Elad Ben Avraham, ChangHao Li, Ron Dorfman, Roy Ganz, Oren Nuriel, Amir Dudai, Aviad Aberdam, Noah Flynn, Elman Mansimov, Aditya Kalyanpur, Ron Litman. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Traditional symbolic reasoning engines, while attractive for their precision and explicability, have a few major drawbacks: the use of brittle inference procedures that rely on exact matching (unification) of logical terms, an inability to deal with uncertainty, and the need for a precompiled rule-base of knowledge (the “knowledge acquisition” problem). To address these issues, we devise a novel logical reasoner called Braid, that supports probabilistic rules, and uses the notion of custom unification functions and dynamic rule generation to overcome the brittle matching and knowledge-gap problem prevalent in traditional reasoners. In this paper, we describe the reasoning algorithms used in Braid, and their implementation in a distributed task-based framework that builds proof/explanation graphs for an input query. We use a simple QA example from a children’s story to motivate Braid’s design and explain how the various components work together to produce a coherent logical explanation. Finally, we evaluate Braid on the ROC Story Cloze test and achieve close to state-of-the-art results while providing frame-based explanations.

In Natural Language (NL) applications, there is often a mismatch between what the NL interface is capable of interpreting and what a lay user knows how to express. This work describes a novel natural language interface that reduces this mismatch by refining natural language input through successive, automatically generated semi-structured templates. In this paper we describe how our approach, called SKATE, uses a neural semantic parser to parse NL input and suggest semi-structured templates, which are recursively filled to produce fully structured interpretations. We also show how SKATE integrates with a neural rule-generation model to interactively suggest and acquire commonsense knowledge. We provide a preliminary coverage analysis of SKATE for the task of story understanding, and then describe a current business use-case of the technology in a restricted domain: COVID-19 policy design.

Nasrin Mostafazadeh, Aditya Kalyanpur, Lori Moon, David Buchanan, Lauren Berkowitz, Or Biran, Jennifer Chu-Carroll. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). 2020.

Abstract Typically, automatic Question Answering (QA) approaches use the question in its entirety in the search for potential answers. We argue that decomposing complex factoid questions into separate facts about their answers is beneficial to QA, since an answer candidate with support coming from multiple independent facts is more likely to be the correct one. We broadly categorize decomposable questions as parallel or nested, and we present a novel question decomposition framework for enhancing the ability of single-shot QA systems to answer complex factoid questions. Essential to the framework are components for decomposition recognition, question rewriting, and candidate answer synthesis and re-ranking. We discuss the interplay among these, with particular emphasis on decomposition recognition, a process which, we argue, can be sufficiently informed by lexico-syntactic features alone. We validate our approach to decomposition by implementing the framework on top of IBM Watson™, a state-of-the-art QA system, and showing a statistically significant improvement over its accuracy.

Automatic open-domain Question Answering has been a long standing research challenge in the AI community. IBM Research undertook this challenge with the design of the DeepQA architecture and the implementation of Watson. This paper addresses a specific subtask of Deep QA, consisting of predicting the Lexical Answer Type (LAT) of a question. Our approach is completely unsupervised and is based on PRISMATIC, a large-scale lexical knowledge base automatically extracted from a Web corpus. Experiments on the Jeopardy! data shows that it is possible to correctly predict the LAT in a substantial number of questions. This approach can be used for general purpose knowledge acquisition tasks such as frame induction from text.

Factoid questions often contain one or more assertions (facts) about their answers. However, existing question-answering (QA) systems have not investigated how the multiple facts may be leveraged to enhance system performance. We argue that decomposing complex factoid questions can benefit QA, as an answer candidate is more likely to be correct if multiple independent facts support it. We categorize decomposable questions as parallel or nested, depending on processing strategy required. We present a novel decomposition framework---for parallel and nested questions---which can be overlaid on top of traditional QA systems. It contains decomposition rules for identifying fact sub-questions, a question-rewriting component and a candidate re-ranker. In a particularly challenging domain for our baseline QA system, our framework shows a statistically significant improvement in end-to-end QA performance.

As an increasingly large number of OWL ontologies become available on the Semantic Web and the descriptions in the ontologies become more complicated, finding the cause of errors becomes an extremely hard task even for experts. Existing ontology development environments provide some limited support, in conjunction with a reasoner, for detecting and diagnosing errors in OWL ontologies. Typically these are restricted to the mere detection of, for example, unsatisfiable concepts. We have integrated a number of simple debugging cues generated from our description logic reasoner, Pellet, in our hypertextual ontology development environment, Swoop. These cues, in conjunction with extensive undo/redo and Annotea based collaboration support in Swoop, significantly improve the OWL debugging experience, and point the way to more general improvements in the presentation of an ontology to new users.

The task of building an open and scalable ontology browsing and editing tool based on OWL, the first standardized Web-oriented ontology language, requires the rethinking of critical user interface and ontological engineering issues. In this article, we describe Swoop, a browser and editor specifically tailored to OWL ontologies. Taking a “Web view” of things has proven quite instructive, and we discuss some insights into Web ontologies that we gained through our experience with Swoop, including issues related to the display, navigation, editing, and collaborative annotation of OWL ontological data.