When to Use What: An In-Depth Comparative Empirical Analysis of OpenIE Systems for Downstream Applications

Open Information Extraction (OpenIE) has been used in the pipelines of various NLP tasks. Unfortunately, there is no clear consensus on which models to use in which tasks. Muddying things further is the lack of comparisons that take differing training sets into account. In this paper, we present an application-focused empirical survey of neural OpenIE models, training sets, and benchmarks in an effort to help users choose the most suitable OpenIE systems for their applications. We find that the different assumptions made by different models and datasets have a statistically significant effect on performance, making it important to choose the most appropriate model for one's applications. We demonstrate the applicability of our recommendations on a downstream Complex QA application.

Coordinated Topic Modeling

We propose a new problem called coordinated topic modeling that imitates human behavior while describing a text corpus. It considers a set of well-defined topics like the axes of a semantic space with a reference representation. It then uses the axes to model a corpus for easily understandable representation. This new task helps represent a corpus more interpretably by reusing existing knowledge and benefits the corpora comparison task. We design ECTM, an embedding-based coordinated topic model that effectively uses the reference representation to capture the target corpus-specific aspects while maintaining each topic's global semantics. In ECTM, we introduce the topic- and document-level supervision with a self-training mechanism to solve the problem. Finally, extensive experiments on multiple domains show the superiority of our model over other baselines.

Can Language Models Be Specific? How?

A good speaker not only needs to be correct, but also has the ability to be specific when desired, and so are language models. In this paper, we propose to measure how specific the language of pre-trained language models (PLMs) is. To achieve this, we introduce a novel approach to build a benchmark for specificity testing by forming masked token prediction tasks with prompts. For instance, given ``J. K. Rowling was born in [MASK].'', we want to test whether a more specific answer will be better filled in by PLMs, e.g., Yate instead of England. From our evaluations, we show that existing PLMs have only a slight preference for more specific answers. We identify underlying factors affecting the specificity and design two prompt-based methods to improve the specificity. Results show that the specificity of the models can be improved by the proposed methods without additional training. We believe this work can provide new insights for language modeling and encourage the research community to further explore this important but understudied problem.

Are Large Pre-Trained Language Models Leaking Your Personal Information?

Large Pre-Trained Language Models (PLMs) have facilitated and dominated many NLP tasks in recent years. However, despite the great success of PLMs, there are also privacy concerns brought with PLMs. For example, recent studies show that PLMs memorize a lot of training data, including sensitive information, while the information may be leaked unintentionally and be utilized by malicious attackers. In this paper, we propose to measure whether PLMs are prone to leaking personal information. Specifically, we attempt to query PLMs for email addresses with contexts of the email address or prompts containing the owner's name. We find that PLMs do leak personal information due to memorization. However, the risk of specific personal information being extracted by attackers is low because the models are weak at associating the personal information with its owner. We hope this work could help the community to better understand the privacy risk of PLMs and bring new insights to make PLMs safe.

DKG: A Descriptive Knowledge Graph for Explaining Relationships between Entities

In this paper, we propose Descriptive Knowledge Graph (DKG) - an open and interpretable form of modeling relationships between entities. In DKGs, relationships between entities are represented by relation descriptions. For instance, the relationship between entities of machine learning and algorithm can be described as "Machine learning explores the study and construction of algorithms that can learn from and make predictions on data." To construct DKGs, we propose a self-supervised learning method to extract relation descriptions with the analysis of dependency patterns and a transformer-based relation description synthesizing model to generate relation descriptions. Experiments demonstrate that our system can extract and generate high-quality relation descriptions for explaining entity relationships.

Domain Representative Keywords Selection: A Probabilistic Approach

We propose a probabilistic approach to select a subset of a \textit{target domain representative keywords} from a candidate set, contrasting with a context domain. Such a task is crucial for many downstream tasks in natural language processing. To contrast the target domain and the context domain, we adapt the \textit{two-component mixture model} concept to generate a distribution of candidate keywords. It provides more importance to the \textit{distinctive} keywords of the target domain than common keywords contrasting with the context domain. To support the \textit{representativeness} of the selected keywords towards the target domain, we introduce an \textit{optimization algorithm} for selecting the subset from the generated candidate distribution. We have shown that the optimization algorithm can be efficiently implemented with a near-optimal approximation guarantee. Finally, extensive experiments on multiple domains demonstrate the superiority of our approach over other baselines for the tasks of keyword summary generation and trending keywords selection.

CDM: Combining Extraction and Generation for Definition Modeling

Definitions are essential for term understanding. Recently, there is an increasing interest in extracting and generating definitions of terms automatically. However, existing approaches for this task are either extractive or abstractive - definitions are either extracted from a corpus or generated by a language generation model. In this paper, we propose to combine extraction and generation for definition modeling: first extract self- and correlative definitional information of target terms from the Web and then generate the final definitions by incorporating the extracted definitional information. Experiments demonstrate our framework can generate high-quality definitions for technical terms and outperform state-of-the-art models for definition modeling significantly.

CoVA: Context-aware Visual Attention for Webpage Information Extraction

Webpage information extraction (WIE) is an important step to create knowledge bases. For this, classical WIE methods leverage the Document Object Model (DOM) tree of a website. However, use of the DOM tree poses significant challenges as context and appearance are encoded in an abstract manner. To address this challenge we propose to reformulate WIE as a context-aware Webpage Object Detection task. Specifically, we develop a Context-aware Visual Attention-based (CoVA) detection pipeline which combines appearance features with syntactical structure from the DOM tree. To study the approach we collect a new large-scale dataset of e-commerce websites for which we manually annotate every web element with four labels: product price, product title, product image and background. On this dataset we show that the proposed CoVA approach is a new challenging baseline which improves upon prior state-of-the-art methods.

Open Relation Modeling: Learning to Define Relations between Entities

Relations between entities can be represented by different instances, e.g., a sentence containing both entities or a fact in a Knowledge Graph (KG). However, these instances may not well capture the general relations between entities, may be difficult to understand by humans, even may not be found due to the incompleteness of the knowledge source. In this paper, we introduce the Open Relation Modeling task - given two entities, generate a coherent sentence describing the relation between them. To solve this task, we propose to teach machines to generate definition-like relation descriptions by letting them learn from definitions of entities. Specifically, we fine-tune Pre-trained Language Models (PLMs) to produce definitions conditioned on extracted entity pairs. To help PLMs reason between entities and provide additional relational knowledge to PLMs for open relation modeling, we incorporate reasoning paths in KGs and include a reasoning path selection mechanism. We show that PLMs can select interpretable and informative reasoning paths by confidence estimation, and the selected path can guide PLMs to generate better relation descriptions. Experimental results show that our model can generate concise but informative relation descriptions that capture the representative characteristics of entities and relations.

Measuring Fine-Grained Domain Relevance of Terms: A Hierarchical Core-Fringe Approach

We propose to measure fine-grained domain relevance - the degree that a term is relevant to a broad (e.g., computer science) or narrow (e.g., deep learning) domain. Such measurement is crucial for many downstream tasks in natural language processing. To handle long-tail terms, we build a core-anchored semantic graph, which uses core terms with rich description information to bridge the vast remaining fringe terms semantically. To support a fine-grained domain without relying on a matching corpus for supervision, we develop hierarchical core-fringe learning, which learns core and fringe terms jointly in a semi-supervised manner contextualized in the hierarchy of the domain. To reduce expensive human efforts, we employ automatic annotation and hierarchical positive-unlabeled learning. Our approach applies to big or small domains, covers head or tail terms, and requires little human effort. Extensive experiments demonstrate that our methods outperform strong baselines and even surpass professional human performance.