https://github.com/tensorflow/mesh
공식 코드Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity
Papers with Code 아카이브
Question Answering
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 19
- 평가표
- 153
- 보존된 평가 기록
- 1,781
Question answering can be segmented into domain-specific tasks like community question answering and knowledge-base question answering. Popular benchmark datasets for evaluation question answering systems include SQuAD, HotPotQA, bAbI, TriviaQA, WikiQA, and many others. Models for question answering are typically evaluated on metrics like EM and F1. Some recent top performing models are T5 and XLNet.
( Image credit: SQuAD )
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/tensorflow/models
공식 코드Learning a Natural Language Interface with Neural Programmer
https://github.com/tensorflow/models/tree/master/official/nlp/projects/mobilebert
공식 코드MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices
https://github.com/tensorflow/ranking
공식 코드TF-Ranking: Scalable TensorFlow Library for Learning-to-Rank
https://github.com/tensorflow/tensor2tensor
공식 코드https://github.com/testingautomated-usi/bisupervised
공식 코드Adopting Two Supervisors for Efficient Use of Large-Scale Remote Deep Neural Networks
https://github.com/tetherless-world/metaexplainer
공식 코드An Ontology-Enabled Approach For User-Centered and Knowledge-Enabled Explanations of AI Systems
https://github.com/text-machine-lab/xword_benchmark
공식 코드Down and Across: Introducing Crossword-Solving as a New NLP Benchmark
https://github.com/tfnribeiro/webqamgaze
공식 코드WebQAmGaze: A Multilingual Webcam Eye-Tracking-While-Reading Dataset
https://github.com/tgc1997/RMN
공식 코드Learning to Discretely Compose Reasoning Module Networks for Video Captioning
https://github.com/thaihungle/NSM
공식 코드https://github.com/thaihungle/SAM
공식 코드https://github.com/thanhnguyentang/neural-offline-rl
공식 코드VIPeR: Provably Efficient Algorithm for Offline RL with Neural Function Approximation
https://github.com/thaolmk54/hcrn-videoqa
공식 코드Hierarchical Conditional Relation Networks for Video Question Answering
https://github.com/the-anonymous-bs/favor
공식 코드Fine-grained Audio-Visual Joint Representations for Multimodal Large Language Models
https://github.com/the-finai/pixiu
공식 코드FinBen: A Holistic Financial Benchmark for Large Language Models
https://github.com/the-jb/athena-math
공식 코드https://github.com/thepurpleowl/codequeries-benchmark
공식 코드https://github.com/thiliniiw/knowledgeprompts
공식 코드https://github.com/thinkwee/nover
공식 코드NOVER: Incentive Training for Language Models via Verifier-Free Reinforcement Learning
https://github.com/thisishwang/exit
공식 코드EXIT: Context-Aware Extractive Compression for Enhancing Retrieval-Augmented Generation
https://github.com/thomaswei-cn/MC-CoT
공식 코드https://github.com/thu-keg/knot
공식 코드Untangle the KNOT: Interweaving Conflicting Knowledge and Reasoning Skills in Large Language Models
https://github.com/thu-keg/rearag
공식 코드https://github.com/thu-keg/seakr
공식 코드SeaKR: Self-aware Knowledge Retrieval for Adaptive Retrieval Augmented Generation
https://github.com/thu-keg/vta
공식 코드https://github.com/thu-nics/framefusion
공식 코드https://github.com/thu-spmi/jsa-krtod
공식 코드Knowledge-Retrieval Task-Oriented Dialog Systems with Semi-Supervision
https://github.com/thudm/glm-4-voice
공식 코드GLM-4-Voice: Towards Intelligent and Human-Like End-to-End Spoken Chatbot
https://github.com/thudm/webglm
공식 코드WebGLM: Towards An Efficient Web-Enhanced Question Answering System with Human Preferences
https://github.com/thunlp-mt/extagents
공식 코드Scaling External Knowledge Input Beyond Context Windows of LLMs via Multi-Agent Collaboration
https://github.com/thunlp-mt/fiig
공식 코드https://github.com/thunlp-mt/symbol2language
공식 코드Speak It Out: Solving Symbol-Related Problems with Symbol-to-Language Conversion for Language Models
https://github.com/thunlp/ERICA
공식 코드https://github.com/thunlp/LegalPLMs
공식 코드Lawformer: A Pre-trained Language Model for Chinese Legal Long Documents
https://github.com/thunlp/OpenKE
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.