More Like this

1. Judge the Judges: A Large-Scale Evaluation Study of Neural Language Models for Online Review Generation

   Garbacea, Cristina; Carton, Samuel; Yan, Shiyan; Mei, Qiaozhu (January 2019, Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing)

   We conduct a large-scale, systematic study to evaluate the existing evaluation methods for natural language generation in the context of generating online product reviews. We compare human-based evaluators with a variety of automated evaluation procedures, including discriminative evaluators that measure how well machine-generated text can be distinguished from human-written text, as well as word overlap metrics that assess how similar the generated text compares to human-written references. We determine to what extent these different evaluators agree on the ranking of a dozen of state-of-the-art generators for online product reviews. We find that human evaluators do not correlate well with discriminative evaluators, leaving a bigger question of whether adversarial accuracy is the correct objective for natural language generation. In general, distinguishing machine-generated text is challenging even for human evaluators, and human decisions correlate better with lexical overlaps. We find lexical diversity an intriguing metric that is indicative of the assessments of different evaluators. A post-experiment survey of participants provides insights into how to evaluate and improve the quality of natural language generation systems. 

   more » « less
2. Do Transformer Networks Improve the Discovery of Inference Rules from Text?

   Rahimi, Mahdi; Surdeanu, Mihai (June 2022, LREC proceedings)

   With their Discovery of Inference Rules from Text (DIRT) algorithm, Lin and Pantel (2001) made a seminal contribution to the field of rule acquisition from text, by adapting the distributional hypothesis of Harris (1954) to patterns that model binary relations such as X treat Y, where patterns are implemented as syntactic dependency paths. DIRT’s relevance is renewed in today’s neural era given the recent focus on interpretability in the field of natural language processing. We propose a novel take on the DIRT algorithm, where we implement the distributional hypothesis using the contextualized embeddings provided by BERT, a transformer-network-based language model (Vaswani et al., 2017; Devlin et al., 2018). In particular, we change the similarity measure between pairs of slots (i.e., the set of words matched by a pattern) from the original formula that relies on lexical items to a formula computed using contextualized embeddings. We empirically demonstrate that this new similarity method yields a better implementation of the distributional hypothesis, and this, in turn, yields patterns that outperform the original algorithm in the question answering-based evaluation proposed by Lin and Pantel (2001). 

   more » « less
3. Teaching Probabilistic Logical Reasoning to Transformers

   Nafar, Aliakbar; Venable, K Brent; Kordjamshidi, Parisa (March 2024, Association for Computational Linguistics)

   Abstract In this paper, we evaluate the capability of transformer-based language models in making inferences over uncertain text that includes uncertain rules of reasoning. We cover both Pre-trained Language Models (PLMs) and generative Large Language Models (LLMs). Our evaluation results show that both generations of language models struggle with reasoning over uncertain text. We propose a novel end-to-end fine-tuning approach, Probabilistic Constraint Training (PCT), that utilizes probabilistic logical rules as constraints in the fine-tuning phase without relying on these rules in the inference stage. To assess the effectiveness of PCT, we utilize the related corpora and, additionally, create a new and more challenging benchmark that, unlike the previous ones, uses instance-specific rules. Our study demonstrates that PCT improves the transformer-based language model’s intrinsic reasoning and makes their probabilistic logical reasoning process more explicit and explainable. Furthermore, PCT equips these models to effectively handle novel situations, including higher reasoning depth, new domains, and complex probabilistic structures. 

   more » « less
4. Knowledge Authoring with Factual English

   https://doi.org/10.4204/EPTCS.364.10  

   Wang, Yuheng; Borca-Tasciuc, Giorgian; Goel, Nikhil; Fodor, Paul; Kifer, Michael (August 2022, Electronic proceedings in theoretical computer science)

   Lierler, Yuliya; Morales, Jose F; Dodaro, Carmine; Dahl, Veroniica; Gebser, Martin; Tekle, Tuncay (Ed.)

   Knowledge representation and reasoning (KRR) systems represent knowledge as collections of facts and rules. Like databases, KRR systems contain information about domains of human activities like industrial enterprises, science, and business. KRRs can represent complex concepts and relations, and they can query and manipulate information in sophisticated ways. Unfortunately, the KRR technology has been hindered by the fact that specifying the requisite knowledge requires skills that most domain experts do not have, and professional knowledge engineers are hard to find. One solution could be to extract knowledge from English text, and a number of works have attempted to do so (OpenSesame, Google's Sling, etc.). Unfortunately, at present, extraction of logical facts from unrestricted natural language is still too inaccurate to be used for reasoning, while restricting the grammar of the language (so-called controlled natural language, or CNL) is hard for the users to learn and use. Nevertheless, some recent CNL-based approaches, such as the Knowledge Authoring Logic Machine (KALM), have shown to have very high accuracy compared to others, and a natural question is to what extent the CNL restrictions can be lifted. In this paper, we address this issue by transplanting the KALM framework to a neural natural language parser, mStanza. Here we limit our attention to authoring facts and queries and therefore our focus is what we call factual English statements. Authoring other types of knowledge, such as rules, will be considered in our followup work. As it turns out, neural network based parsers have problems of their own and the mistakes they make range from part-of-speech tagging to lemmatization to dependency errors. We present a number of techniques for combating these problems and test the new system, KALMFL (i.e., KALM for factual language), on a number of benchmarks, which show KALMFL achieves correctness in excess of 95%. 

   more » « less
5. Text-to-Model Transformation: Natural Language-Based Model Generation Framework

   https://doi.org/10.3390/systems12090369  

   Akundi, Aditya; Ontiveros, Joshua; Luna, Sergio (September 2024, Systems)

   System modeling language (SysML) diagrams generated manually by system modelers can sometimes be prone to errors, which are time-consuming and introduce subjectivity. Natural language processing (NLP) techniques and tools to create SysML diagrams can aid in improving software and systems design processes. Though NLP effectively extracts and analyzes raw text data, such as text-based requirement documents, to assist in design specification, natural language, inherent complexity, and variability pose challenges in accurately interpreting the data. In this paper, we explore the integration of NLP with SysML to automate the generation of system models from input textual requirements. We propose a model generation framework leveraging Python and the spaCy NLP library to process text input and generate class/block definition diagrams using PlantUML for visual representation. The intent of this framework is to aid in reducing the manual effort in creating SysML v1.6 diagrams—class/block definition diagrams in this case. We evaluate the effectiveness of the framework using precision and recall measures. The contribution of this paper to the systems modeling domain is two-fold. First, a review and analysis of natural language processing techniques for the automated generation of SysML diagrams are provided. Second, a framework to automatically extract textual relationships tailored for generating a class diagram/block diagram that contains the classes/blocks, their relationships, methods, and attributes is presented. 

   more » « less