance.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Reinforcement Learning for Relation Classification from Noisy Data
In this paper, we propose a novel model for relation classification at the sentence level from noisy data.
An Operation Network for Abstractive Sentence Compression
Delete-based models have the strong ability to delete undesired words, while generate-based models are able to reorder or rephrase the words, which are more coherent to human sentence compression.
Memory-augmented Dialogue Management for Task-oriented Dialogue Systems
Dialogue management (DM) decides the next action of a dialogue system according to the current dialogue state, and thus plays a central role in task-oriented dialogue systems.
Sentiment Analysis by Capsules
Based on capsule representation, the probability module computes the capsule’s state probability.
Ranked #6 on
Sentiment Analysis
on MR
An Interpretable Reasoning Network for Multi-Relation Question Answering
Multi-relation Question Answering is a challenging task, due to the requirement of elaborated analysis on questions and reasoning over multiple fact triples in knowledge base.
Linguistically Regularized LSTM for Sentiment Classification
This paper deals with sentence-level sentiment classification.
Assigning personality/identity to a chatting machine for coherent conversation generation
Endowing a chatbot with personality or an identity is quite challenging but critical to deliver more realistic and natural conversations.
Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory
Perception and expression of emotion are key factors to the success of dialogue systems or conversational agents.
Context-aware Natural Language Generation for Spoken Dialogue Systems
Most tranditional QA systems based on templates or rules tend to generate rigid and stylised responses without the natural variation of human language.
GAKE: Graph Aware Knowledge Embedding
Knowledge embedding, which projects triples in a given knowledge base to d-dimensional vectors, has attracted considerable research efforts recently.
Product Review Summarization by Exploiting Phrase Properties
The main idea of our method is to leverage phrase properties to choose a subset of optimal phrases for generating the final summary.
Linguistically Regularized LSTMs for Sentiment Classification
In this paper, we propose simple models trained with sentence-level annotation, but also attempt to generating linguistically coherent representations by employing regularizers that model the linguistic role of sentiment lexicons, negation words, and intensity words.
KSR: A Semantic Representation of Knowledge Graph within a Novel Unsupervised Paradigm
Since both aspects and categories are semantics-relevant, the collection of categories in each aspect is treated as the semantic representation of this triple.
SSP: Semantic Space Projection for Knowledge Graph Embedding with Text Descriptions
To this end, this paper proposes a semantic representation method for knowledge graph \textbf{(KSR)}, which imposes a two-level hierarchical generative process that globally extracts many aspects and then locally assigns a specific category in each aspect for every triple.
From One Point to A Manifold: Knowledge Graph Embedding For Precise Link Prediction
Knowledge graph embedding aims at offering a numerical knowledge representation paradigm by transforming the entities and relations into continuous vector space.
TransG : A Generative Mixture Model for Knowledge Graph Embedding
Recently, knowledge graph embedding, which projects symbolic entities and relations into continuous vector space, has become a new, hot topic in artificial intelligence.
TransA: An Adaptive Approach for Knowledge Graph Embedding
Knowledge representation is a major topic in AI, and many studies attempt to represent entities and relations of knowledge base in a continuous vector space.
Margin-Based Feed-Forward Neural Network Classifiers
Margin-Based Principle has been proposed for a long time, it has been proved that this principle could reduce the structural risk and improve the performance in both theoretical and practical aspects.
Max-Entropy Feed-Forward Clustering Neural Network
Entropy-Based Principle is the principle with which we could estimate the unknown distribution under some limited conditions.
Knowlege Graph Embedding by Flexible Translation
TransF regards relation as translation between head entity vector and tail entity vector with flexible magnitude.
