Articles

We present a new approach to encourage neu- ral machine translation to satisfy lexical con- straints. Our method acts at the training step and thereby avoiding the...

The recent abundance of conversational data on the Web and elsewhere calls for effec- tive NLP systems for dialogue understanding. Complete utterance-level understanding often requires context understanding, partly defined by the nearby utterances and by the user inten- tion and background. In recent years, a num- ber of context-aware approaches …...

Rhetorical implicit emotion identification is one of important and challenging tasks in nat- ural language processing. We observe that each rhetoric may express certain evidence of semantic and syntactic patterns. Then, we design a gate mechanism based classification module to capture respective rhetorical repre- sentation and identify each rhetoric. More- …...

Recent progress has been made in using BERT framework for Chinese spelling error correc- tion (CSC). However, most existing methods correct words based on local contextual in- formation, without considering the influence of error words in sentences. Imposing at- tention on error contextual information could mislead and decrease the overall …...

Neural sequence models can generate highly fluent sentences, but recent studies have also shown that they are also prone to hallucinate additional content not supported by the input. These variety of fluent but wrong outputs are particularly problematic, as it will not be possi- ble for users to tell they …...

We study the problem of injecting knowl- edge into large pre-trained models like BERT and RoBERTa. Existing methods typically update the original parameters of pre-trained models when injecting knowledge. However, when multiple kinds of knowledge are injected, the historically injected knowledge would be flushed away. To address this, we propose …...

Fully non-autoregressive neural machine trans- lation (NAT) simultaneously predicts tokens with single forward of neural networks, which significantly reduces the inference latency at the expense of quality drop compared to the Transformer baseline. In this work, we target on closing the performance gap while main- taining the latency advantage. We …...

While social media becomes a primary source of news now, it also becomes more challeng- ing for people to distinguish the rumors and non-rumors, which attracts malicious manip- ulation and may lead to public health harm or economic loss. Consequently, many ru- mor detection models have been proposed to automatically …...

Document-level relation extraction aims to de- tect the relations within one document, which is challenging since it requires complex rea- soning using mentions, entities, local and global contexts. Few previous studies have dis- tinguished local and global reasoning explic- itly, which may be problematic because they play different roles in …...

Aspect sentiment classification (ASC) aims at determining sentiments expressed towards dif- ferent aspects in a sentence. While state-of- the-art ASC models have achieved remarkable performance, they are recently shown to suffer from the issue of robustness. Particularly in two common scenarios: when domains of test and training data are different …...

Graph Attention Networks (GATs) have proven a promising model that takes advantage of localized attention mechanism to perform knowledge representation learning (KRL) on graph-structure data, e.g., Knowledge Graphs (KGs). While such approaches model entities’ local pairwise importance, they lack the capa- bility to model global importance relative to other entities …...

Identifying events and mapping them to a pre-defined taxonomy of event types has long been an important NLP problem. Most previ- ous work has relied heavily on labor-intensive, domain-specific, annotation, ignoring the se- mantic meaning of the event types’ labels. Consequently, the learned models cannot ef- fectively generalize to new …...

Recently, driven by numerous publicly available machine reading comprehension (MRC) datasets, MRC systems have made some progress. These datasets, however, have two major limitations: 1) the defined tasks are relatively simple, and 2) they do not provide explainable evaluation which is crit- ical to objectively and comprehensively review the reasoning …...

Distantly supervised (DS) relation extraction (RE) has attracted much attention in the past few years as it can utilize large-scale auto- labeled data. However, its evaluation has long been a problem: previous works either take costly and inconsistent methods to manually examine a small sample of model predictions, or directly …...

Automated program repair (APR) aims to find an automatic solution to program lan- guage bugs without human intervention, and it can potentially reduce debugging costs and improve software quality. Conven- tional approaches adopt learning-based meth- ods such as sequence-to-sequence models for the patches generation. However, they tend to ignore the …...

In this paper, we introduce the new task of con- trollable text edition, in which we take as input a long text, a question, and a target answer, and the output is a minimally modified text, so that it fits the target answer. This task is very impor- tant in …...

Recently, deep neural networks (DNNs) have achieved great success in semantically chal- lenging NLP tasks, yet it remains unclear whether DNN models can capture composi- tional meanings, those aspects of meaning that have been long studied in formal semantics. To investigate this issue, we propose a Sys- tematic Generalization testbed …...

Target meaning representations for semantic parsing tasks are often based on programming or query languages, such as SQL, and can be formalized by a context-free grammar. As- suming a priori knowledge of the target do- main, such grammars can be exploited to en- force syntactical constraints when predicting logical forms. …...

Despite considerable advancements with deep neural language models (LMs), neural text generation still suffers from degeneration: the generated text is repetitive, generic, self- contradictory, and often lacks commonsense. Our analyses on sentence-level attention pat- terns in LMs reveal that neural degeneration may be associated with insufficient learning of task-specific characteristics …...

Model-agnostic meta-learning (MAML) has been recently put forth as a strategy to learn resource-poor languages in a sample-efficient fashion. Nevertheless, the properties of these languages are often not well represented by those available during training. Hence, we argue that the i.i.d. assumption ingrained in MAML makes it ill-suited for cross-lingual …...