Combining ELECTRA and Adaptive Graph Encoding for Frame Identification
This paper presents contributions in two directions: first we propose a new system for Frame Identification (FI), based on pre-trained text encoders trained discriminatively and graphs embedding, producing state of the art performance and, second, we take in consideration all the extremely different procedures used to evaluate systems for this task performing a complete evaluation over two benchmarks and all possible splits and cleaning procedures used in the FI literature.
Code (1)
Tasks
AllSimilar Papers 제목 키워드 기반
Are ELECTRA's Sentence Embeddings Beyond Repair? The Case of Semantic Textual Similarity
While BERT produces high-quality sentence embeddings, its pre-training computational cost is a significant drawback. In contrast, ELECTRA provides a cost-effective pre-training objective and downstream task performance i…
Semantic Textual SimilaritySentenceSentence EmbeddingsSTS+2LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relations
This work aims to tackle the challenging heterogeneous graph encoding problem in the text-to-SQL task. Previous methods are typically node-centric and merely utilize different weight matrices to parameterize edge types, …
Text to SQLText-To-SQLGenerative Relevance Feedback and Convergence of Adaptive Re-Ranking: University of Glasgow Terrier Team at TREC DL 2023
This paper describes our participation in the TREC 2023 Deep Learning Track. We submitted runs that apply generative relevance feedback from a large language model in both a zero-shot and pseudo-relevance feedback settin…
Language ModelingLanguage ModellingLarge Language ModelRe-Ranking+1SaGE: 基于句法感知图卷积神经网络和ELECTRA的中文隐喻识别模型(SaGE: Syntax-aware GCN with ELECTRA for Chinese Metaphor Detection)
“隐喻是人类语言中经常出现的一种特殊现象,隐喻识别对于自然语言处理各项任务来说具有十分基础和重要的意义。针对中文领域的隐喻识别任务,我们提出了一种基于句法感知图卷积神经网络和ELECTRA的隐喻识别模型(Syntax-aware GCN withELECTRA SaGE)。该模型从语言学出发,使用ELECTRA和Transformer编码器抽取句子的语义特征,将句子按照依存关系组织成一张图并使用图卷积神经网络抽取其句法特征,在此基础上对…
On the effectiveness of small, discriminatively pre-trained language representation models for biomedical text mining
Neural language representation models such as BERT have recently shown state of the art performance in downstream NLP tasks and bio-medical domain adaptation of BERT (Bio-BERT) has shown same behavior on biomedical text …
Domain AdaptationGPUnamed-entity-recognitionNamed Entity Recognition+3