The Future of AI-Assisted Writing

The development of Natural Language Generation models has led to the creation of powerful Artificial Intelligence-assisted writing tools. These tools are capable of predicting users' needs and actively providing suggestions as they write. In this work, we conduct a comparative user-study between such tools from an information retrieval lens: pull and push. Specifically, we investigate the user demand of AI-assisted writing, the impact of the two paradigms on quality, ownership of the writing product, and efficiency and enjoyment of the writing process. We also seek to understand the impact of bias of AI-assisted writing. Our findings show that users welcome seamless assistance of AI in their writing. Furthermore, AI helped users to diversify the ideas in their writing while keeping it clear and concise more quickly. Users also enjoyed the collaboration with AI-assisted writing tools and did not feel a lack of ownership. Finally, although participants did not experience bias in our experiments, they still expressed explicit and clear concerns that should be addressed in future AI-assisted writing tools.

OntoType: Ontology-Guided Zero-Shot Fine-Grained Entity Typing with Weak Supervision from Pre-Trained Language Models

Fine-grained entity typing (FET), which assigns entities in text with context-sensitive, fine-grained semantic types, will play an important role in natural language understanding. A supervised FET method, which typically relies on human-annotated corpora for training, is costly and difficult to scale. Recent studies leverage pre-trained language models (PLMs) to generate rich and context-aware weak supervision for FET. However, a PLM may still generate a mixture of rough and fine-grained types, or tokens unsuitable for typing. In this study, we vision that an ontology provides a semantics-rich, hierarchical structure, which will help select the best results generated by multiple PLM models and head words. Specifically, we propose a novel zero-shot, ontology-guided FET method, OntoType, which follows a type ontological structure, from coarse to fine, ensembles multiple PLM prompting results to generate a set of type candidates, and refines its type resolution, under the local context with a natural language inference model. Our experiments on the Ontonotes, FIGER, and NYT datasets using their associated ontological structures demonstrate that our method outperforms the state-of-the-art zero-shot fine-grained entity typing methods. Our error analysis shows that refinement of the existing ontology structures will further improve fine-grained entity typing.

MEGClass: Text Classification with Extremely Weak Supervision via Mutually-Enhancing Text Granularities

Text classification typically requires a substantial amount of human-annotated data to serve as supervision, which is costly to obtain in dynamic emerging domains. Certain methods seek to address this problem by solely relying on the surface text of class names to serve as extremely weak supervision. However, existing methods fail to account for single-class documents discussing multiple topics. Both topic diversity and vague sentences may introduce noise into the document's underlying representation and consequently the precision of the predicted class. Furthermore, current work focuses on text granularities (documents, sentences, or words) independently, which limits the degree of coarse- or fine-grained context that we can jointly extract from all three to identify significant subtext for classification. In order to address this problem, we propose MEGClass, an extremely weakly-supervised text classification method to exploit Mutually-Enhancing Text Granularities. Specifically, MEGClass constructs class-oriented sentence and class representations based on keywords for performing a sentence-level confidence-weighted label ensemble in order to estimate a document's initial class distribution. This serves as the target distribution for a multi-head attention network with a class-weighted contrastive loss. This network learns contextualized sentence representations and weights to form document representations that reflect its original document and sentence-level topic diversity. Retaining this heterogeneity allows MEGClass to select the most class-indicative documents to serve as iterative feedback for enhancing the class representations. Finally, these top documents are used to fine-tune a pre-trained text classifier. As demonstrated through extensive experiments on six benchmark datasets, MEGClass outperforms other weakly and extremely weakly supervised methods.