Existing approaches to active learning maximize the system performance by sampling unlabeled instances for annotation that yield the most efficient training. However, when active learning is integrated with an end-user application, this can lead to frustration for participating users, as they spend time labeling instances that they would not otherwise be interested in reading. In this paper, we propose a new active learning approach that jointly optimizes the seemingly counteracting objectives of the active learning system (training efficiently) and the user (receiving useful instances). We study our approach in an educational application, which particularly benefits from this technique as the system needs to rapidly learn to predict the appropriateness of an exercise to a particular user, while the users should receive only exercises that match their skills. We evaluate multiple learning strategies and user types with data from real users and find that our joint approach better satisfies both objectives when alternative methods lead to many unsuitable exercises for end users.
Large state-of-the-art corpora for training neural networks to create abstractive summaries are mostly limited to the news genre, as it is expensive to acquire human-written summaries for other types of text at a large scale. In this paper, we present a novel automatic corpus construction approach to tackle this issue as well as three new large open-licensed summarization corpora based on our approach that can be used for training abstractive summarization models. Our constructed corpora contain fictional narratives, descriptive texts, and summaries about movies, television, and book series from different domains. All sources use a creative commons (CC) license, hence we can provide the corpora for download. In addition, we also provide a ready-to-use framework that implements our automatic construction approach to create custom corpora with desired parameters like the length of the target summary and the number of source documents from which to create the summary. The main idea behind our automatic construction approach is to use existing large text collections (e.g., thematic wikis) and automatically classify whether the texts can be used as (query-focused) multi-document summaries and align them with potential source texts. As a final contribution, we show the usefulness of our automatic construction approach by running state-of-the-art summarizers on the corpora and through a manual evaluation with human annotators.
Neural sequence-to-sequence models have been successfully applied to text compression. However, these models were trained on huge automatically induced parallel corpora, which are only available for a few domains and tasks. In this paper, we propose a novel interactive setup to neural text compression that enables transferring a model to new domains and compression tasks with minimal human supervision. This is achieved by employing active learning, which intelligently samples from a large pool of unlabeled data. Using this setup, we can successfully adapt a model trained on small data of 40k samples for a headline generation task to a general text compression dataset at an acceptable compression quality with just 500 sampled instances annotated by a human.
We propose two novel manipulation strategies for increasing and decreasing the difficulty of C-tests automatically. This is a crucial step towards generating learner-adaptive exercises for self-directed language learning and preparing language assessment tests. To reach the desired difficulty level, we manipulate the size and the distribution of gaps based on absolute and relative gap difficulty predictions. We evaluate our approach in corpus-based experiments and in a user study with 60 participants. We find that both strategies are able to generate C-tests with the desired difficulty level.
Many complex discourse-level tasks can aid domain experts in their work but require costly expert annotations for data creation. To speed up and ease annotations, we investigate the viability of automatically generated annotation suggestions for such tasks. As an example, we choose a task that is particularly hard for both humans and machines: the segmentation and classification of epistemic activities in diagnostic reasoning texts. We create and publish a new dataset covering two domains and carefully analyse the suggested annotations. We find that suggestions have positive effects on annotation speed and performance, while not introducing noteworthy biases. Envisioning suggestion models that improve with newly annotated texts, we contrast methods for continuous model adjustment and suggest the most effective setup for suggestions in future expert tasks.
A robust evaluation metric has a profound impact on the development of text generation systems. A desirable metric compares system output against references based on their semantics rather than surface forms. In this paper we investigate strategies to encode system and reference texts to devise a metric that shows a high correlation with human judgment of text quality. We validate our new metric, namely MoverScore, on a number of text generation tasks including summarization, machine translation, image captioning, and data-to-text generation, where the outputs are produced by a variety of neural and non-neural systems. Our findings suggest that metrics combining contextualized representations with a distance measure perform the best. Such metrics also demonstrate strong generalization capability across tasks. For ease-of-use we make our metrics available as web service.
Reinforcement Learning (RL)based document summarisation systems yield state-of-the-art performance in terms of ROUGE scores, because they directly use ROUGE as the rewards during training. However, summaries with high ROUGE scores often receive low human judgement. To find a better reward function that can guide RL to generate human-appealing summaries, we learn a reward function from human ratings on 2,500 summaries. Our reward function only takes the document and system summary as input. Hence, once trained, it can be used to train RL based summarisation systems without using any reference summaries. We show that our learned rewards have significantly higher correlation with human ratings than previous approaches. Human evaluation experiments show that, compared to the state-of-the-art supervised-learning systems and ROUGE-as-rewards RL summarisation systems, the RL systems using our learned rewards during training generate summaries with higher human ratings. The learned reward function and our source code are available at https://github.com/yg211/summary-reward-no-reference.
Our proposed system FAMULUS helps students learn to diagnose based on automatic feedback in virtual patient simulations, and it supports instructors in labeling training data. Diagnosing is an exceptionally difficult skill to obtain but vital for many different professions (e.g., medical doctors, teachers). Previous case simulation systems are limited to multiple-choice questions and thus cannot give constructive individualized feedback on a student’s diagnostic reasoning process. Given initially only limited data, we leverage a (replaceable) NLP model to both support experts in their further data annotation with automatic suggestions, and we provide automatic feedback for students. We argue that because the central model consistently improves, our interactive approach encourages both students and instructors to recurrently use the tool, and thus accelerate the speed of data creation and annotation. We show results from two user studies on diagnostic reasoning in medicine and teacher education and outline how our system can be extended to further use cases.
The 2017 Fake News Challenge Stage 1 (FNC-1) shared task addressed a stance classification task as a crucial first step towards detecting fake news. To date, there is no in-depth analysis paper to critically discuss FNC-1’s experimental setup, reproduce the results, and draw conclusions for next-generation stance classification methods. In this paper, we provide such an in-depth analysis for the three top-performing systems. We first find that FNC-1’s proposed evaluation metric favors the majority class, which can be easily classified, and thus overestimates the true discriminative power of the methods. Therefore, we propose a new F1-based metric yielding a changed system ranking. Next, we compare the features and architectures used, which leads to a novel feature-rich stacked LSTM model that performs on par with the best systems, but is superior in predicting minority classes. To understand the methods’ ability to generalize, we derive a new dataset and perform both in-domain and cross-domain experiments. Our qualitative and quantitative study helps interpreting the original FNC-1 scores and understand which features help improving performance and why. Our new dataset and all source code used during the reproduction study are publicly available for future research.
We propose a method to perform automatic document summarisation without using reference summaries. Instead, our method interactively learns from users’ preferences. The merit of preference-based interactive summarisation is that preferences are easier for users to provide than reference summaries. Existing preference-based interactive learning methods suffer from high sample complexity, i.e. they need to interact with the oracle for many rounds in order to converge. In this work, we propose a new objective function, which enables us to leverage active learning, preference learning and reinforcement learning techniques in order to reduce the sample complexity. Both simulation and real-user experiments suggest that our method significantly advances the state of the art. Our source code is freely available at https://github.com/UKPLab/emnlp2018-april.
Concept-map-based multi-document summarization is a variant of traditional summarization that produces structured summaries in the form of concept maps. In this work, we propose a new model for the task that addresses several issues in previous methods. It learns to identify and merge coreferent concepts to reduce redundancy, determines their importance with a strong supervised model and finds an optimal summary concept map via integer linear programming. It is also computationally more efficient than previous methods, allowing us to summarize larger document sets. We evaluate the model on two datasets, finding that it outperforms several approaches from previous work.
In this paper, we propose an extractive multi-document summarization (MDS) system using joint optimization and active learning for content selection grounded in user feedback. Our method interactively obtains user feedback to gradually improve the results of a state-of-the-art integer linear programming (ILP) framework for MDS. Our methods complement fully automatic methods in producing high-quality summaries with a minimum number of iterations and feedbacks. We conduct multiple simulation-based experiments and analyze the effect of feedback-based concept selection in the ILP setup in order to maximize the user-desired content in the summary.
Coherent extracts are a novel type of summary combining the advantages of manually created abstractive summaries, which are fluent but difficult to evaluate, and low-quality automatically created extractive summaries, which lack coherence and structure. We use a corpus of heterogeneous documents to address the issue that information seekers usually face – a variety of different types of information sources. We directly extract information from these, but minimally redact and meaningfully order it to form a coherent text. Our qualitative and quantitative evaluations show that quantitative results are not sufficient to judge the quality of a summary and that other quality criteria, such as coherence, should also be taken into account. We find that our manually created corpus is of high quality and that it has the potential to bridge the gap between reference corpora of abstracts and automatic methods producing extracts. Our corpus is available to the research community for further development.
We introduce the task of detecting cross-lingual marketing blunders, which occur if a trade name resembles an inappropriate or negatively connotated word in a target language. To this end, we suggest a formal task definition and a semi-automatic method based the propagation of pragmatic labels from Wiktionary across sense-disambiguated translations. Our final tool assists users by providing clues for problematic names in any language, which we simulate in two experiments on detecting previously occurred marketing blunders and identifying relevant clues for established international brands. We conclude the paper with a suggested research roadmap for this new task. To initiate further research, we publish our online demo along with the source code and data at http://uby.ukp.informatik.tu-darmstadt.de/blunder/.
We present UBY-LMF, an LMF-based model for large-scale, heterogeneous multilingual lexical-semantic resources (LSRs). UBY-LMF allows the standardization of LSRs down to a fine-grained level of lexical information by employing a large number of Data Categories from ISOCat. We evaluate UBY-LMF by converting nine LSRs in two languages to the corresponding format: the English WordNet, Wiktionary, Wikipedia, OmegaWiki, FrameNet and VerbNet and the German Wikipedia, Wiktionary and GermaNet. The resulting LSR, UBY (Gurevych et al., 2012), holds interoperable versions of all nine resources which can be queried by an easy to use public Java API. UBY-LMF covers a wide range of information types from expert-constructed and collaboratively constructed resources for English and German, also including links between different resources at the word sense level. It is designed to accommodate further resources and languages as well as automatically mined lexical-semantic knowledge.
This paper describes the Open Linguistics Working Group (OWLG) of the Open Knowledge Foundation (OKFN). The OWLG is an initiative concerned with linguistic data by scholars from diverse fields, including linguistics, NLP, and information science. The primary goal of the working group is to promote the idea of open linguistic resources, to develop means for their representation and to encourage the exchange of ideas across different disciplines. This paper summarizes the progress of the working group, goals that have been identified, problems that we are going to address, and recent activities and ongoing developments. Here, we put particular emphasis on the development of a Linked Open Data (sub-)cloud of linguistic resources that is currently being pursued by several OWLG members.