AdvEntuRe: Adversarial Training for Textual Entailment with Knowledge-Guided Examples Artificial Intelligence

We consider the problem of learning textual entailment models with limited supervision (5K-10K training examples), and present two complementary approaches for it. First, we propose knowledge-guided adversarial example generators for incorporating large lexical resources in entailment models via only a handful of rule templates. Second, to make the entailment model - a discriminator - more robust, we propose the first GAN-style approach for training it using a natural language example generator that iteratively adjusts based on the discriminator's performance. We demonstrate effectiveness using two entailment datasets, where the proposed methods increase accuracy by 4.7% on SciTail and by 2.8% on a 1% training sub-sample of SNLI. Notably, even a single hand-written rule, negate, improves the accuracy on the negation examples in SNLI by 6.1%.

SciTaiL: A Textual Entailment Dataset from Science Question Answering

AAAI Conferences

We present a new dataset and model for textual entailment, derived from treating multiple-choice question-answering as an entailment problem. SciTail is the first entailment set that is created solely from natural sentences that already exist independently ``in the wild'' rather than sentences authored specifically for the entailment task. Different from existing entailment datasets, we create hypotheses from science questions and the corresponding answer candidates, and premises from relevant web sentences retrieved from a large corpus. These sentences are often linguistically challenging. This, combined with the high lexical similarity of premise and hypothesis for both entailed and non-entailed pairs, makes this new entailment task particularly difficult. The resulting challenge is evidenced by state-of-the-art textual entailment systems achieving mediocre performance on SciTail, especially in comparison to a simple majority class baseline. As a step forward, we demonstrate that one can improve accuracy on SciTail by 5% using a new neural model that exploits linguistic structure.

Probabilistic Reasoning with Inconsistent Beliefs Using Inconsistency Measures

AAAI Conferences

The classical probabilistic entailment problem is to determine upper and lower bounds on the probability of formulas, given a consistent set of probabilistic assertions. We generalize this problem by omitting the consistency assumption and, thus, provide a general framework for probabilistic reasoning under inconsistency. To do so, we utilize inconsistency measures to determine probability functions that are closest to satisfying the knowledge base. We illustrate our approach on several examples and show that it has both nice formal and computational properties.

Bridging Knowledge Gaps in Neural Entailment via Symbolic Models Artificial Intelligence

Most textual entailment models focus on lexical gaps between the premise text and the hypothesis, but rarely on knowledge gaps. We focus on filling these knowledge gaps in the Science Entailment task, by leveraging an external structured knowledge base (KB) of science facts. Our new architecture combines standard neural entailment models with a knowledge lookup module. To facilitate this lookup, we propose a fact-level decomposition of the hypothesis, and verifying the resulting sub-facts against both the textual premise and the structured KB. Our model, NSnet, learns to aggregate predictions from these heterogeneous data formats. On the SciTail dataset, NSnet outperforms a simpler combination of the two predictions by 3% and the base entailment model by 5%.

A Logical Study of Partial Entailment

Journal of Artificial Intelligence Research

We introduce a novel logical notion--partial entailment--to propositional logic. In contrast with classical entailment, that a formula P partially entails another formula Q with respect to a background formula set \Gamma intuitively means that under the circumstance of \Gamma, if P is true then some "part" of Q will also be true. We distinguish three different kinds of partial entailments and formalize them by using an extended notion of prime implicant. We study their semantic properties, which show that, surprisingly, partial entailments fail for many simple inference rules. Then, we study the related computational properties, which indicate that partial entailments are relatively difficult to be computed. Finally, we consider a potential application of partial entailments in reasoning about rational agents.