Articles

Meta-learning has emerged as a trending tech- nique to tackle few-shot text classification and achieved state-of-the-art performance. How- ever, existing solutions heavily rely on the ex- ploitation of lexical features and their distri- butional signatures on training data, while ne- glecting to strengthen the model’s ability to adapt to new …...

Document-level relation extraction (DocRE) models generally use graph networks to im- plicitly model the reasoning skill (i.e., pattern recognition, logical reasoning, coreference reasoning, etc.) related to the relation between one entity pair in a document. In this paper, we propose a novel discriminative reasoning framework to explicitly model the paths …...

Named Entity Recognition (NER) is a fun- damental and widely used task in natural language processing (NLP), which is gener- ally trained on the human-annotated corpus. However, data annotation is costly and time- consuming, which restricts its scale and further leads to the performance bottleneck of NER models. In reality, …...

Event detection is a fundamental task in infor- mation extraction. Most previous approaches typically view event detection as a trigger- based classification problem, focusing on us- ing syntactic dependency structure or exter- nal knowledge to boost the classification per- formance. To overcome the inherent issues with existing trigger classification based …...

Adversarial attacks expose important blind spots of deep learning systems. While word- and sentence-level attack scenarios mostly deal with finding semantic paraphrases of the input that fool NLP models, character-level attacks typically insert typos into the input stream. It is commonly thought that these are easier to defend via spelling …...

Zero-resource named entity recognition (NER) severely suffers from data scarcity in a spe- cific domain or language. Most studies on zero-resource NER transfer knowledge from various data by fine-tuning on different aux- iliary tasks. However, how to properly se- lect training data and fine-tuning tasks is still an open problem. …...

Task-oriented dialog (TOD) systems typically manage structured knowledge (e.g. ontologies and databases) to guide the goal-oriented con- versations. However, they fall short of han- dling dialog turns grounded on unstructured knowledge (e.g. reviews and documents). In this paper, we formulate a task of modeling TOD grounded on both structured and …...

Autoregressive models have been widely used in unsupervised text style transfer. Despite their success, these models still suffer from the content preservation problem that they usu- ally ignore part of the source sentence and generate some irrelevant words with strong styles. In this paper, we propose a Non- Autoregressive generator …...

Pretrained language models (PLMs) perform poorly under adversarial attacks. To im- prove the adversarial robustness, adversarial data augmentation (ADA) has been widely adopted to cover more search space of adver- sarial attacks by adding textual adversarial ex- amples during training. However, the num- ber of adversarial examples for text augmen- …...

This paper studies how to automatically gen- erate a natural language text that describes the facts in knowledge graph (KG). Considering the few-shot setting, we leverage the excel- lent capacities of pretrained language models (PLMs) in language understanding and gener- ation. We make three major technical contri- butions, namely representation …...

Meaning Representation (AMR) is a rooted, labeled, acyclic graph representing the semantics of natural language. As previous works show, although AMR is designed for En- glish at first, it can also represent semantics in other languages. However, they find that con- cepts in their predicted AMR graphs are less specific. …...

In recent years, neural paraphrase generation based on Seq2Seq has achieved superior per- formance, however, the generated paraphrase still has the problem of lack of diversity. In this paper, we focus on improving the diver- sity between the generated paraphrase and the original sentence, i.e., making generated para- phrase different …...

Real-world machine learning systems are achieving remarkable performance in terms of coarse-grained metrics like overall accuracy and F-1 score. However, model improvement and development often require fine-grained modeling on individual data subsets or slices, for instance, the data slices where the mod- els have unsatisfactory results. In practice, it gives …...

To train a question answering model based on machine reading comprehension (MRC), sig- nificant effort is required to prepare annotated training data composed of questions and their answers from contexts. Recent research has focused on synthetically generating a question from a given context and an annotated (or gen- erated) answer …...

Question: I have five fingers but I am not alive. What am I? Answer: a glove. Answering such a riddle-style question is a challenging cognitive process, in that it re- quires complex commonsense reasoning abil- ities, an understanding of figurative language, and counterfactual reasoning skills, which are all important abilities …...

Great research interests have been attracted to devise AI services that are able to provide men- tal health support. However, the lack of cor- pora is a main obstacle to this research, par- ticularly in Chinese language. In this paper, we propose PsyQA, a Chinese dataset of psy- chological health …...

Adapting a model to a handful of personal- ized data is challenging, especially when it has gigantic parameters, such as a Transformer- based pretrained model. The standard way of fine-tuning all the parameters necessitates storing a huge model for each user. In this work, we introduce a lightweight approach dubbed …...

Aspect Sentiment Triplet Extraction (ASTE) aims to extract triplets from sentences, where each triplet includes an entity, its associated sentiment, and the opinion span explaining the reason for the sentiment. Most existing re- search addresses this problem in a multi-stage pipeline manner, which neglects the mutual information between such three …...

In this work, we propose BertGCN, a model that combines large scale pretraining and trans- ductive learning for text classification. Bert- GCN constructs a heterogeneous graph over the dataset and represents documents as nodes using BERT representations. By jointly train- ing the BERT and GCN modules within Bert- GCN, the …...

Neural machine translation systems are known to be vulnerable to adversarial test inputs, how- ever, as we show in this paper, these systems are also vulnerable to training attacks. Specifi- cally, we propose a poisoning attack in which a malicious adversary inserts a small poisoned sample of monolingual text into …...