Building compositional explanations requires models to combine two or more facts that, together, describe why the answer to a question is correct. Typically, these "multi-hop" explanations are evaluated relative to one (or a small number of) gold explanations. In this work, we show these evaluations substantially underestimate model performance, both in terms of the relevance of included facts, as well as the completeness of model-generated explanations, because models regularly discover and produce valid explanations that are different than gold explanations. To address this, we construct a large corpus of 126k domain-expert (science teacher) relevance ratings that augment a corpus of explanations to standardized science exam questions, discovering 80k additional relevant facts not rated as gold. We build three strong models based on different methodologies (generation, ranking, and schemas), and empirically show that while expert-augmented ratings provide better estimates of explanation quality, both original (gold) and expert-augmented automatic evaluations still substantially underestimate performance by up to 36% when compared with full manual expert judgements, with different models being disproportionately affected. This poses a significant methodological challenge to accurately evaluating explanations produced by compositional reasoning models.
相關內容
Every day people ask short questions through smart devices or online forums to seek answers to all kinds of queries. With the increasing number of questions collected it becomes difficult to provide answers to each of them, which is one of the reasons behind the growing interest in automated question answering. Some questions are similar to existing ones that have already been answered, while others could be answered by an external knowledge source such as Wikipedia. An important question is what can be revealed by analysing a large set of questions. In 2017, "We the Curious" science centre in Bristol started a project to capture the curiosity of Bristolians: the project collected more than 10,000 questions on various topics. As no rules were given during collection, the questions are truly open-domain, and ranged across a variety of topics. One important aim for the science centre was to understand what concerns its visitors had beyond science, particularly on societal and cultural issues. We addressed this question by developing an Artificial Intelligence tool that can be used to perform various processing tasks: detection of equivalence between questions; detection of topic and type; and answering of the question. As we focused on the creation of a "generalist" tool, we trained it with labelled data from different datasets. We called the resulting model QBERT. This paper describes what information we extracted from the automated analysis of the WTC corpus of open-domain questions.
Topic model evaluation, like evaluation of other unsupervised methods, can be contentious. However, the field has coalesced around automated estimates of topic coherence, which rely on the frequency of word co-occurrences in a reference corpus. Contemporary neural topic models surpass classical ones according to these metrics. At the same time, topic model evaluation suffers from a validation gap: automated coherence, developed for classical models, has not been validated using human experimentation for neural models. In addition, a meta-analysis of topic modeling literature reveals a substantial standardization gap in automated topic modeling benchmarks. To address the validation gap, we compare automated coherence with the two most widely accepted human judgment tasks: topic rating and word intrusion. To address the standardization gap, we systematically evaluate a dominant classical model and two state-of-the-art neural models on two commonly used datasets. Automated evaluations declare a winning model when corresponding human evaluations do not, calling into question the validity of fully automatic evaluations independent of human judgments.
Alternatively inferring on the visual facts and commonsense is fundamental for an advanced VQA system. This ability requires models to go beyond the literal understanding of commonsense. The system should not just treat objects as the entrance to query background knowledge, but fully ground commonsense to the visual world and imagine the possible relationships between objects, e.g., "fork, can lift, food". To comprehensively evaluate such abilities, we propose a VQA benchmark, CRIC, which introduces new types of questions about Compositional Reasoning on vIsion and Commonsense, and an evaluation metric integrating the correctness of answering and commonsense grounding. To collect such questions and rich additional annotations to support the metric, we also propose an automatic algorithm to generate question samples from the scene graph associated with the images and the relevant knowledge graph. We further analyze several representative types of VQA models on the CRIC dataset. Experimental results show that grounding the commonsense to the image region and joint reasoning on vision and commonsense are still challenging for current approaches. The dataset is available at //cricvqa.github.io.
Natural language inference (NLI) is a fundamental NLP task, investigating the entailment relationship between two texts. Popular NLI datasets present the task at sentence-level. While adequate for testing semantic representations, they fall short for testing contextual reasoning over long texts, which is a natural part of the human inference process. We introduce ConTRoL, a new dataset for ConTextual Reasoning over Long texts. Consisting of 8,325 expert-designed "context-hypothesis" pairs with gold labels, ConTRoL is a passage-level NLI dataset with a focus on complex contextual reasoning types such as logical reasoning. It is derived from competitive selection and recruitment test (verbal reasoning test) for police recruitment, with expert level quality. Compared with previous NLI benchmarks, the materials in ConTRoL are much more challenging, involving a range of reasoning types. Empirical results show that state-of-the-art language models perform by far worse than educated humans. Our dataset can also serve as a testing-set for downstream tasks like Checking Factual Correctness of Summaries.
Causal inference is a critical research topic across many domains, such as statistics, computer science, education, public policy and economics, for decades. Nowadays, estimating causal effect from observational data has become an appealing research direction owing to the large amount of available data and low budget requirement, compared with randomized controlled trials. Embraced with the rapidly developed machine learning area, various causal effect estimation methods for observational data have sprung up. In this survey, we provide a comprehensive review of causal inference methods under the potential outcome framework, one of the well known causal inference framework. The methods are divided into two categories depending on whether they require all three assumptions of the potential outcome framework or not. For each category, both the traditional statistical methods and the recent machine learning enhanced methods are discussed and compared. The plausible applications of these methods are also presented, including the applications in advertising, recommendation, medicine and so on. Moreover, the commonly used benchmark datasets as well as the open-source codes are also summarized, which facilitate researchers and practitioners to explore, evaluate and apply the causal inference methods.
Relevance search is to find top-ranked entities in a knowledge graph (KG) that are relevant to a query entity. Relevance is ambiguous, particularly over a schema-rich KG like DBpedia which supports a wide range of different semantics of relevance based on numerous types of relations and attributes. As users may lack the expertise to formalize the desired semantics, supervised methods have emerged to learn the hidden user-defined relevance from user-provided examples. Along this line, in this paper we propose a novel generative model over KGs for relevance search, named GREASE. The model applies to meta-path based relevance where a meta-path characterizes a particular type of semantics of relating the query entity to answer entities. It is also extended to support properties that constrain answer entities. Extensive experiments on two large-scale KGs demonstrate that GREASE has advanced the state of the art in effectiveness, expressiveness, and efficiency.
Recent progress in pretraining language models on large textual corpora led to a surge of improvements for downstream NLP tasks. Whilst learning linguistic knowledge, these models may also be storing relational knowledge present in the training data, and may be able to answer queries structured as "fill-in-the-blank" cloze statements. Language models have many advantages over structured knowledge bases: they require no schema engineering, allow practitioners to query about an open class of relations, are easy to extend to more data, and require no human supervision to train. We present an in-depth analysis of the relational knowledge already present (without fine-tuning) in a wide range of state-of-the-art pretrained language models. We find that (i) without fine-tuning, BERT contains relational knowledge competitive with traditional NLP methods that have some access to oracle knowledge, (ii) BERT also does remarkably well on open-domain question answering against a supervised baseline, and (iii) certain types of factual knowledge are learned much more readily than others by standard language model pretraining approaches. The surprisingly strong ability of these models to recall factual knowledge without any fine-tuning demonstrates their potential as unsupervised open-domain QA systems. The code to reproduce our analysis is available at //github.com/facebookresearch/LAMA.
Although neural network approaches achieve remarkable success on a variety of NLP tasks, many of them struggle to answer questions that require commonsense knowledge. We believe the main reason is the lack of commonsense \mbox{connections} between concepts. To remedy this, we provide a simple and effective method that leverages external commonsense knowledge base such as ConceptNet. We pre-train direct and indirect relational functions between concepts, and show that these pre-trained functions could be easily added to existing neural network models. Results show that incorporating commonsense-based function improves the baseline on three question answering tasks that require commonsense reasoning. Further analysis shows that our system \mbox{discovers} and leverages useful evidence from an external commonsense knowledge base, which is missing in existing neural network models and help derive the correct answer.
The question addressed in this paper is: If we present to a user an AI system that explains how it works, how do we know whether the explanation works and the user has achieved a pragmatic understanding of the AI? In other words, how do we know that an explanainable AI system (XAI) is any good? Our focus is on the key concepts of measurement. We discuss specific methods for evaluating: (1) the goodness of explanations, (2) whether users are satisfied by explanations, (3) how well users understand the AI systems, (4) how curiosity motivates the search for explanations, (5) whether the user's trust and reliance on the AI are appropriate, and finally, (6) how the human-XAI work system performs. The recommendations we present derive from our integration of extensive research literatures and our own psychometric evaluations.
Existing question answering (QA) datasets fail to train QA systems to perform complex reasoning and provide explanations for answers. We introduce HotpotQA, a new dataset with 113k Wikipedia-based question-answer pairs with four key features: (1) the questions require finding and reasoning over multiple supporting documents to answer; (2) the questions are diverse and not constrained to any pre-existing knowledge bases or knowledge schemas; (3) we provide sentence-level supporting facts required for reasoning, allowing QA systems to reason with strong supervision and explain the predictions; (4) we offer a new type of factoid comparison questions to test QA systems' ability to extract relevant facts and perform necessary comparison. We show that HotpotQA is challenging for the latest QA systems, and the supporting facts enable models to improve performance and make explainable predictions.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191