Hypothetical induction is recognized as the main reasoning type when scientists make observations about the world and try to propose hypotheses to explain those observations. Past research on hypothetical induction is under a constrained setting: (1) the observation annotations in the dataset are carefully manually handpicked sentences (resulting in a close-domain setting); and (2) the ground truth hypotheses are mostly commonsense knowledge, making the task less challenging. In this work, we tackle these problems by proposing the first dataset for social science academic hypotheses discovery, with the final goal to create systems that automatically generate valid, novel, and helpful scientific hypotheses, given only a pile of raw web corpus. Unlike previous settings, the new dataset requires (1) using open-domain data (raw web corpus) as observations; and (2) proposing hypotheses even new to humanity. A multi-module framework is developed for the task, including three different feedback mechanisms to boost performance, which exhibits superior performance in terms of both GPT-4 based and expert-based evaluation.To the best of our knowledge, this is the first work showing that LLMs are able to generate novel (”not existing in literature”) and valid (”reflecting reality”) scientific hypotheses.

Inductive reasoning is a core component of human intelligence. In the past research of inductive reasoning within computer science, formal language is used as representations of knowledge (facts and rules, more specifically). However, formal language can cause systematic problems for inductive reasoning such as disability of handling raw input such as natural language, sensitiveness to mislabeled data, and incapacity to handle ambiguous input. To this end, we propose a new paradigm (task) for inductive reasoning, which is to induce natural language rules from natural language facts, and create a dataset termed DEER containing 1.2k rule-fact pairs for the task, where rules and facts are written in natural language. New automatic metrics are also proposed and analysed for the evaluation of this task. With DEER, we investigate a modern approach for inductive reasoning where we use natural language as representation for knowledge instead of formal language and use pretrained language models as ”reasoners”. Moreover, we provide the first and comprehensive analysis of how well pretrained language models can induce natural language rules from natural language facts. We also propose a new framework drawing insights from philosophy literature for this task, which we show in the experiment section that surpasses baselines in both automatic and human evaluations. We discuss about our future perspectives for inductive reasoning in Section 7. Dataset and code are available at https://github.com/ZonglinY/Inductive_Reasoning.

Recent studies have revealed some issues of Multi-Head Attention (MHA), e.g., redundancy and over-parameterization. Specifically, the heads of MHA were originally designed to attend to information from different representation subspaces, whereas prior studies found that some attention heads likely learn similar features and can be pruned without harming performance. Inspired by the minimum-redundancy feature selection, we assume that focusing on the most representative and distinctive features with minimum resources can mitigate the above issues and lead to more effective and efficient MHAs. In particular, we propose Grouped Head Attention, trained with a self-supervised group constraint that group attention heads, where each group focuses on an essential but distinctive feature subset. We additionally propose a Voting-to-Stay procedure to remove redundant heads, thus achieving a transformer with lighter weights. Extensive experiments are consistent with our hypothesis. Moreover, our method achieves significant performance gains on three well-established tasks while considerably compressing parameters.

Dialogue discourse parsing is a fundamental natural language processing task. It can benefit a series of conversation-related downstream tasks including dialogue summarization and emotion recognition in conversations. However, existing parsing approaches are constrained by predefined relation types, which can impede the adaptability of the parser for downstream tasks. To this end, we propose to introduce a task-aware paradigm to improve the versatility of the parser in this paper. Moreover, to alleviate error propagation and learning bias, we design a graph-based discourse parsing model termed DialogDP. Building upon the symmetrical property of matrix-embedded parsing graphs, we have developed an innovative self-supervised mechanism that leverages both bottom-up and top-down parsing strategies. This approach allows the parsing graphs to mutually regularize and enhance each other. Empirical studies on dialogue discourse parsing datasets and a downstream task demonstrate the effectiveness and flexibility of our framework.

Pretrained language models have been shown to store knowledge in their parameters and have achieved reasonable performance in commonsense knowledge base completion (CKBC) tasks. However, CKBC is knowledge-intensive and it is reported that pretrained language models’ performance in knowledge-intensive tasks are limited because of their incapability of accessing and manipulating knowledge. As a result, we hypothesize that providing retrieved passages that contain relevant knowledge as additional input to the CKBC task will improve performance. In particular, we draw insights from Case-Based Reasoning (CBR) – which aims to solve a new problem by reasoning with retrieved relevant cases, and investigate the direct application of it to CKBC. On two benchmark datasets, we demonstrate through automatic and human evaluations that our End-to-end Case-Based Reasoning Framework (ECBRF) generates more valid, informative, and novel knowledge than the state-of-the-art COMET model for CKBC in both the fully supervised and few-shot settings. We provide insights on why previous retrieval-based methods only achieve merely the same performance with COMET. From the perspective of CBR, our framework addresses a fundamental question on whether CBR methodology can be utilized to improve deep learning models.

End-to-end models in NLP rarely encode external world knowledge about length of time. We introduce two effective models for duration prediction, which incorporate external knowledge by reading temporal-related news sentences (time-aware pre-training). Specifically, one model predicts the range/unit where the duration value falls in (R-PRED); and the other predicts the exact duration value (E-PRED). Our best model – E-PRED, substantially outperforms previous work, and captures duration information more accurately than R-PRED. We also demonstrate our models are capable of duration prediction in the unsupervised setting, outperforming the baselines.