Recently, a lot of research has been carried out to improve the efficiency of Transformer. Among them, the sparse pattern-based method is an important branch of efficient Transformers. However, some existing sparse methods usually use fixed patterns to select words, without considering similarities between words. Other sparse methods use clustering patterns to select words, but the clustering process is separate from the training process of the target task, which causes a decrease in effectiveness. To address these limitations, we design a neural clustering method, which can be seamlessly integrated into the Self-Attention Mechanism in Transformer. The clustering task and the target task are jointly trained and optimized to benefit each other, leading to significant effectiveness improvement. In addition, our method groups the words with strong dependencies into the same cluster and performs the attention mechanism for each cluster independently, which improves the efficiency. We verified our method on machine translation, text classification, natural language inference, and text matching tasks. Experimental results show that our method outperforms two typical sparse attention methods, Reformer and Routing Transformer while having a comparable or even better time and memory efficiency.

We investigate the usage of entity linking (EL)in downstream tasks and present the first modularized EL toolkit for easy task adaptation. Different from the existing EL methods that dealwith all the features simultaneously, we modularize the whole model into separate parts witheach feature. This decoupled design enablesflexibly adding new features without retraining the whole model as well as flow visualization with better interpretability of the ELresult. We release the corresponding toolkit,HOSMEL, for Chinese, with three flexible usage modes, a live demo, and a demonstrationvideo. Experiments on two benchmarks forthe question answering task demonstrate thatHOSMEL achieves much less time and spaceconsumption as well as significantly better accuracy performance compared with existingSOTA EL methods. We hope the release ofHOSMEL will call for more attention to studyEL for downstream tasks in non-English languages.

Fact verification is an essential tool to mitigate the spread of false information online, which has gained a widespread attention recently. However, a fact verification in the question-answering dialogue is still underexplored. In this paper, we propose a neural network based approach called question-answering dialogue based fact verification with mixture of experts (QaDialMoE). It exploits questions and evidence effectively in the verification process and can significantly improve the performance of fact verification. Specifically, we exploit the mixture of experts to focus on various interactions among responses, questions and evidence. A manager with an attention guidance module is implemented to guide the training of experts and assign a reasonable attention score to each expert. A prompt module is developed to generate synthetic questions that make our approach more generalizable. Finally, we evaluate the QaDialMoE and conduct a comparative study on three benchmark datasets. The experimental results demonstrate that our QaDialMoE outperforms previous approaches by a large margin and achieves new state-of-the-art results on all benchmarks. This includes the accuracy improvements on the HEALTHVER as 84.26%, the FAVIQ A dev set as 78.7%, the FAVIQ R dev set as 86.1%, test set as 86.0%, and the COLLOQUIAL as 89.5%. To our best knowledge, this is the first work to investigate a question-answering dialogue based fact verification, and achieves new state-of-the-art results on various benchmark datasets.

Transformer has been demonstrated effective in Neural Machine Translation (NMT). However, it is memory-consuming and time-consuming in edge devices, resulting in some difficulties for real-time feedback. To compress and accelerate Transformer, we propose a Hybrid Tensor-Train (HTT) decomposition, which retains full rank and meanwhile reduces operations and parameters. A Transformer using HTT, named Hypoformer, consistently and notably outperforms the recent light-weight SOTA methods on three standard translation tasks under different parameter and speed scales. In extreme low resource scenarios, Hypoformer has 7.1 points absolute improvement in BLEU and 1.27 X speedup than vanilla Transformer on IWSLT’14 De-En task.

One of the key challenges of knowledge base question answering (KBQA) is the multi-hop reasoning. Since in different hops, one attends to different parts of question, it is important to dynamically represent the question semantics for each hop. Existing methods, however, (i) infer the dynamic question representation only through coarse-grained attention mechanisms, which may bring information loss, (ii) and have not effectively modeled the sequential logic, which is crucial for the multi-hop reasoning process in KBQA.To address these issues, we propose a sequential reasoning self-attention mechanism to capture the crucial reasoning information of each single hop in a more fine-grained way. Based on Gated Recurrent Unit (GRU) which is good at modeling sequential process, we propose a simple but effective GRU-inspired Flow Control (GFC) framework to model sequential logic in the whole multi-hop process.Extensive experiments on three popular benchmark datasets have demonstrated the superior effectiveness of our model. In particular, GFC achieves new state-of-the-art Hits@1 of 76.8% on WebQSP and is also effective when KB is incomplete. Our code and data are available at https://github.com/Xie-Minghui/GFC.

Augmenting pre-trained language models (PLMs) with knowledge graphs (KGs) has demonstrated superior performance on commonsense reasoning. Given a commonsense based QA context (question and multiple choices), existing approaches usually estimate the plausibility of candidate choices separately based on their respective retrieved KGs, without considering the interference among different choices. In this paper, we propose an Attention guided Commonsense rEasoning Network (ACENet) to endow the neural network with the capability of integrating hybrid knowledge. Specifically, our model applies the multi-layer interaction of answer choices to continually strengthen correct choice information and guide the message passing of GNN. In addition, we also design a mix attention mechanism of nodes and edges to iteratively select supporting evidence on hybrid knowledge graph. Experimental results demonstrate the effectiveness of our proposed model through considerable performance gains across CommonsenseQA and OpenbookQA datasets.

Cross-domain named entity recognition aims to improve performance in a target domain with shared knowledge from a well-studied source domain. The previous sequence-labeling based method focuses on promoting model parameter sharing among domains. However, such a paradigm essentially ignores the domain-specific information and suffers from entity type conflicts. To address these issues, we propose a novel machine reading comprehension based framework, named DoSEA, which can identify domain-specific semantic differences and mitigate the subtype conflicts between domains. Concretely, we introduce an entity existence discrimination task and an entity-aware training setting, to recognize inconsistent entity annotations in the source domain and bring additional reference to better share information across domains. Experiments on six datasets prove the effectiveness of our DoSEA. Our source code can be obtained from https://github.com/mhtang1995/DoSEA.

Recent research has investigated quantum NLP, designing algorithms that process natural language in quantum computers, and also quantum-inspired algorithms that improve NLP performance on classical computers. In this survey, we review representative methods at the intersection of NLP and quantum physics in the past ten years, categorizing them according to the use of quantum theory, the linguistic targets that are modeled, and the downstream application. The literature review ends with a discussion on the key factors to the success that has been achieved by existing work, as well as challenges ahead, with the goal of better understanding the promises and further directions.

Natural Language Understanding (NLU) is a core component of dialog systems. It typically involves two tasks - Intent Classification (IC) and Slot Labeling (SL), which are then followed by a dialogue management (DM) component. Such NLU systems cater to utterances in isolation, thus pushing the problem of context management to DM. However, contextual information is critical to the correct prediction of intents in a conversation. Prior work on contextual NLU has been limited in terms of the types of contextual signals used and the understanding of their impact on the model. In this work, we propose a context-aware self-attentive NLU (CASA-NLU) model that uses multiple signals over a variable context window, such as previous intents, slots, dialog acts and utterances, in addition to the current user utterance. CASA-NLU outperforms a recurrent contextual NLU baseline on two conversational datasets, yielding a gain of up to 7% on the IC task. Moreover, a non-contextual variant of CASA-NLU achieves state-of-the-art performance on standard public datasets - SNIPS and ATIS.

Relation extraction is the task of finding pre-defined semantic relations between two entities or entity mentions from text. Many methods, such as feature-based and kernel-based methods, have been proposed in the literature. Among them, feature-based methods draw much attention from researchers. However, to the best of our knowledge, existing feature-based methods did not explicitly incorporate the position feature and no in-depth analysis was conducted in this regard. In this paper, we define and exploit nine types of position information between two named entity mentions and then use it along with other features in a multi-class classification framework for Chinese relation extraction. Experiments on the ACE 2005 data set show that the position feature is more effective than the other recognized features like entity type/subtype and character-based N-gram context. Most important, it can be easily captured and does not require as much effort as applying deep natural language processing.