HCCL at SemEval-2018 Task 8: An End-to-End System for Sequence Labeling from Cybersecurity Reports

2018-06-01 · SEMEVAL 2018 6 · Mingming Fu, Xuemin Zhao, Yonghong Yan

This paper describes HCCL team systems that participated in SemEval 2018 Task 8: SecureNLP (Semantic Extraction from cybersecurity reports using NLP). To solve the problem, our team applied a neural network architecture that benefits from both word and character level representaions automatically, by using combination of Bi-directional LSTM, CNN and CRF (Ma and Hovy, 2016). Our system is truly end-to-end, requiring no feature engineering or data preprocessing, and we ranked 4th in the subtask 1, 7th in the subtask2 and 3rd in the SubTask2-relaxed.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Feature Engineering Named Entity Recognition (NER)Structured Prediction

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음

Tanh Activation 설명 없음

LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…

CRF Conditional Random Fields or CRFs are a type of probabilistic graph model that take neighboring sample context into account for tasks like classification. Prediction is…

HCCL at SemEval-2017 Task 2: Combining Multilingual Word Embeddings and Transliteration Model for Semantic Similarity

2017-08-01 · SEMEVAL 2017 8 · Junqing He, Long Wu, Xuemin Zhao, Yonghong Yan

In this paper, we introduce an approach to combining word embeddings and machine translation for multilingual semantic word similarity, the task2 of SemEval-2017. Thanks to the unsupervised transliteration model, our cro…

Cross-Lingual Word Embeddings Machine Translation Multilingual Word Embeddings Semantic Similarity+9

Hierarchical Cross Contrastive Learning of Visual Representations

2021-09-29 · Hesen Chen, Ming Lin, Xiuyu Sun, Rong Jin

The rapid progress of self-supervised learning (SSL) has greatly reduced the labeling cost in computer vision. The key idea of SSL is to learn invariant visual representations by maximizing the similarity between differe…

Contrastive Learning Few-Shot Learning Self-Supervised Learning

CLaC at SemEval-2023 Task 2: Comparing Span-Prediction and Sequence-Labeling approaches for NER

2023-05-05 · Harsh Verma, Sabine Bergler

This paper summarizes the CLaC submission for the MultiCoNER 2 task which concerns the recognition of complex, fine-grained named entities. We compare two popular approaches for NER, namely Sequence Labeling and Span Pre…

NER Prediction Task 2

LIPN at SemEval-2017 Task 10: Filtering Candidate Keyphrases from Scientific Publications with Part-of-Speech Tag Sequences to Train a Sequence Labeling Model

2017-08-01 · SEMEVAL 2017 8 · Hern, Simon David ez, Davide Buscaldi, Thierry Charnois

This paper describes the system used by the team LIPN in SemEval 2017 Task 10: Extracting Keyphrases and Relations from Scientific Publications. The team participated in Scenario 1, that includes three subtasks, Identifi…

TAG

BERTatDE at SemEval-2020 Task 6: Extracting Term-definition Pairs in Free Text Using Pre-trained Model

2020-12-01 · SEMEVAL 2020 · Huihui Zhang, Feiliang Ren

Definition extraction is an important task in Nature Language Processing, and it is used to identify the terms and definitions related to terms. The task contains sentence classification task (i.e., classify whether it c…

Definition Extraction Sentence Sentence Classification