Most of the existing discourse-level Information Extraction tasks have been modeled to be extractive in nature. However, we argue that extracting information from larger bodies of discourse-like documents requires more natural language understanding and reasoning capabilities. In our work, we propose the novel task of document-level event argument aggregation which generates consolidated event-arguments at a document-level with minimal loss of information. More specifically, we focus on generating precise document-level information frames in a multilingual setting using prompt-based methods. In this paper, we show the effectiveness of u prompt-based text generation approach to generate document-level argument spans in a low-resource and zero-shot setting. We also release the first of its kind multilingual event argument aggregation dataset that can be leveraged in other related multilingual text generation tasks as well: https://github.com/DebanjanaKar/ArgGen.

Most of the existing information extraction frameworks (Wadden et al., 2019; Veysehet al., 2020) focus on sentence-level tasks and are hardly able to capture the consolidated information from a given document. In our endeavour to generate precise document-level information frames from lengthy textual records, we introduce the task of Information Aggregation or Argument Aggregation. More specifically, our aim is to filter irrelevant and redundant argument mentions that were extracted at a sentence level and render a document level information frame. Majority of the existing works have been observed to resolve related tasks of document-level event argument extraction (Yang et al., 2018; Zheng et al., 2019) and salient entity identification (Jain et al., 2020) using supervised techniques. To remove dependency from large amounts of labelled data, we explore the task of information aggregation using weakly supervised techniques. In particular, we present an extractive algorithm with multiple sieves which adopts active learning strategies to work efficiently in low-resource settings. For this task, we have annotated our own test dataset comprising of 131 document information frames and have released the code and dataset to further research prospects in this new domain. To the best of our knowledge, we are the first to establish baseline results for this task in English. Our data and code are publicly available at https://github.com/DebanjanaKar/ArgFuse.

Event Argument extraction refers to the task of extracting structured information from unstructured text for a particular event of interest. The existing works exhibit poor capabilities to extract causal event arguments like Reason and After Effects. Futhermore, most of the existing works model this task at a sentence level, restricting the context to a local scope. While it may be effective for short spans of text, for longer bodies of text such as news articles, it has often been observed that the arguments for an event do not necessarily occur in the same sentence as that containing an event trigger. To tackle the issue of argument scattering across sentences, the use of global context becomes imperative in this task. In our work, we propose an external knowledge aided approach to infuse document level event information to aid the extraction of complex event arguments. We develop a causal network for our event-annotated dataset by extracting relevant event causal structures from ConceptNet and phrases from Wikipedia. We use the extracted event causal features in a bi-directional transformer encoder to effectively capture long-range inter-sentence dependencies. We report the effectiveness of our proposed approach through both qualitative and quantitative analysis. In this task, we establish our findings on an event annotated dataset in 5 Indian languages. This dataset adds further complexity to the task by labeling arguments of entity type (like Time, Place) as well as more complex argument types (like Reason, After-Effect). Our approach achieves state-of-the-art performance across all the five languages. Since our work does not rely on any language specific features, it can be easily extended to other languages as well.

We propose a metric for machine translation evaluation based on frame semantics which does not require the use of reference translations or human corrections, but is aimed at comparing original and translated output directly. The metrics is described on the basis of an existing manual frame-semantic annotation of a parallel corpus with an English original and a Brazilian Portuguese and a German translation. We discuss implications of our metrics design, including the potential of scaling it for multiple languages.