Learning Ordered Binary Decision Diagrams (OBDDs) from large-scale datasets is an important topic of explainable artificial intelligence. However, existing search-based methods are still limited in scalability regarding dataset size, since they must explicitly encode the satisfaction of all examples in a dataset. To tackle this challenge, we introduce an OBDD encoding method to parameterize a neural network. This method frees satisfaction encoding of all examples in a dataset while leveraging mini-batch training techniques to enhance learning efficiency. Our main theoretical contribution is to prove that our approach enables the simulation of OBDD inference within a continuous space. Besides, we identify faithful OBDD encoding to fulfill the properties required by OBDDs, allowing to interpret an OBDD directly from the learned parameter assignment. With faithful OBDD encoding, we present an end-to-end neural model named ØBDDNet, being capable of coping with large-scale datasets. Experimental results exhibit better scalability and competitive prediction performance of ØBDDNet compared to state-of-the-art OBDD learners. Valuable insights about faithful OBDD encoding are derived from the ablation study. The implementation is available at: https://github.com/jmq-design/OBDD-NET.

Aspect-based sentiment analysis (ABSA) has attracted much attention due to its wide application scenarios. Most previous studies have focused solely on monolingual ABSA, posing a formidable challenge when extending ABSA applications to multilingual scenarios. In this paper, we study upgrading monolingual ABSA to cross-lingual ABSA. Existing methods usually exploit pre-trained cross-lingual language to model cross-lingual ABSA, and enhance the model with translation data. However, the low-resource languages might be under-represented during the pre-training phase, and the translation-enhanced methods heavily rely on the quality of the translation and label projection. Inspired by the observation that quantum entanglement can correlate multiple single systems, we map the monolingual expression to the quantum Hilbert space as a single quantum system, and then utilize quantum entanglement and quantum measurement to achieve cross-lingual ABSA. Specifically, we propose a novel quantum neural model named QPEN (short for quantum projection and quantum entanglement enhanced network). It is equipped with a proposed quantum projection module that projects aspects as quantum superposition on a complex-valued Hilbert space. Furthermore, a quantum entanglement module is proposed in QPEN to share language-specific features between different languages without transmission. We conducted simulation experiments on the classical computer, and experimental results on SemEval-2016 dataset demonstrate that our method achieves state-of-the-art performance in terms of F1-scores for five languages.

Document-level relation extraction (DocRE)aims to extract relations between entities in a whole document.One of the pivotal challenges of DocRE is to capture the intricate interdependencies between relations of entity pairs.Previous methods have shown that logical rules can explicitly help capture such interdependencies.These methods either learn logical rules to refine the output of a trained DocRE model, or first learn logical rules from annotated data and then inject the learnt rules into a DocRE model using an auxiliary training objective.However, these learning pipelines may suffer from the issue of error propagation.To mitigate this issue, we propose Joint Modeling Relation extraction and Logical rules or JMRL for short, a novel rule-based framework that jointly learns both a DocRE model and logical rules in an endto-end fashion.Specifically, we parameterize a rule reasoning module in JMRL to simulate the inference of logical rules, thereby explicitly modeling the reasoning process.We also introduce an auxiliary loss and a residual connection mechanism in JMRL to better reconcile the DocRE model and the rule reasoning module.Experimental results on four benchmark datasets demonstrate that our proposed JMRL framework is consistently superior to existing rule-based frameworks, improving five baseline models for DocRE by a significant margin.

Knowledge graph completion (KGC) aims to infer missing facts from existing facts. Learning logical rules plays a pivotal role in KGC, as logical rules excel in explaining why a missing fact is inferred. Most existing rule learning methods focus merely on learning chain-like rules, neglecting type constraints on entities. In practice, type constraints are crucial in expressing precise rules. Therefore, we propose a novel formalism for logical rules named TC-rules, which complements chain-like rules with both explicit and implicit type constraints on entity variables. Accordingly, we propose an end-to-end approach to effectively learn TC-rules, by parameterizing a neural model to simulate the inference of TC-rules. Considering that existing end-to-end methods learn two different sets of logical rules to respectively answer a head query (?,rnew, t) and a tail query (h,rrnew, ?), leading to confusing explanations for supporting a new fact (h,rnew, t), we propose a bi-directional learning mechanism to ensure that the TC-rules learnt for answering (?,rnew, t) are the same as the TC-rules learnt for answering (h,rnew, ?). Experimental results on eight benchmark datasets demonstrate that the proposed method outperforms state-of-the-art rule learners in both the link prediction task and the triple classification task. Furthermore, our case study confirms that expressive TC-rules can be extracted from the parameter assignment of the learnt neural model.

Learning rule-based systems plays a pivotal role in knowledge graph completion (KGC). Existing rule-based systems restrict the input of the system to structural knowledge only, which may omit some useful knowledge for reasoning, e.g., textual knowledge. In this paper, we propose a two-stage framework that imposes both structural and textual knowledge to learn rule-based systems. In the first stage, we compute a set of triples with confidence scores (called \emph{soft triples}) from a text corpus by distant supervision, where a textual entailment model with multi-instance learning is exploited to estimate whether a given triple is entailed by a set of sentences. In the second stage, these soft triples are used to learn a rule-based model for KGC. To mitigate the negative impact of noise from soft triples, we propose a new formalism for rules to be learnt, named \emph{text enhanced rules} or \emph{TE-rules} for short. To effectively learn TE-rules, we propose a neural model that simulates the inference of TE-rules. We theoretically show that any set of TE-rules can always be interpreted by a certain parameter assignment of the neural model. We introduce three new datasets to evaluate the effectiveness of our method. Experimental results demonstrate that the introduction of soft triples and TE-rules results in significant performance improvements in inductive link prediction.

Cross-lingual natural language inference (XNLI) is a fundamental task in cross-lingual natural language understanding.Recently this task is commonly addressed by pre-trained cross-lingual language models.Existing methods usually enhance pre-trained language models with additional data, such as annotated parallel corpora.These additional data, however, are rare in practice, especially for low-resource languages.Inspired by recent promising results achieved by prompt-learning, this paper proposes a novel prompt-learning based framework for enhancing XNLI.It reformulates the XNLI problem to a masked language modeling problem by constructing cloze-style questions through cross-lingual templates.To enforce correspondence between different languages, the framework augments a new question for every question using a sampled template in another language and then introduces a consistency loss to make the answer probability distribution obtained from the new question as similar as possible with the corresponding distribution obtained from the original question.Experimental results on two benchmark datasets demonstrate that XNLI models enhanced by our proposed framework significantly outperform original ones under both the full-shot and few-shot cross-lingual transfer settings.

Query feeds recommendation is a new recommended paradigm in mobile search applications, where a stream of queries need to be recommended to improve user engagement. It requires a great quantity of attractive queries for recommendation. A conventional solution is to retrieve queries from a collection of past queries recorded in user search logs. However, these queries usually have poor readability and limited coverage of article content, and are thus not suitable for the query feeds recommendation scenario. Furthermore, to deploy the generated queries for recommendation, human validation, which is costly in practice, is required to filter unsuitable queries. In this paper, we propose TitIE, a query mining system to generate valuable queries using the titles of documents. We employ both an extractive text generator and an abstractive text generator to generate queries from titles. To improve the acceptance rate during human validation, we further propose a model-based scoring strategy to pre-select the queries that are more likely to be accepted during human validation. Finally, we propose a novel dual learning approach to jointly learn the generation model and the selection model by making full use of the unlabeled corpora under a semi-supervised scheme, thereby simultaneously improving the performance of both models. Results from both offline and online evaluations demonstrate the superiority of our approach.

Cross-lingual natural language inference is a fundamental task in cross-lingual natural language understanding, widely addressed by neural models recently. Existing neural model based methods either align sentence embeddings between source and target languages, heavily relying on annotated parallel corpora, or exploit pre-trained cross-lingual language models that are fine-tuned on a single language and hard to transfer knowledge to another language. To resolve these limitations in existing methods, this paper proposes an adversarial training framework to enhance both pre-trained models and classical neural models for cross-lingual natural language inference. It trains on the union of data in the source language and data in the target language, learning language-invariant features to improve the inference performance. Experimental results on the XNLI benchmark demonstrate that three popular neural models enhanced by the proposed framework significantly outperform the original models.

Aspect-based sentiment analysis (ABSA) aims to detect the targets (which are composed by continuous words), aspects and sentiment polarities in text. Published datasets from SemEval-2015 and SemEval-2016 reveal that a sentiment polarity depends on both the target and the aspect. However, most of the existing methods consider predicting sentiment polarities from either targets or aspects but not from both, thus they easily make wrong predictions on sentiment polarities. In particular, where the target is implicit, i.e., it does not appear in the given text, the methods predicting sentiment polarities from targets do not work. To tackle these limitations in ABSA, this paper proposes a novel method for target-aspect-sentiment joint detection. It relies on a pre-trained language model and can capture the dependence on both targets and aspects for sentiment prediction. Experimental results on the SemEval-2015 and SemEval-2016 restaurant datasets show that the proposed method achieves a high performance in detecting target-aspect-sentiment triples even for the implicit target cases; moreover, it even outperforms the state-of-the-art methods for those subtasks of target-aspect-sentiment detection that they are competent to.

This paper proposes a validation mechanism for newly added triples in a growing knowledge graph. Given a logical theory, a knowledge graph, a text corpus, and a new triple to be validated, this mechanism computes a sorted list of explanations for the new triple to facilitate the validation of it, where an explanation, called an abductive text evidence, is a set of pairs of the form (triple, window) where appending the set of triples on the left to the knowledge graph enforces entailment of the new triple under the logical theory, while every sentence window on the right which is contained in the text corpus explains to some degree why the triple on the left is true. From the angle of practice, a special class of abductive text evidences called TEP-based abductive text evidence is proposed, which is constructed from explanation patterns seen before in the knowledge graph. Accordingly, a method for computing the complete set of TEP-based abductive text evidences is proposed. Moreover, a method for sorting abductive text evidences based on distantly supervised learning is proposed. To evaluate the proposed validation mechanism, four knowledge graphs with logical theories are constructed from the four great classical masterpieces of Chinese literature. Experimental results on these datasets demonstrate the efficiency and effectiveness of the proposed mechanism.