Search Results for author:
Found 30 papers, 17 papers with code
kFolden: k-Fold Ensemble for Out-Of-Distribution Detection
Out-of-Distribution (OOD) detection is an important problem in natural language processing (NLP).
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
+2
A General Framework for Defending Against Backdoor Attacks via Influence Graph
In this work, we propose a new and general framework to defend against backdoor attacks, inspired by the fact that attack triggers usually follow a \textsc{specific} type of attacking pattern, and therefore, poisoned training examples have greater impacts on each other during training.
Interpreting Deep Learning Models in Natural Language Processing: A Review
Neural network models have achieved state-of-the-art performances in a wide range of natural language processing (NLP) tasks.
GNN-LM: Language Modeling based on Global Contexts via GNN
Inspired by the notion that ``{\it to copy is easier than to memorize}``, in this work, we introduce GNN-LM, which extends the vanilla neural language model (LM) by allowing to reference similar contexts in the entire training corpus.
BadPre: Task-agnostic Backdoor Attacks to Pre-trained NLP Foundation Models
The key feature of our attack is that the adversary does not need prior information about the downstream tasks when implanting the backdoor to the pre-trained model.
OpenViDial 2.0: A Larger-Scale, Open-Domain Dialogue Generation Dataset with Visual Contexts
In order to better simulate the real human conversation process, models need to generate dialogue utterances based on not only preceding textual contexts but also visual contexts.
Ranked #1 on
Multi-modal Dialogue Generation
on OpenViDial 2.0
An MRC Framework for Semantic Role Labeling
We formalize predicate disambiguation as multiple-choice machine reading comprehension, where the descriptions of candidate senses of a given predicate are used as options to select the correct sense.
Ranked #1 on
Semantic Role Labeling
on CoNLL 2005
Paraphrase Generation as Unsupervised Machine Translation
Then based on the paraphrase pairs produced by these UMT models, a unified surrogate model can be trained to serve as the final \sts model to generate paraphrases, which can be directly used for test in the unsupervised setup, or be finetuned on labeled datasets in the supervised setup.
ConRPG: Paraphrase Generation using Contexts as Regularizer
A long-standing issue with paraphrase generation is how to obtain reliable supervision signals.
$k$Folden: $k$-Fold Ensemble for Out-Of-Distribution Detection
For a task with $k$ training labels, $k$Folden induces $k$ sub-models, each of which is trained on a subset with $k-1$ categories with the left category masked unknown to the sub-model.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
+2
Layer-wise Model Pruning based on Mutual Information
The proposed pruning strategy offers merits over weight-based pruning techniques: (1) it avoids irregular memory access since representations and matrices can be squeezed into their smaller but dense counterparts, leading to greater speedup; (2) in a manner of top-down pruning, the proposed method operates from a more global perspective based on training signals in the top layer, and prunes each layer by propagating the effect of global signals through layers, leading to better performances at the same sparsity level.
ChineseBERT: Chinese Pretraining Enhanced by Glyph and Pinyin Information
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.
Defending Against Backdoor Attacks in Natural Language Generation
The frustratingly fragile nature of neural network models make current natural language generation (NLG) systems prone to backdoor attacks and generate malicious sequences that could be sexist or offensive.
Modeling Text-visual Mutual Dependency for Multi-modal Dialog Generation
Specifically, we propose to model the mutual dependency between text-visual features, where the model not only needs to learn the probability of generating the next dialog utterance given preceding dialog utterances and visual contexts, but also the probability of predicting the visual features in which a dialog utterance takes place, leading the generated dialog utterance specific to the visual context.
Fast Nearest Neighbor Machine Translation
Fast $k$NN-MT constructs a significantly smaller datastore for the nearest neighbor search: for each word in a source sentence, Fast $k$NN-MT first selects its nearest token-level neighbors, which is limited to tokens that are the same as the query token.
Parameter Estimation for the SEIR Model Using Recurrent Nets
Next, based on this recurrent net that is able to generalize SEIR simulations, we are able to transform the objective to a differentiable one with respect to $\Theta_\text{SEIR}$, and straightforwardly obtain its optimal value.
Sentence Similarity Based on Contexts
The proposed framework is based on the core idea that the meaning of a sentence should be defined by its contexts, and that sentence similarity can be measured by comparing the probabilities of generating two sentences given the same context.
Dependency Parsing as MRC-based Span-Span Prediction
The proposed method has the following merits: (1) it addresses the fundamental problem that edges in a dependency tree should be constructed between subtrees; (2) the MRC framework allows the method to retrieve missing spans in the span proposal stage, which leads to higher recall for eligible spans.
BertGCN: Transductive Text Classification by Combining GCN and BERT
In this work, we propose BertGCN, a model that combines large scale pretraining and transductive learning for text classification.
Ranked #1 on
Text Classification
on 20 Newsgroups
OpenViDial: A Large-Scale, Open-Domain Dialogue Dataset with Visual Contexts
Based on this dataset, we propose a family of encoder-decoder models leveraging both textual and visual contexts, from coarse-grained image features extracted from CNNs to fine-grained object features extracted from Faster R-CNNs.
Self-Explaining Structures Improve NLP Models
The proposed model comes with the following merits: (1) span weights make the model self-explainable and do not require an additional probing model for interpretation; (2) the proposed model is general and can be adapted to any existing deep learning structures in NLP; (3) the weight associated with each text span provides direct importance scores for higher-level text units such as phrases and sentences.
Ranked #2 on
Sentiment Analysis
on SST-5 Fine-grained classification
(using extra training data)
Neural Semi-supervised Learning for Text Classification Under Large-Scale Pretraining
The goal of semi-supervised learning is to utilize the unlabeled, in-domain dataset U to improve models trained on the labeled dataset D. Under the context of large-scale language-model (LM) pretraining, how we can make the best use of U is poorly understood: is semi-supervised learning still beneficial with the presence of large-scale pretraining?
Ranked #3 on
Text Classification
on IMDb
Summarize, Outline, and Elaborate: Long-Text Generation via Hierarchical Supervision from Extractive Summaries
The difficulty of generating coherent long texts lies in the fact that existing models overwhelmingly focus on predicting local words, and cannot make high level plans on what to generate or capture the high-level discourse dependencies between chunks of texts.
Dice Loss for Data-imbalanced NLP Tasks
Many NLP tasks such as tagging and machine reading comprehension are faced with the severe data imbalance issue: negative examples significantly outnumber positive examples, and the huge number of background examples (or easy-negative examples) overwhelms the training.
Ranked #1 on
Chinese Named Entity Recognition
on OntoNotes 4
(using extra training data)
Chinese Named Entity Recognition
Machine Reading Comprehension
+5
Is Word Segmentation Necessary for Deep Learning of Chinese Representations?
Based on these observations, we conduct comprehensive experiments to study why word-based models underperform char-based models in these deep learning-based NLP tasks.
Glyce: Glyph-vectors for Chinese Character Representations
However, due to the lack of rich pictographic evidence in glyphs and the weak generalization ability of standard computer vision models on character data, an effective way to utilize the glyph information remains to be found.
Ranked #1 on
Chinese Word Segmentation
on AS
Chinese Dependency Parsing
Chinese Named Entity Recognition
+19
Enhanced Network Embeddings via Exploiting Edge Labels
Network embedding methods aim at learning low-dimensional latent representation of nodes in a network.
Social and Information Networks Physics and Society
A General Framework for Content-enhanced Network Representation Learning
This paper investigates the problem of network embedding, which aims at learning low-dimensional vector representation of nodes in networks.
