arXiv subjects

Hongyu Lin

Publications and source records attributed to Hongyu Lin.

143 records · Page 8Linked to original sources

arXiv2021

Text2Event: Controllable Sequence-to-Structure Generation for End-to-end Event Extraction

Event extraction is challenging due to the complex structure of event records and the semantic gap between text and event. Traditional methods usually extract event records by decomposing the complex structure prediction task into multiple subtasks. In this paper, we propose Text2Event, a sequence-to-structure generation paradigm that can directly extract events from the text in an end-to-end manner. Specifically, we design a sequence-to-structure network for unified event extraction, a constrained decoding algorithm for event knowledge injection during inference, and a curriculum learning algorithm for efficient model learning. Experimental results show that, by uniformly modeling all tasks in a single model and universally predicting different labels, our method can achieve competitive performance using only record-level annotations in both supervised learning and transfer learning settings.

cs.CL↗

arXiv2021

De-biasing Distantly Supervised Named Entity Recognition via Causal Intervention

Distant supervision tackles the data bottleneck in NER by automatically generating training instances via dictionary matching. Unfortunately, the learning of DS-NER is severely dictionary-biased, which suffers from spurious correlations and therefore undermines the effectiveness and the robustness of the learned models. In this paper, we fundamentally explain the dictionary bias via a Structural Causal Model (SCM), categorize the bias into intra-dictionary and inter-dictionary biases, and identify their causes. Based on the SCM, we learn de-biased DS-NER via causal interventions. For intra-dictionary bias, we conduct backdoor adjustment to remove the spurious correlations introduced by the dictionary confounder. For inter-dictionary bias, we propose a causal invariance regularizer which will make DS-NER models more robust to the perturbation of dictionaries. Experiments on four datasets and three DS-NER models show that our method can significantly improve the performance of DS-NER.

cs.CL↗

arXiv2021

Denoising Distantly Supervised Named Entity Recognition via a Hypergeometric Probabilistic Model

Denoising is the essential step for distant supervision based named entity recognition. Previous denoising methods are mostly based on instance-level confidence statistics, which ignore the variety of the underlying noise distribution on different datasets and entity types. This makes them difficult to be adapted to high noise rate settings. In this paper, we propose Hypergeometric Learning (HGL), a denoising algorithm for distantly supervised NER that takes both noise distribution and instance-level confidence into consideration. Specifically, during neural network training, we naturally model the noise samples in each batch following a hypergeometric distribution parameterized by the noise-rate. Then each instance in the batch is regarded as either correct or noisy one according to its label confidence derived from previous training step, as well as the noise distribution in this sampled batch. Experiments show that HGL can effectively denoise the weakly-labeled data retrieved from distant supervision, and therefore results in significant improvements on the trained models.

cs.CL↗

arXiv2021

Element Intervention for Open Relation Extraction

Open relation extraction aims to cluster relation instances referring to the same underlying relation, which is a critical step for general relation extraction. Current OpenRE models are commonly trained on the datasets generated from distant supervision, which often results in instability and makes the model easily collapsed. In this paper, we revisit the procedure of OpenRE from a causal view. By formulating OpenRE using a structural causal model, we identify that the above-mentioned problems stem from the spurious correlations from entities and context to the relation type. To address this issue, we conduct \emph{Element Intervention}, which intervenes on the context and entities respectively to obtain the underlying causal effects of them. We also provide two specific implementations of the interventions based on entity ranking and context contrasting. Experimental results on unsupervised relation extraction datasets show that our methods outperform previous state-of-the-art methods and are robust across different datasets.

cs.CL↗

arXiv2021

From Discourse to Narrative: Knowledge Projection for Event Relation Extraction

Current event-centric knowledge graphs highly rely on explicit connectives to mine relations between events. Unfortunately, due to the sparsity of connectives, these methods severely undermine the coverage of EventKGs. The lack of high-quality labelled corpora further exacerbates that problem. In this paper, we propose a knowledge projection paradigm for event relation extraction: projecting discourse knowledge to narratives by exploiting the commonalities between them. Specifically, we propose Multi-tier Knowledge Projection Network (MKPNet), which can leverage multi-tier discourse knowledge effectively for event relation extraction. In this way, the labelled data requirement is significantly reduced, and implicit event relations can be effectively extracted. Intrinsic experimental results show that MKPNet achieves the new state-of-the-art performance, and extrinsic experimental results verify the value of the extracted event relations.

cs.CL↗

arXiv2021

Tunable photon blockade in a two-mode second-order nonlinear system embedded with a two-level atom

The conventional photon blockade for high-frequency mode is investigated in a two-mode second-order nonlinear system embedded with a two-level atom. By solving the master equation and calculating the zero-delay-time second-order correlation function $g^{(2)}(0)$, we obtain that strong photon antibunching can be achieved in this scheme. In particular, we find that by increasing the linear coupling coefficient of the system, a perfect blockade region will be formed near the zero second-order nonlinear coupling coefficient. Similarly, by increasing the nonlinear coupling coefficient of the system, the perfect blockade zone will appear. And this scheme is not sensitive to the reservoir temperature, both of which make the current system easier to implement experimentally.

quant-ph↗

arXiv2021

Syntactic and Semantic-driven Learning for Open Information Extraction

One of the biggest bottlenecks in building accurate, high coverage neural open IE systems is the need for large labelled corpora. The diversity of open domain corpora and the variety of natural language expressions further exacerbate this problem. In this paper, we propose a syntactic and semantic-driven learning approach, which can learn neural open IE models without any human-labelled data by leveraging syntactic and semantic knowledge as noisier, higher-level supervisions. Specifically, we first employ syntactic patterns as data labelling functions and pretrain a base model using the generated labels. Then we propose a syntactic and semantic-driven reinforcement learning algorithm, which can effectively generalize the base model to open situations with high accuracy. Experimental results show that our approach significantly outperforms the supervised counterparts, and can even achieve competitive performance to supervised state-of-the-art (SoA) model

cs.CL↗

arXiv2020

A Rigorous Study on Named Entity Recognition: Can Fine-tuning Pretrained Model Lead to the Promised Land?

Fine-tuning pretrained model has achieved promising performance on standard NER benchmarks. Generally, these benchmarks are blessed with strong name regularity, high mention coverage and sufficient context diversity. Unfortunately, when scaling NER to open situations, these advantages may no longer exist. And therefore it raises a critical question of whether previous creditable approaches can still work well when facing these challenges. As there is no currently available dataset to investigate this problem, this paper proposes to conduct randomization test on standard benchmarks. Specifically, we erase name regularity, mention coverage and context diversity respectively from the benchmarks, in order to explore their impact on the generalization ability of models. To further verify our conclusions, we also construct a new open NER dataset that focuses on entity types with weaker name regularity and lower mention coverage to verify our conclusion. From both randomization test and empirical experiments, we draw the conclusions that 1) name regularity is critical for the models to generalize to unseen mentions; 2) high mention coverage may undermine the model generalization ability and 3) context patterns may not require enormous data to capture when using pretrained encoders.

cs.CL↗

arXiv2020

End-to-End Neural Event Coreference Resolution

Traditional event coreference systems usually rely on pipeline framework and hand-crafted features, which often face error propagation problem and have poor generalization ability. In this paper, we propose an End-to-End Event Coreference approach -- E3C neural network, which can jointly model event detection and event coreference resolution tasks, and learn to extract features from raw text automatically. Furthermore, because event mentions are highly diversified and event coreference is intricately governed by long-distance, semantic-dependent decisions, a type-guided event coreference mechanism is further proposed in our E3C neural network. Experiments show that our method achieves new state-of-the-art performance on two standard datasets.

cs.CL↗

arXiv2020

ISCAS at SemEval-2020 Task 5: Pre-trained Transformers for Counterfactual Statement Modeling

ISCAS participated in two subtasks of SemEval 2020 Task 5: detecting counterfactual statements and detecting antecedent and consequence. This paper describes our system which is based on pre-trained transformers. For the first subtask, we train several transformer-based classifiers for detecting counterfactual statements. For the second subtask, we formulate antecedent and consequence extraction as a query-based question answering problem. The two subsystems both achieved third place in the evaluation. Our system is openly released at https://github.com/casnlu/ISCAS-SemEval2020Task5.

cs.CL↗

arXiv2020

Unconventional photon blockade based on double second order nonlinear coupling system

In the recent publications [Phys. Rev. A 92,023838 (2015)], the unconventional photon blockade are studied in a two-mode-second-order-nonlinear system with nonlinear coupling between the low frequency and high frequency modes. In this paper, we study the unconventional photon blockade in a three-mode system with weakly coupled nonlinear cavities via $χ^{(2)}$ nonlinearity. By solving the master equation in the steady-state limit and calculating the zero-delay time second-order correlation function, we obtain the conditions of strong photon antibunching in the low frequency mode. The numerical result are compared with the analytical results, the results show that they are in complete agreement. By the analysis of numerical solutions, we find that this scheme is not sensitive to the change of decay rates and the reservoir temperature, and the three-mode drives make the system have more adjustable parameters, both of which increases the possibility of experimental implementation.

physics.optics↗

arXiv2020

Single-photon transport in one-dimensional coupled-resonator waveguide with second order nonlinearity coupling to a nanocavity containing a two-level atom and Kerr nonlinearity

We study controllable single photon scattering in a one-dimensional waveguide coupling with an additional cavity by second order nonlinear materials in a non-cascading configuration, where the additional cavity is embedded with two-level atom and filled with Kerr-nonlinear materials. Considering the second order nonlinear coupling, we analyze the transmission properties of the three different coupling forms as follows: (i) The two-level atom is excited without the Kerr-nonlinearity. (ii)The Kerr-nonlinearity is excited without the two-level atom. (iii) Both of the two-level atom and Kerr-nonlinearity are excited. The transmission and reflection amplitudes are obtained by the discrete coordinates approach for the three cases. The results showed that the transmission properties can be adjusted by the above three different coupling forms, which indicate our scheme can be used as a single photon switch to control the transmission and reflection of the single photon in the one-dimensional coupled resonant waveguide. We compared the results with [Phys. Rev. A 85, 053840(2012)] and find the advantages.

physics.optics↗

arXiv2020

Kerr-nonlinearity Enhanced Conventional Photon Blockade in Second-order-nonlinear System

In the recent publication [Phys. Rev. B 87, 235319 (2013)], the conventional photon blockade(CPB) was studied for the low frequency mode in a second-order nonlinear system. In this paper, we will study the CPB for the high frequency mode in a second-order nonlinear system with the Kerr nonlinearity filling in the low-frequency cavity. By solving the master equation and calculating the zero-delay-time second order correlation function $g^{(2)}(0)$, strong photon antibunching can be obtained in the high frequency cavity. The optimal condition for strong antibunching is found by analyticcal culations and discussions of the optimal condition are presented. We find that the Kerr-nonlinearities can enhanced the CPB effect. In addition, this scheme is not sensitive to the reservoir temperature, which make the current system easier to implement experimentally.

physics.optics↗

arXiv2019

Cost-sensitive Regularization for Label Confusion-aware Event Detection

In supervised event detection, most of the mislabeling occurs between a small number of confusing type pairs, including trigger-NIL pairs and sibling sub-types of the same coarse type. To address this label confusion problem, this paper proposes cost-sensitive regularization, which can force the training procedure to concentrate more on optimizing confusing type pairs. Specifically, we introduce a cost-weighted term into the training loss, which penalizes more on mislabeling between confusing label pairs. Furthermore, we also propose two estimators which can effectively measure such label confusion based on instance-level or population-level statistics. Experiments on TAC-KBP 2017 datasets demonstrate that the proposed method can significantly improve the performances of different models in both English and Chinese event detection.

cs.CL↗

arXiv2019

Sequence-to-Nuggets: Nested Entity Mention Detection via Anchor-Region Networks

Sequential labeling-based NER approaches restrict each word belonging to at most one entity mention, which will face a serious problem when recognizing nested entity mentions. In this paper, we propose to resolve this problem by modeling and leveraging the head-driven phrase structures of entity mentions, i.e., although a mention can nest other mentions, they will not share the same head word. Specifically, we propose Anchor-Region Networks (ARNs), a sequence-to-nuggets architecture for nested mention detection. ARNs first identify anchor words (i.e., possible head words) of all mentions, and then recognize the mention boundaries for each anchor word by exploiting regular phrase structures. Furthermore, we also design Bag Loss, an objective function which can train ARNs in an end-to-end manner without using any anchor word annotation. Experiments show that ARNs achieve the state-of-the-art performance on three standard nested entity mention detection benchmarks.

cs.CL↗

arXiv2018

Adaptive Scaling for Sparse Detection in Information Extraction

This paper focuses on detection tasks in information extraction, where positive instances are sparsely distributed and models are usually evaluated using F-measure on positive classes. These characteristics often result in deficient performance of neural network based detection models. In this paper, we propose adaptive scaling, an algorithm which can handle the positive sparsity problem and directly optimize over F-measure via dynamic cost-sensitive learning. To this end, we borrow the idea of marginal utility from economics and propose a theoretical framework for instance importance measuring without introducing any additional hyper-parameters. Experiments show that our algorithm leads to a more effective and stable training of neural network based detection models.

cs.CL↗

arXiv2018

Nugget Proposal Networks for Chinese Event Detection

Neural network based models commonly regard event detection as a word-wise classification task, which suffer from the mismatch problem between words and event triggers, especially in languages without natural word delimiters such as Chinese. In this paper, we propose Nugget Proposal Networks (NPNs), which can solve the word-trigger mismatch problem by directly proposing entire trigger nuggets centered at each character regardless of word boundaries. Specifically, NPNs perform event detection in a character-wise paradigm, where a hybrid representation for each character is first learned to capture both structural and semantic information from both characters and words. Then based on learned representations, trigger nuggets are proposed and categorized by exploiting character compositional structures of Chinese event triggers. Experiments on both ACE2005 and TAC KBP 2017 datasets show that NPNs significantly outperform the state-of-the-art methods.

cs.CL↗