Resolving pronouns to their referents has long been studied as a fundamental natural language understanding problem. Previous works on pronoun coreference resolution (PCR) mostly focus on resolving pronouns to mentions in text while ignoring the exop
horic scenario. Exophoric pronouns are common in daily communications, where speakers may directly use pronouns to refer to some objects present in the environment without introducing the objects first. Although such objects are not mentioned in the dialogue text, they can often be disambiguated by the general topics of the dialogue. Motivated by this, we propose to jointly leverage the local context and global topics of dialogues to solve the out-of-text PCR problem. Extensive experiments demonstrate the effectiveness of adding topic regularization for resolving exophoric pronouns.
Reading order detection is the cornerstone to understanding visually-rich documents (e.g., receipts and forms). Unfortunately, no existing work took advantage of advanced deep learning models because it is too laborious to annotate a large enough dat
aset. We observe that the reading order of WORD documents is embedded in their XML metadata; meanwhile, it is easy to convert WORD documents to PDFs or images. Therefore, in an automated manner, we construct ReadingBank, a benchmark dataset that contains reading order, text, and layout information for 500,000 document images covering a wide spectrum of document types. This first-ever large-scale dataset unleashes the power of deep neural networks for reading order detection. Specifically, our proposed LayoutReader captures the text and layout information for reading order prediction using the seq2seq model. It performs almost perfectly in reading order detection and significantly improves both open-source and commercial OCR engines in ordering text lines in their results in our experiments. The dataset and models are publicly available at https://aka.ms/layoutreader.
Relevance in summarization is typically de- fined based on textual information alone, without incorporating insights about a particular decision. As a result, to support risk analysis of pancreatic cancer, summaries of medical notes may include irrel
evant information such as a knee injury. We propose a novel problem, decision-focused summarization, where the goal is to summarize relevant information for a decision. We leverage a predictive model that makes the decision based on the full text to provide valuable insights on how a decision can be inferred from text. To build a summary, we then select representative sentences that lead to similar model decisions as using the full text while accounting for textual non-redundancy. To evaluate our method (DecSum), we build a testbed where the task is to summarize the first ten reviews of a restaurant in support of predicting its future rating on Yelp. DecSum substantially outperforms text-only summarization methods and model-based explanation methods in decision faithfulness and representativeness. We further demonstrate that DecSum is the only method that enables humans to outperform random chance in predicting which restaurant will be better rated in the future.
Masked language models (MLMs) have contributed to drastic performance improvements with regard to zero anaphora resolution (ZAR). To further improve this approach, in this study, we made two proposals. The first is a new pretraining task that trains
MLMs on anaphoric relations with explicit supervision, and the second proposal is a new finetuning method that remedies a notorious issue, the pretrain-finetune discrepancy. Our experiments on Japanese ZAR demonstrated that our two proposals boost the state-of-the-art performance, and our detailed analysis provides new insights on the remaining challenges.
In this paper, we present coreference resolution experiments with a newly created multilingual corpus CorefUD (Nedoluzhko et al.,2021). We focus on the following languages: Czech, Russian, Polish, German, Spanish, and Catalan. In addition to monoling
ual experiments, we combine the training data in multilingual experiments and train two joined models - for Slavic languages and for all the languages together. We rely on an end-to-end deep learning model that we slightly adapted for the CorefUD corpus. Our results show that we can profit from harmonized annotations, and using joined models helps significantly for the languages with smaller training data.
We point out that common evaluation practices for cross-document coreference resolution have been unrealistically permissive in their assumed settings, yielding inflated results. We propose addressing this issue via two evaluation methodology princip
les. First, as in other tasks, models should be evaluated on predicted mentions rather than on gold mentions. Doing this raises a subtle issue regarding singleton coreference clusters, which we address by decoupling the evaluation of mention detection from that of coreference linking. Second, we argue that models should not exploit the synthetic topic structure of the standard ECB+ dataset, forcing models to confront the lexical ambiguity challenge, as intended by the dataset creators. We demonstrate empirically the drastic impact of our more realistic evaluation principles on a competitive model, yielding a score which is 33 F1 lower compared to evaluating by prior lenient practices.
Event coreference resolution is an important research problem with many applications. Despite the recent remarkable success of pre-trained language models, we argue that it is still highly beneficial to utilize symbolic features for the task. However
, as the input for coreference resolution typically comes from upstream components in the information extraction pipeline, the automatically extracted symbolic features can be noisy and contain errors. Also, depending on the specific context, some features can be more informative than others. Motivated by these observations, we propose a novel context-dependent gated module to adaptively control the information flows from the input symbolic features. Combined with a simple noisy training method, our best models achieve state-of-the-art results on two datasets: ACE 2005 and KBP 2016.
In this paper, we propose a global, self- explainable solution to solve a prominent NLP problem: Entity Resolution (ER). We formu- late ER as a graph partitioning problem. Every mention of a real-world entity is represented by a node in the graph, an
d the pairwise sim- ilarity scores between the mentions are used to associate these nodes to exactly one clique, which represents a real-world entity in the ER domain. In this paper, we use Clique Partition- ing Problem (CPP), which is an Integer Pro- gram (IP) to formulate ER as a graph partition- ing problem and then highlight the explainable nature of this method. Since CPP is NP-Hard, we introduce an efficient solution procedure, the xER algorithm, to solve CPP as a combi- nation of finding maximal cliques in the graph and then performing generalized set packing using a novel formulation. We discuss the advantages of using xER over the traditional methods and provide the computational exper- iments and results of applying this method to ER data sets.
Post-hoc explanation methods are an important class of approaches that help understand the rationale underlying a trained model's decision. But how useful are they for an end-user towards accomplishing a given task? In this vision paper, we argue the
need for a benchmark to facilitate evaluations of the utility of post-hoc explanation methods. As a first step to this end, we enumerate desirable properties that such a benchmark should possess for the task of debugging text classifiers. Additionally, we highlight that such a benchmark facilitates not only assessing the effectiveness of explanations but also their efficiency.
Recent work on entity coreference resolution (CR) follows current trends in Deep Learning applied to embeddings and relatively simple task-related features. SOTA models do not make use of hierarchical representations of discourse structure. In this w
ork, we leverage automatically constructed discourse parse trees within a neural approach and demonstrate a significant improvement on two benchmark entity coreference-resolution datasets. We explore how the impact varies depending upon the type of mention.
