Articles

Filtering target-irrelevant information through hierarchically refining hidden states has been demonstrated to be effective for obtaining in- formative representations. However, previous work simply relies on locally normalized at- tention without considering possible labels at other time steps, the capacity for modeling long-term dependency relations is thus limited. In this paper, …...

Many task-oriented dialogue systems use deep reinforcement learning (DRL) to learn policies that respond to the user appropriately and com- plete the tasks successfully. Training DRL agents with diverse dialogue trajectories pre- pare them well for rare user requests and un- seen situations. One effective diversification method is to let …...

It is well known that human is not good at de- ception detection because of a natural inclina- tion of truth-bias. However, during a conversa- tion, when an interlocutor (interrogator) is be- ing asked explicitly to assess whether his/her interacting partner (deceiver) is lying, this per- ceptual judgment depends highly …...

There is a recent interest in investigating few- shot NER, where the low-resource target do- main has different label sets compared with a resource-rich source domain. Existing meth- ods use a similarity-based metric. However, they cannot make full use of knowledge trans- fer in NER model parameters. To address the …...

While synthetic bilingual corpora have demon- strated their effectiveness in low-resource neu- ral machine translation (NMT), adding more synthetic data often deteriorates translation performance. In this work, we propose al- ternated training with synthetic and authen- tic data for NMT. The basic idea is to al- ternate synthetic and authentic …...

This paper focuses on utilizing metaphor inter- pretation to enhance metaphor detection. Con- sidering that existing approaches to metaphor interpretation are limited by ambiguous mean- ings of the metaphorical substitute words, this paper proposes a novel interpretation mechanism that utilizes glosses to interpret metaphorical words. Since there is no dataset …...

Topic models are effective in capturing the la- tent semantics of large-scale textual data while existing methods are normally designed and evaluated on balanced corpora. However, it contradicts the fact that general corpora in our world are naturally long-tailed, and the long- tailed bias can highly impair the topic model- …...

Named Entity Recognition (NER) is a key Natural Language Processing task. However, most existing work on NER targets flat named entities (NEs) and ignores the recognition of nested structures, where entities can be en- closed within other NEs. Moreover, evaluation of Nested Named Entity Recognition (NNER) across domains remains challenging, …...

Applying reinforcement learning to dialogue policy learning requires prohibitively large rounds of human-machine interactions. To improve the learning performance, the Deep Dyna-Q framework with a world model that imitates real users is widely used in recent years. Unfortunately, how to build an effec- tive world model and how to evaluate …...

In the pursuit of a deeper understanding of a model’s behaviour, there is recent impetus for developing suites of probes aimed at di- agnosing models beyond simple metrics like accuracy or BLEU. This paper takes a step back and asks an important and timely ques- tion: how reliable are these …...

Topic modeling is an unsupervised method for revealing the hidden semantic structure of a corpus. It has been increasingly widely adopted as a tool in the social sciences, in- cluding political science, digital humanities and sociological research in general. One desirable property of topic models is to al- low users …...

ion, Concretization and Completion Jie Zhou1,2∗, Shengding Hu1,2∗, Xin Lv1,2, Cheng Yang4, Zhiyuan Liu1,2,3†, Wei Xu5, Jie Jiang5, Juanzi Li1,2, Maosong Sun1,2,3 1Department of Computer Science and Technology 2Institute for Artificial Intelligence 3State Key Lab on Intelligent Technology and Systems, Tsinghua University, Beijing, China 4School of Computer Science, Beijing University …...

With pre-trained models, such as BERT, gain- ing more and more attention, plenty of re- search has been done to further promote their capabilities, from enhancing the experimental procedures (Sun et al., 2019) to improving the mathematical principles. In this paper, we pro- pose a concise method for improving BERT’s …...

BERT has been studied as a promising tech- nique to improve NMT. Given that BERT is based on the similar Transformer architecture to NMT and the current datasets for most MT tasks are rather large, how pre-training has managed to outperform standard Transformer NMT models is underestimated. We compare MT …...

The major paradigm of applying a pre-trained language model to downstream tasks is to fine- tune it on labeled task data, which often suf- fers instability and low performance when the labeled examples are scarce. One way to alle- viate this problem is to apply post-training on unlabeled task data …...

Cross-lingual pre-training aims at providing effective prior representations for the inputs from multiple languages. With the model- ing of bidirectional contexts, recently preva- lent language modeling approaches such as XLM achieve better performance than tradi- tional methods based on embedding align- ment, which strives to assign similar vector representations to …...

Recent work has proposed several efficient ap- proaches for generating gradient-based adver- sarial perturbations on embeddings and proved that the model’s performance and robustness can be improved when they are trained with these contaminated embeddings. While they paid little attention to how to help the model to learn these adversarial …...

Unsupervised extractive summarization aims to extract salient sentences from documents without labeled corpus. Existing methods are mostly graph-based by computing sentence centrality. These methods usually tend to select sentences within the same facet, how- ever, which often leads to the facet bias prob- lem especially when the document has mul- …...

Continuous representations of linguistic struc- tures are an important part of modern natu- ral language processing systems. Despite the diversity, most of the existing log-multilinear embedding models are organized under vector operations. However, these operations can not precisely represent the compositionality of nat- ural language due to a lack of …...

Scientific document understanding is challeng- ing as the data is highly domain specific and diverse. However, datasets for tasks with scien- tific text require expensive manual annotation and tend to be small and limited to only one or a few fields. At the same time, scientific docu- ments contain many …...