Skip to search formSkip to main contentSkip to account menu

Linformer: Self-Attention with Linear Complexity

This paper demonstrates that the self-attention mechanism of the Transformer can be approximated by a low-rank matrix, and proposes a new self-Attention mechanism, which reduces the overall self-ATTention complexity from $O(n^2)$ to $O (n)$ in both time and space.
View PDF on arXiv (opens in a new tab)

CLEAR: Contrastive Learning for Sentence Representation

This paper proposes Contrastive LEArning for sentence Representation (CLEAR), which employs multiple sentence-level augmentation strategies in order to learn a noise-invariant sentence representation and investigates the key reasons that make contrastive learning effective through numerous experiments.
View PDF on arXiv (opens in a new tab)

The Number of Scholarly Documents on the Public Web

The number of scholarly documents available on the web is estimated using capture/recapture methods by studying the coverage of two major academic search engines: Google Scholar and Microsoft Academic Search, and shows that among these fields the percentage of documents defined as freely available varies significantly.
View on PubMed (opens in a new tab)

The CHEMDNER corpus of chemicals and drugs and its annotation principles

The CHEMDNER corpus is presented, a collection of 10,000 PubMed abstracts that contain a total of 84,355 chemical entity mentions labeled manually by expert chemistry literature curators, following annotation guidelines specifically defined for this task.
View on Springer (opens in a new tab)

Entailment as Few-Shot Learner

A new approach is proposed, named as EFL, that can turn small LMs into better few-shot learners, and improves the various existing SOTA few-shots learning methods by 12%, and yields competitive few- shot performance with 500 times larger models, such as GPT-3.
View PDF on arXiv (opens in a new tab)

UniPELT: A Unified Framework for Parameter-Efficient Language Model Tuning

A unified framework, UniPELT, is proposed, which incorporates different PELT methods as submodules and learns to activate the ones that best suit the current data or task setup via gating mechanism, indicating that a mixture of multiple P ELT methods may be inherently more effective than single methods.
View on ACL (opens in a new tab)

Building Natural Language Interfaces to Web APIs

This work proposes the first end-to-end framework to build an NL2API for a given web API, and applies it to real-world APIs, and shows that it can collect high-quality training data at a low cost, and build NL2APIs with good performance from scratch.
View on ACM (opens in a new tab)

Online Person Name Disambiguation with Constraints

An extension to the density-based clustering algorithm (DBSCAN) to handle online clustering so that the disambiguation process can be done iteratively as new data points are added, and implements two types of clustering constraints to demonstrate the concept.
View on ACM (opens in a new tab)

CiteSeerX: AI in a Digital Library Search Engine

This work presents key AI technologies used in the following components of CiteSeerX: document classification and deduplication, document and citation clustering, automatic metadata extraction and indexing, and author disambiguation.
View via Publisher (opens in a new tab)

Learning to identify relevant studies for systematic reviews using random forest and external information

This work introduces a novel method for representing systematic reviews based not only on lexical features, but also utilizing word clustering and citation features that is shown to outperform previously used features in representing systematic Reviews, regardless of the classifier.
View on Springer (opens in a new tab)
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)