Searching for Legal Clauses by Analogy. Few-shot Semantic Retrieval Shared Task
Explore this paper's citation graph
Summary
It is shown that state-of-the-art pre-trained encoders fail to provide satisfactory results on the task proposed, whereas Language Model based solutions perform well, especially when unsupervised fine-tuning is applied.
- Type
- preprint
- Published
- 2019-11-10
- Cited by
- 0
- References
- 38
- Access
- Open access
- OpenAlex
- https://openalex.org/W2984303924
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:207852633
Keywords
Computer science, Task (project management), Natural language processing, Artificial intelligence, Encoder
References
- From Word Embeddings To Document Distances
- Efficient Estimation of Word Representations in Vector Space
- A large annotated corpus for learning natural language inference
- Finding Structure with Randomness: Probabilistic Algorithms for Constructing Approximate Matrix Decompositions
- Independent component analysis: algorithms and applications
- GloVe: Global Vectors for Word Representation
- Information Retrieval: Implementing and Evaluating Search Engines
- A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference
- Supervised Learning of Universal Sentence Representations from Natural Language Inference Data
- Overview of COLIEE 2017
- A Simple but Tough-to-Beat Baseline for Sentence Embeddings
- Deep Contextualized Word Representations
- Universal Sentence Encoder
- Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms
- Convolutional Neural Network for Universal Sentence Embeddings
- Extracting Fairness Policies from Legal Documents
- Learning Universal Sentence Representations with Mean-Max Attention Autoencoder
- Zero-training Sentence Embedding via Orthogonal Basis
- End-to-End Retrieval in Continuous Space
- CBOW Is Not All You Need: Combining CBOW with the Compositional Matrix Space Model
Cited by
No citing papers recorded for this paper.
Related papers
- Two-step cascaded textual entailment for legal bar exam question answering
- LegalDB: Long DistilBERT for Legal Document Classification
- A deep neural network model for speakers coreference resolution in legal texts
- A semantic-based approach to information processing
- Автоматическое построение семантической сети для получения ответов на вопросы
- Statute Law Information Retrieval and Entailment
- Information retrieval with semantic memory model
- Syntactically-informed representation for sentence selection