Search

Multi-head Latent Attention (MLA) is an innovative architecture proposed by DeepSeek, designed to ensure efficient and economical inference by significantly compressing the Key-Value (KV) cache into a latent vector. Compared to MLA, standard LLMs employing Multi-Head Attention (MHA) and its variants such as Grouped-Query Attention (GQA) exhibit significant cost disadvantages. Enabling well-trained LLMs (e.g., Llama) to rapidly adapt to MLA without pre-training from scratch is both meaningful and challenging. This paper proposes the first data-efficient fine-tuning method for transitioning from MHA to MLA (MHA2MLA), which includes two key components: for partial-RoPE, we remove RoPE from dimensions of queries and keys that contribute less to the attention scores, for low-rank approximation, we introduce joint SVD approximations based on the pre-trained parameters of keys and values. These carefully designed strategies enable MHA2MLA to recover performance using only a small fraction (0.3% to 0.6%) of the data, significantly reducing inference costs while seamlessly integrating with compression techniques such as KV cache quantization. For example, the KV cache size of Llama2-7B is reduced by 92.19%, with only a 0.5% drop in LongBench performance., Comment: 16 pages, 8 figures

Nuclear excitation by electron capture (NEEC) is an important nuclear excitation mechanism which still lacks conclusive experimental verification. This is primarily attributed to strong background x-/$\gamma$-ray noise and competing nuclear excitation processes which would overshadow the signals in various environments that NEEC takes place. Here, we propose an experimental approach to observe the NEEC process within a background-free environment. Through collisions with a highly-compressed mono-energetic electron beam in an electron beam ion trap, nuclei may get excited to a long-lived isomeric state via the NEEC process. Subsequently, ions can be extracted and Penning-trap mass spectrometry employed to unambiguously detect the isomer. Our study focuses on the promising candidate $^{189}\mathrm{Os}$, demonstrating measurable detection rates of the NEEC process and discussing the feasibility of the proposed approach. This new approach for observing the NEEC process may be realized in the near future.

Current Large Language Models (LLMs) for understanding proteins primarily treats amino acid sequences as a text modality. Meanwhile, Protein Language Models (PLMs), such as ESM-2, have learned massive sequential evolutionary knowledge from the universe of natural protein sequences. Furthermore, structure-based encoders like ProteinMPNN learn the structural information of proteins through Graph Neural Networks. However, whether the incorporation of protein encoders can enhance the protein understanding of LLMs has not been explored. To bridge this gap, we propose EvoLlama, a multimodal framework that connects a structure-based encoder, a sequence-based protein encoder and an LLM for protein understanding. EvoLlama consists of a ProteinMPNN structure encoder, an ESM-2 protein sequence encoder, a multimodal projector to align protein and text representations and a Llama-3 text decoder. To train EvoLlama, we fine-tune it on protein-oriented instructions and protein property prediction datasets verbalized via natural language instruction templates. Our experiments show that EvoLlama's protein understanding capabilities have been significantly enhanced, outperforming other fine-tuned protein-oriented LLMs in zero-shot settings by an average of 1%-8% and surpassing the state-of-the-art baseline with supervised fine-tuning by an average of 6%. On protein property prediction datasets, our approach achieves promising results that are competitive with state-of-the-art task-specific baselines. We will release our code in a future version.

Causal Language Modeling (CLM) and Masked Language Modeling (MLM) are two mainstream learning paradigms based on Transformer networks, specifically the Decoder-only and Encoder-only architectures. The strengths of each paradigm in downstream tasks have shown a mix of advantages and disadvantages. In the past BabyLM Challenge 2023, although the MLM paradigm achieved the best average performance, the CLM paradigm demonstrated significantly faster convergence rates. For the BabyLM Challenge 2024, we propose a novel language modeling paradigm named $\textbf{AntLM}$, which integrates both CLM and MLM to leverage the advantages of these two classic paradigms. We chose the strict-small track and conducted experiments on two foundation models: BabyLlama, representing CLM, and LTG-BERT, representing MLM. During the training process for specific foundation models, we alternate between applying CLM or MLM training objectives and causal or bidirectional attention masks. Experimental results show that combining the two pretraining objectives leverages their strengths, enhancing overall training performance. Under the same epochs, $AntLM_{BabyLlama}$ improves Macro-average by 1%, and $AntLM_{LTG-BERT}$ achieves a 2.2% increase over the baselines., Comment: CoNLL Shared Task BabyLM Challenge

We introduce a new dynamic vocabulary for language models. It can involve arbitrary text spans during generation. These text spans act as basic generation bricks, akin to tokens in the traditional static vocabularies. We show that, the ability to generate multi-tokens atomically improve both generation quality and efficiency (compared to the standard language model, the MAUVE metric is increased by 25%, the latency is decreased by 20%). The dynamic vocabulary can be deployed in a plug-and-play way, thus is attractive for various downstream applications. For example, we demonstrate that dynamic vocabulary can be applied to different domains in a training-free manner. It also helps to generate reliable citations in question answering tasks (substantially enhancing citation results without compromising answer accuracy)., Comment: EMNLP 2024

Large Vision-Language Models (LVLMs) have achieved impressive performance, yet research has pointed out a serious issue with object hallucinations within these models. However, there is no clear conclusion as to which part of the model these hallucinations originate from. In this paper, we present an in-depth investigation into the object hallucination problem specifically within the CLIP model, which serves as the backbone for many state-of-the-art vision-language systems. We unveil that even in isolation, the CLIP model is prone to object hallucinations, suggesting that the hallucination problem is not solely due to the interaction between vision and language modalities. To address this, we propose a counterfactual data augmentation method by creating negative samples with a variety of hallucination issues. We demonstrate that our method can effectively mitigate object hallucinations for CLIP model, and we show the the enhanced model can be employed as a visual encoder, effectively alleviating the object hallucination issue in LVLMs., Comment: EMNLP 2024

Existing rhetorical understanding and generation datasets or corpora primarily focus on single coarse-grained categories or fine-grained categories, neglecting the common interrelations between different rhetorical devices by treating them as independent sub-tasks. In this paper, we propose the Chinese Essay Rhetoric Dataset (CERD), consisting of 4 commonly used coarse-grained categories including metaphor, personification, hyperbole and parallelism and 23 fine-grained categories across both form and content levels. CERD is a manually annotated and comprehensive Chinese rhetoric dataset with five interrelated sub-tasks. Unlike previous work, our dataset aids in understanding various rhetorical devices, recognizing corresponding rhetorical components, and generating rhetorical sentences under given conditions, thereby improving the author's writing proficiency and language usage skills. Extensive experiments are conducted to demonstrate the interrelations between multiple tasks in CERD, as well as to establish a benchmark for future research on rhetoric. The experimental results indicate that Large Language Models achieve the best performance across most tasks, and jointly fine-tuning with multiple tasks further enhances performance.

In recent years, the field of electroencephalography (EEG) analysis has witnessed remarkable advancements, driven by the integration of machine learning and artificial intelligence. This survey aims to encapsulate the latest developments, focusing on emerging methods and technologies that are poised to transform our comprehension and interpretation of brain activity. We delve into self-supervised learning methods that enable the robust representation of brain signals, which are fundamental for a variety of downstream applications. We also explore emerging discriminative methods, including graph neural networks (GNN), foundation models, and large language models (LLMs)-based approaches. Furthermore, we examine generative technologies that harness EEG data to produce images or text, offering novel perspectives on brain activity visualization and interpretation. The survey provides an extensive overview of these cutting-edge techniques, their current applications, and the profound implications they hold for future research and clinical practice. The relevant literature and open-source materials have been compiled and are consistently being refreshed at \url{https://github.com/wpf535236337/LLMs4TS}, Comment: submitted to IECE Chinese Journal of Information Fusion

The nuclear isomeric state $^{229m}$Th with an exceptionally low excitation energy makes the $^{229}$Th isotope a crucial candidate for nuclear clocks and many other applications. Efficient and controllable production of $^{229m}$Th is essential and still remains a challenge. Here we report a novel approach for efficient production of $^{229m}$Th by the excitation of $^{229}$Th to the above-lying excited state at $29.19$ keV energy via the process of nuclear excitation by electron capture (NEEC). We show theoretically that the production rate of $^{229m}$Th per nucleus with accessible conditions can be six orders of magnitude larger than the value experimentally demonstrated using $29$-keV synchrotron radiation for this indirect excitation. With the efficient production of $^{229m}$Th, our results identify scenarios, as well as the characteristic NEEC signature with which NEEC events could be unambiguously identified, for a clear experimental identification of the long-sought NEEC phenomenon., Comment: 7 pages, 3 figures

Giant resonances (GRs) provide crucial insights into nuclear physics and astrophysics. Exciting GRs using particles like electrons is effective, yet the angular momentum (AM) transfer of electrons, including both intrinsic spin and orbital degrees of freedom in inelastic scattering, has never been studied. Here, we investigate AM transfer in GRs excited by plane-wave and vortex electrons, developing a comprehensive AM-resolved inelastic electron scattering theory. We find that even plane-wave electrons can model-independently extract transition strengths of higher multipolarity by selecting specific AM states of scattered electrons. Additionally, relativistic vortex electrons with orbital angular momentum (OAM) $\pm1$ can be efficiently generated. Vortex electrons can also be used to extract GR transition strength as in the plane-wave case, regardless of the position of nucleus relative to the beam axis. Furthermore, relativistic vortex electrons with larger OAM can be generated for on-axis nuclei due to AM conservation. Our method offers new perspectives for nuclear structure research and paves the way for generating vortex particles.

Aspect-based sentiment analysis (ABSA) is an important subtask of sentiment analysis, which aims to extract the aspects and predict their sentiments. Most existing studies focus on improving the performance of the target domain by fine-tuning domain-specific models (trained on source domains) based on the target domain dataset. Few works propose continual learning tasks for ABSA, which aim to learn the target domain's ability while maintaining the history domains' abilities. In this paper, we propose a Large Language Model-based Continual Learning (\texttt{LLM-CL}) model for ABSA. First, we design a domain knowledge decoupling module to learn a domain-invariant adapter and separate domain-variant adapters dependently with an orthogonal constraint. Then, we introduce a domain knowledge warmup strategy to align the representation between domain-invariant and domain-variant knowledge. In the test phase, we index the corresponding domain-variant knowledge via domain positioning to not require each sample's domain ID. Extensive experiments over 19 datasets indicate that our \texttt{LLM-CL} model obtains new state-of-the-art performance.

Generalizing to longer sentences is important for recent Transformer-based language models. Besides algorithms manipulating explicit position features, the success of Transformers without position encodings (NoPE) provides a new way to overcome the challenge. In this paper, we study the length generalization property of NoPE. We find that although NoPE can extend to longer sequences than the commonly used explicit position encodings, it still has a limited context length. We identify a connection between the failure of NoPE's generalization and the distraction of attention distributions. We propose a parameter-efficient tuning for searching attention heads' best temperature hyper-parameters, which substantially expands NoPE's context size. Experiments on long sequence language modeling, the synthetic passkey retrieval task and real-world long context tasks show that NoPE can achieve competitive performances with state-of-the-art length generalization algorithms. The source code is publicly accessible

Knowledge of the medical decision process, which can be modeled as medical decision trees (MDTs), is critical to build clinical decision support systems. However, the current MDT construction methods rely heavily on time-consuming and laborious manual annotation. In this work, we propose a novel task, Text2MDT, to explore the automatic extraction of MDTs from medical texts such as medical guidelines and textbooks. We normalize the form of the MDT and create an annotated Text-to-MDT dataset in Chinese with the participation of medical experts. We investigate two different methods for the Text2MDT tasks: (a) an end-to-end framework which only relies on a GPT style large language models (LLM) instruction tuning to generate all the node information and tree structures. (b) The pipeline framework which decomposes the Text2MDT task to three subtasks. Experiments on our Text2MDT dataset demonstrate that: (a) the end-to-end method basd on LLMs (7B parameters or larger) show promising results, and successfully outperform the pipeline methods. (b) The chain-of-thought (COT) prompting method \cite{Wei2022ChainOT} can improve the performance of the fine-tuned LLMs on the Text2MDT test set. (c) the lightweight pipelined method based on encoder-based pretrained models can perform comparably with LLMs with model complexity two magnititudes smaller. Our Text2MDT dataset is open-sourced at \url{https://tianchi.aliyun.com/dataset/95414}, and the source codes are open-sourced at \url{https://github.com/michael-wzhu/text2dt}.

Machine unlearning aims to revoke some training data after learning in response to requests from users, model developers, and administrators. Most previous methods are based on direct fine-tuning, which may neither remove data completely nor retain full performances on the remain data. In this work, we find that, by first masking some important parameters before fine-tuning, the performances of unlearning could be significantly improved. We propose a new masking strategy tailored to unlearning based on Fisher information. Experiments on various datasets and network structures show the effectiveness of the method: without any fine-tuning, the proposed Fisher masking could unlearn almost completely while maintaining most of the performance on the remain data. It also exhibits stronger stability compared to other unlearning baselines

Existing models for named entity recognition (NER) are mainly based on large-scale labeled datasets, which always obtain using crowdsourcing. However, it is hard to obtain a unified and correct label via majority voting from multiple annotators for NER due to the large labeling space and complexity of this task. To address this problem, we aim to utilize the original multi-annotator labels directly. Particularly, we propose a Confidence-based Partial Label Learning (CPLL) method to integrate the prior confidence (given by annotators) and posterior confidences (learned by models) for crowd-annotated NER. This model learns a token- and content-dependent confidence via an Expectation-Maximization (EM) algorithm by minimizing empirical risk. The true posterior estimator and confidence estimator perform iteratively to update the true posterior and confidence respectively. We conduct extensive experimental results on both real-world and synthetic datasets, which show that our model can improve performance effectively compared with strong baselines.

Large language models (LLMs) pre-trained on massive corpora have demonstrated impressive few-shot learning ability on many NLP tasks. A common practice is to recast the task into a text-to-text format such that generative LLMs of natural language (NL-LLMs) like GPT-3 can be prompted to solve it. However, it is nontrivial to perform information extraction (IE) tasks with NL-LLMs since the output of the IE task is usually structured and therefore is hard to be converted into plain text. In this paper, we propose to recast the structured output in the form of code instead of natural language and utilize generative LLMs of code (Code-LLMs) such as Codex to perform IE tasks, in particular, named entity recognition and relation extraction. In contrast to NL-LLMs, we show that Code-LLMs can be well-aligned with these IE tasks by designing code-style prompts and formulating these IE tasks as code generation tasks. Experiment results on seven benchmarks show that our method consistently outperforms fine-tuning moderate-size pre-trained models specially designed for IE tasks (e.g., UIE) and prompting NL-LLMs under few-shot settings. We further conduct a series of in-depth analyses to demonstrate the merits of leveraging Code-LLMs for IE tasks., Comment: Accepted to ACL 2023 (main conference). Code and data are publicly available at https://github.com/dasepli/CodeIE

Entity relation extraction consists of two sub-tasks: entity recognition and relation extraction. Existing methods either tackle these two tasks separately or unify them with word-by-word interactions. In this paper, we propose HIORE, a new method for unified entity relation extraction. The key insight is to leverage the high-order interactions, i.e., the complex association among word pairs, which contains richer information than the first-order word-by-word interactions. For this purpose, we first devise a W-shape DNN (WNet) to capture coarse-level high-order connections. Then, we build a heuristic high-order graph and further calibrate the representations with a graph neural network (GNN). Experiments on three benchmarks (ACE04, ACE05, SciERC) show that HIORE achieves the state-of-the-art performance on relation extraction and an improvement of 1.1~1.8 F1 points over the prior best unified model., Comment: 10 pages

Entity Alignment (EA) aims to find equivalent entity pairs between KGs, which is the core step of bridging and integrating multi-source KGs. In this paper, we argue that existing GNN-based EA methods inherit the inborn defects from their neural network lineage: weak scalability and poor interpretability. Inspired by recent studies, we reinvent the Label Propagation algorithm to effectively run on KGs and propose a non-neural EA framework -- LightEA, consisting of three efficient components: (i) Random Orthogonal Label Generation, (ii) Three-view Label Propagation, and (iii) Sparse Sinkhorn Iteration. According to the extensive experiments on public datasets, LightEA has impressive scalability, robustness, and interpretability. With a mere tenth of time consumption, LightEA achieves comparable results to state-of-the-art methods across all datasets and even surpasses them on many., Comment: 15 pages; Accepted by EMNLP2022 (Main Conf)

Due to the absence of connectives, implicit discourse relation recognition (IDRR) is still a challenging and crucial task in discourse analysis. Most of the current work adopted multi-task learning to aid IDRR through explicit discourse relation recognition (EDRR) or utilized dependencies between discourse relation labels to constrain model predictions. But these methods still performed poorly on fine-grained IDRR and even utterly misidentified on most of the few-shot discourse relation classes. To address these problems, we propose a novel Prompt-based Connective Prediction (PCP) method for IDRR. Our method instructs large-scale pre-trained models to use knowledge relevant to discourse relation and utilizes the strong correlation between connectives and discourse relation to help the model recognize implicit discourse relations. Experimental results show that our method surpasses the current state-of-the-art model and achieves significant improvements on those fine-grained few-shot discourse relation. Moreover, our approach is able to be transferred to EDRR and obtain acceptable results. Our code is released in https://github.com/zh-i9/PCP-for-IDRR., Comment: Findings of EMNLP 2022 Accepted

Existing distantly supervised relation extractors usually rely on noisy data for both model training and evaluation, which may lead to garbage-in-garbage-out systems. To alleviate the problem, we study whether a small clean dataset could help improve the quality of distantly supervised models. We show that besides getting a more convincing evaluation of models, a small clean dataset also helps us to build more robust denoising models. Specifically, we propose a new criterion for clean instance selection based on influence functions. It collects sample-level evidence for recognizing good instances (which is more informative than loss-level evidence). We also propose a teacher-student mechanism for controlling purity of intermediate results when bootstrapping the clean set. The whole approach is model-agnostic and demonstrates strong performances on both denoising real (NYT) and synthetic noisy datasets., Comment: Accepted by COLING 2022

Pun location is to identify the punning word (usually a word or a phrase that makes the text ambiguous) in a given short text, and pun interpretation is to find out two different meanings of the punning word. Most previous studies adopt limited word senses obtained by WSD(Word Sense Disambiguation) technique or pronunciation information in isolation to address pun location. For the task of pun interpretation, related work pays attention to various WSD algorithms. In this paper, a model called DANN (Dual-Attentive Neural Network) is proposed for pun location, effectively integrates word senses and pronunciation with context information to address two kinds of pun at the same time. Furthermore, we treat pun interpretation as a classification task and construct pungloss pairs as processing data to solve this task. Experiments on the two benchmark datasets show that our proposed methods achieve new state-of-the-art results. Our source code is available in the public code repository.

Cross-lingual entity alignment (EA) aims to find the equivalent entities between crosslingual KGs, which is a crucial step for integrating KGs. Recently, many GNN-based EA methods are proposed and show decent performance improvements on several public datasets. Meanwhile, existing GNN-based EA methods inevitably inherit poor interpretability and low efficiency from neural networks. Motivated by the isomorphic assumption of GNNbased methods, we successfully transform the cross-lingual EA problem into the assignment problem. Based on this finding, we propose a frustratingly Simple but Effective Unsupervised entity alignment method (SEU) without neural networks. Extensive experiments show that our proposed unsupervised method even beats advanced supervised methods across all public datasets and has high efficiency, interpretability, and stability., Comment: 11 pages; Accepted by EMNLP2021 (Main Conf)

Entity alignment (EA) aims to find the equivalent entities in different KGs, which is a crucial step in integrating multiple KGs. However, most existing EA methods have poor scalability and are unable to cope with large-scale datasets. We summarize three issues leading to such high time-space complexity in existing EA methods: (1) Inefficient graph encoders, (2) Dilemma of negative sampling, and (3) "Catastrophic forgetting" in semi-supervised learning. To address these challenges, we propose a novel EA method with three new components to enable high Performance, high Scalability, and high Robustness (PSR): (1) Simplified graph encoder with relational graph sampling, (2) Symmetric negative-free alignment loss, and (3) Incremental semi-supervised learning. Furthermore, we conduct detailed experiments on several public datasets to examine the effectiveness and efficiency of our proposed method. The experimental results show that PSR not only surpasses the previous SOTA in performance but also has impressive scalability and robustness., Comment: 11 pages; Accepted by CIKM 2021 (Full)

Long-lived excited states of atomic nuclei can act as energy traps. These states, known as nuclear isomers, can store a large amount of energy over long periods of time, with a very high energy-to-mass ratio. Under natural conditions, the trapped energy is only slowly released, limited by the long isomer lifetimes. Dynamical external control of nuclear state population has proven so far very challenging, despite ground-breaking incentives for a clean and efficient energy storage solution. Here, we describe a protocol to achieve the external control of the isomeric nuclear decay by using electrons whose wavefunction has been especially designed and reshaped on demand. Recombination of these electrons into the atomic shell around the isomer can lead to the controlled release of the stored nuclear energy. On the example of $^{93m}$Mo, we show that the use of tailored electron vortex beams increases the depletion by four orders of magnitude compared to the spontaneous nuclear decay of the isomer. Furthermore, specific orbitals can sustain an enhancement of the recombination cross section for vortex electron beams by as much as six orders of magnitude, providing a handle for manipulating the capture mechanism. These findings open new prospects for controlling the interplay between atomic and nuclear degrees of freedom, with potential energy-related and high-energy radiation sources applications., Comment: 14 pages, 3 figures

Many joint entity relation extraction models setup two separated label spaces for the two sub-tasks (i.e., entity detection and relation classification). We argue that this setting may hinder the information interaction between entities and relations. In this work, we propose to eliminate the different treatment on the two sub-tasks' label spaces. The input of our model is a table containing all word pairs from a sentence. Entities and relations are represented by squares and rectangles in the table. We apply a unified classifier to predict each cell's label, which unifies the learning of two sub-tasks. For testing, an effective (yet fast) approximate decoder is proposed for finding squares and rectangles from tables. Experiments on three benchmarks (ACE04, ACE05, SciERC) show that, using only half the number of parameters, our model achieves competitive accuracy with the best extractor, and is faster., Comment: ACL2021

In this paper, we investigate the problem of reasoning over natural language statements. Prior neural based approaches do not explicitly consider the inter-dependency among answers and their proofs. In this paper, we propose PRobr, a novel approach for joint answer prediction and proof generation. PRobr defines a joint probabilistic distribution over all possible proof graphs and answers via an induced graphical model. We then optimize the model using variational approximation on top of neural textual representation. Experiments on multiple datasets under diverse settings (fully supervised, few-shot and zero-shot evaluation) verify the effectiveness of PRobr, e.g., achieving 10%-30% improvement on QA accuracy in few/zero-shot evaluation. Our codes and models can be found at https://github.com/changzhisun/PRobr/., Comment: Accepted by Findings of ACL2021

Seeking the equivalent entities among multi-source Knowledge Graphs (KGs) is the pivotal step to KGs integration, also known as \emph{entity alignment} (EA). However, most existing EA methods are inefficient and poor in scalability. A recent summary points out that some of them even require several days to deal with a dataset containing 200,000 nodes (DWY100K). We believe over-complex graph encoder and inefficient negative sampling strategy are the two main reasons. In this paper, we propose a novel KG encoder -- Dual Attention Matching Network (Dual-AMN), which not only models both intra-graph and cross-graph information smartly, but also greatly reduces computational complexity. Furthermore, we propose the Normalized Hard Sample Mining Loss to smoothly select hard negative samples with reduced loss shift. The experimental results on widely used public datasets indicate that our method achieves both high accuracy and high efficiency. On DWY100K, the whole running process of our method could be finished in 1,100 seconds, at least 10* faster than previous work. The performances of our method also outperform previous works across all datasets, where Hits@1 and MRR have been improved from 6% to 13%., Comment: 12 pages; Accepted by TheWebConf(WWW) 2021

A quantum plasma screening model based on the density matrix formalism is used to investigate theoretically the thermonuclear reactions $^{13}$C($\alpha$, $n$)$^{16}$O and $^2$H($d$, $n$)$^3$He in laser-generated plasmas over a large range of densities and temperatures. For cold and dense (solid-state density) plasmas, our results show that quantum effects can enhance the plasma screening for thermonuclear reactions up to one order of magnitude compared to the classical case. This result can have impact on nuclear astrophysics predictions, and also may play a role for fusion energy gain prospects. Our simulations allow us to identify the laser-generated plasma experimental setting in which the quantum effects on plasma screening could be confirmed at existing high-intensity laser facilities., Comment: 7 pages, 2 figures, 1 table; accepted for publication in Physical Review Research

Previous CCG supertaggers usually predict categories using multi-class classification. Despite their simplicity, internal structures of categories are usually ignored. The rich semantics inside these structures may help us to better handle relations among categories and bring more robustness into existing supertaggers. In this work, we propose to generate categories rather than classify them: each category is decomposed into a sequence of smaller atomic tags, and the tagger aims to generate the correct sequence. We show that with this finer view on categories, annotations of different categories could be shared and interactions with sentence contexts could be enhanced. The proposed category generator is able to achieve state-of-the-art tagging (95.5% accuracy) and parsing (89.8% labeled F1) performances on the standard CCGBank. Furthermore, its performances on infrequent (even unseen) categories, out-of-domain texts and low resource language give promising results on introducing generation models to the general CCG analyses., Comment: Accepted by AAAI 2021

We propose a novel in-order chart-based model for constituent parsing. Compared with previous CKY-style and top-down models, our model gains advantages from in-order traversal of a tree (rich features, lookahead information and high efficiency) and makes a better use of structural knowledge by encoding the history of decisions. Experiments on the Penn Treebank show that our model outperforms previous chart-based models and achieves competitive performance compared with other discriminative single models., Comment: 10 pages, 2 figures

Entity alignment aims to identify equivalent entity pairs from different Knowledge Graphs (KGs), which is essential in integrating multi-source KGs. Recently, with the introduction of GNNs into entity alignment, the architectures of recent models have become more and more complicated. We even find two counter-intuitive phenomena within these methods: (1) The standard linear transformation in GNNs is not working well. (2) Many advanced KG embedding models designed for link prediction task perform poorly in entity alignment. In this paper, we abstract existing entity alignment methods into a unified framework, Shape-Builder & Alignment, which not only successfully explains the above phenomena but also derives two key criteria for an ideal transformation operation. Furthermore, we propose a novel GNNs-based method, Relational Reflection Entity Alignment (RREA). RREA leverages Relational Reflection Transformation to obtain relation specific embeddings for each entity in a more efficient way. The experimental results on real-world datasets show that our model significantly outperforms the state-of-the-art methods, exceeding by 5.8%-10.9% on Hits@1., Comment: 10 pages, Accepted by CIKM2020

Modifying characters of a piece of text to their visual similar ones often ap-pear in spam in order to fool inspection systems and other conditions, which we regard as a kind of adversarial attack to neural models. We pro-pose a way of generating such visual text attack and show that the attacked text are readable by humans but mislead a neural classifier greatly. We ap-ply a vision-based model and adversarial training to defense the attack without losing the ability to understand normal text. Our results also show that visual attack is extremely sophisticated and diverse, more work needs to be done to solve this., Comment: 9 pages

We propose a novel linearization of a constituent tree, together with a new locally normalized model. For each split point in a sentence, our model computes the normalizer on all spans ending with that split point, and then predicts a tree span from them. Compared with global models, our model is fast and parallelizable. Different from previous local models, our linearization method is tied on the spans directly and considers more local features when performing span prediction, which is more interpretable and effective. Experiments on PTB (95.8 F1) and CTB (92.4 F1) show that our model significantly outperforms existing local models and efficiently achieves competitive results with global models., Comment: Accepted to ACL 2020

The production of neutron-rich isotopes and the occurrence of neutron capture cascades via laser-driven (pulsed) neutron sources are investigated theoretically. The considered scenario involves the interaction of a laser-driven neutron beam with a target made of a single type of seed nuclide. We present a comprehensive study over $95$ seed nuclides in the range $3\le Z \le 100$ from $^7_3$Li to $^{255}_{100}$Fm. For each element, the heaviest sufficiently-long-lived (half life $> 1$ h) isotope whose data is available in the recent ENDF-B-VIII.0 neutron sublibrary is considered. We identify interesting seed nuclides with good performance in the production of neutron-rich isotopes where neutron capture cascades may occur. The effects of the neutron number per pulse, the neutron-target interaction size and the number of neutron pulses are also analyzed. Our results show the possibility of observing up to $4$ successive neutron capture events leading to neutron-rich isotopes with $4$ more neutrons than the original seed nuclide. This hints at new experimental possibilities to produce neutron-rich isotopes and simulate neutron capture nucleosynthesis in the laboratory. With several selected interesting seed nuclides in the region of the branching point of the $s$-process ($^{126}_{51}$Sb, $^{176}_{71}$Lu and $^{187}_{75}$Re) or the waiting point of the $r$-process (Lu, Re, Os, Tm, Ir and Au), we expect that laser-driven experiments can shed light on our understanding of nucleosynthesis., Comment: 23 pages, 8 figures, 1 table; discussions added; accepted for publication in Physical Review C

X-ray assisted nuclear excitation by electron capture (NEEC) into inner-shell atomic holes in a plasma environment generated by strong optical lasers is investigated theoretically. The considered scenario involves the interaction of a strong optical laser with a solid-state nuclear target leading to the generation of a plasma. In addition, intense x-ray radiation from an X-ray Free Electron Laser (XFEL) produces inner-shell holes in the plasma ions, into which NEEC may occur. As case study we consider the $4.85$-keV transition starting from the 2.4 MeV long-lived $^{\mathrm{93m}}$Mo isomer that can be used to release the energy stored in this metastable nuclear state. We find that the recombination into $2p_{1/2}$ inner-shell holes is most efficient in driving the nuclear transition. Already at few hundred eV plasma temperature, the generation of inner-shell holes can allow optimal conditions for NEEC, otherwise reached for steady-state plasma conditions in thermodynamical equilibrium only at few keV. The combination of x-ray and optical lasers presents two advantages: first, NEEC rates can be maximized at plasma temperatures where the photoexcitation rate remains low. Second, with mJ-class optical lasers and an XFEL repetition rate of $10$ kHz, the NEEC excitation number can reach $\sim 1$ depleted isomer per second and is competitive with scenarios recently envisaged at petawatt-class lasers., Comment: 9 pages, 4 figures; minor modifications made; accepted for publication in Physical Review A

A recent nuclear physics experiment [C. J. Chiara {\it et al.}, Nature (London) {\bf 554}, 216 (2018)] reports the first direct observation of nuclear excitation by electron capture (NEEC) in the depletion of the $^{93m}$Mo isomer. The experiment used a beam-based setup in which Mo highly charged ions with nuclei in the isomeric state $^{93m}$Mo at 2.4 MeV excitation energy were slowed down in a solid-state target. In this process, nuclear excitation to a higher triggering level led to isomer depletion. The reported excitation probability $P_{\rm{exc}} = 0.01$ was solely attributed to the so-far unobserved process of NEEC in lack of a different known channel of comparable efficiency. In this work, we investigate theoretically the beam-based setup and calculate excitation rates via NEEC using state-of-the-art atomic structure and ion stopping power models. For all scenarios, our results disagree with the experimental data by approximately nine orders of magnitude. This stands in conflict with the conclusion that NEEC was the excitation mechanism behind the observed depletion rate., Comment: 6 pages, 3 figures; minor modifications made; accepted for publication in Physical Review Letters

The production of intense neutron beams via thermonuclear reactions in laser-generated plasmas is investigated theoretically. So far, state-of-the-art neutron beams are produced via laser-induced particle acceleration leading to high-energy particle beams that subsequently interact with a secondary target. Here we show that neutron beams of two orders of magnitude narrower bandwidth can be obtained from thermonuclear reactions in plasmas generated by Petawatt-class lasers. The intensity of such neutron beams is about one or two orders of magnitude lower than the one of the state-of-the-art laser-driven neutron beams. We study to this end the reaction $^2$H($d$, $n$)$^3$He in plasmas generated by Petawatt-class lasers interacting with D$_2$ gas jet targets and CD$_2$ solid-state targets. The results also shows the possibility of direct measurements of reaction rates at low temperatures of astrophysical interests. In addition, the use of CD$_2$ solid-state targets can also lead to great enhancements on the plasma screening compared to the case of D$_2$ gas jet targets, opening new possibilities to study this so far unsolved issue in the field of astrophysics., Comment: 8 pages, 4 figures; accepted for publication in Physics of Plasmas