https://github.com/Accelerator66/latent-gaussian-process-priors
공식 코드Raven's Progressive Matrices Completion with Latent Gaussian Process Priors
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Answer Selection is the task of identifying the correct answer to a question from a pool of candidate answers. This task can be formulated as a classification or a ranking problem.
Source: Learning Analogy-Preserving Sentence Embeddings for Answer Selection
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Raven's Progressive Matrices Completion with Latent Gaussian Process Priors
Neural Duplicate Question Detection without Labeled Training Data
Paragraph-based Transformer Pre-training for Multi-Sentence Inference
ComQA:Compositional Question Answering via Hierarchical Graph Neural Networks
Leveraging Large Language Models for Multiple Choice Question Answering
Propagate-Selector: Detecting Supporting Sentences for Question Answering via Graph Neural Networks
CICERO: A Dataset for Contextualized Commonsense Inference in Dialogues
Joint Learning of Answer Selection and Answer Summary Generation in Community Question Answering
Raven's Progressive Matrices Completion with Latent Gaussian Process Priors
Simple and Effective Text Matching with Richer Alignment Features
Hierarchical Memory Networks for Answer Selection on Unknown Words
When Benchmarks are Targets: Revealing the Sensitivity of Large Language Model Leaderboards
The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systems
Ada-LEval: Evaluating long-context LLMs with length-adaptable benchmarks
Applying Deep Learning to Answer Selection: A Study and An Open Task
SynTQA: Synergistic Table-based Question Answering via Mixture of Text-to-SQL and E2E TQA
Utilizing Bidirectional Encoder Representations from Transformers for Answer Selection
MultiCQA: Zero-Shot Transfer of Self-Supervised Text Matching Models on a Massive Scale
ABCNN: Attention-Based Convolutional Neural Network for Modeling Sentence Pairs
Once is Enough: A Light-Weight Cross-Attention for Fast Sentence Pair Modeling
FinBERT-QA: Financial Question Answering with pre-trained BERT Language Models
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.