Search Results for author:
Found 9 papers, 8 papers with code
Imputing Out-of-Vocabulary Embeddings with LOVE Makes LanguageModels Robust with Little Cost
State-of-the-art NLP systems represent inputs with word embeddings, but these are brittle when faced with Out-of-Vocabulary (OOV) words. To address this issue, we follow the principle of mimick-like models to generate vectors for unseen words, by learning the behavior of pre-trained embeddings using only the surface form of words. We present a simple contrastive learning framework, LOVE, which extends the word representation of an existing pre-trained language model (such as BERT) and makes it robust to OOV with few additional parameters. Extensive evaluations demonstrate that our lightweight model achieves similar or even better performances than prior competitors, both on original datasets and on corrupted variants.
Reconfidencing LLMs from the Grouping Loss Perspective
In this work, we construct a new evaluation dataset derived from a knowledge base to assess confidence scores given to answers of Mistral and LLaMA.
Learning High-Quality and General-Purpose Phrase Representations
The framework employs phrase type classification as an auxiliary task and incorporates character-level information more effectively into the phrase representation.
The Locality and Symmetry of Positional Encodings
Positional Encodings (PEs) are used to inject word-order information into transformer-based language models.
YAGO 4.5: A Large and Clean Knowledge Base with a Rich Taxonomy
Knowledge Bases (KBs) find applications in many knowledge-intensive tasks and, most notably, in information retrieval.
Knowledge Base Completion for Long-Tail Entities
To evaluate our method and various baselines, we introduce a novel dataset, called MALT, rooted in Wikidata.
GLADIS: A General and Large Acronym Disambiguation Benchmark
Acronym Disambiguation (AD) is crucial for natural language understanding on various sources, including biomedical reports, scientific papers, and search engine queries.
Imputing Out-of-Vocabulary Embeddings with LOVE Makes Language Models Robust with Little Cost
State-of-the-art NLP systems represent inputs with word embeddings, but these are brittle when faced with Out-of-Vocabulary (OOV) words.
A Lightweight Neural Model for Biomedical Entity Linking
Biomedical entity linking aims to map biomedical mentions, such as diseases and drugs, to standard entities in a given knowledge base.
