While many NLP pipelines assume raw, clean texts, many texts we encounter in the wild, including a vast majority of legal documents, are not so clean, with many of them being visually structured documents (VSDs) such as PDFs. Conventional preprocessi
ng tools for VSDs mainly focused on word segmentation and coarse layout analysis, whereas fine-grained logical structure analysis (such as identifying paragraph boundaries and their hierarchies) of VSDs is underexplored. To that end, we proposed to formulate the task as prediction of transition labels'' between text fragments that maps the fragments to a tree, and developed a feature-based machine learning system that fuses visual, textual and semantic cues. Our system is easily customizable to different types of VSDs and it significantly outperformed baselines in identifying different structures in VSDs. For example, our system obtained a paragraph boundary detection F1 score of 0.953 which is significantly better than a popular PDF-to-text tool with an F1 score of 0.739.
We propose MultiDoc2Dial, a new task and dataset on modeling goal-oriented dialogues grounded in multiple documents. Most previous works treat document-grounded dialogue modeling as machine reading comprehension task based on a single given document
or passage. In this work, we aim to address more realistic scenarios where a goal-oriented information-seeking conversation involves multiple topics, and hence is grounded on different documents. To facilitate such task, we introduce a new dataset that contains dialogues grounded in multiple documents from four different domains. We also explore modeling the dialogue-based and document-based contexts in the dataset. We present strong baseline approaches and various experimental results, aiming to support further research efforts on such a task.
Extracting the most important part of legislation documents has great business value because the texts are usually very long and hard to understand. The aim of this article is to evaluate different algorithms for text summarization on EU legislation
documents. The content contains domain-specific words. We collected a text summarization dataset of EU legal documents consisting of 1563 documents, in which the mean length of summaries is 424 words. Experiments were conducted with different algorithms using the new dataset. A simple extractive algorithm was selected as a baseline. Advanced extractive algorithms, which use encoders show better results than baseline. The best result measured by ROUGE scores was achieved by a fine-tuned abstractive T5 model, which was adapted to work with long texts.
MeasEval aims at identifying quantities along with the entities that are measured with additional properties within English scientific documents. The variety of styles used makes measurements, a most crucial aspect of scientific writing, challenging
to extract. This paper presents ablation studies making the case for several preprocessing steps such as specialized tokenization rules. For linguistic structure, we encode dependency trees in a Deep Graph Convolution Network (DGCNN) for multi-task classification.
Understanding tables is an important and relevant task that involves understanding table structure as well as being able to compare and contrast information within cells. In this paper, we address this challenge by presenting a new dataset and tasks
that addresses this goal in a shared task in SemEval 2020 Task 9: Fact Verification and Evidence Finding for Tabular Data in Scientific Documents (SEM-TAB-FACTS). Our dataset contains 981 manually-generated tables and an auto-generated dataset of 1980 tables providing over 180K statement and over 16M evidence annotations. SEM-TAB-FACTS featured two sub-tasks. In sub-task A, the goal was to determine if a statement is supported, refuted or unknown in relation to a table. In sub-task B, the focus was on identifying the specific cells of a table that provide evidence for the statement. 69 teams signed up to participate in the task with 19 successful submissions to subtask A and 12 successful submissions to subtask B. We present our results and main findings from the competition.
Knowledge-intensive tasks such as question answering often require assimilating information from different sections of large inputs such as books or article collections. We propose ReadTwice, a simple and effective technique that combines several str
engths of prior approaches to model long-range dependencies with Transformers. The main idea is to read text in small segments, in parallel, summarizing each segment into a memory table to be used in a second read of the text. We show that the method outperforms models of comparable size on several question answering (QA) datasets and sets a new state of the art on the challenging NarrativeQA task, with questions about entire books.
Current document embeddings require large training corpora but fail to learn high-quality representations when confronted with a small number of domain-specific documents and rare terms. Further, they transform each document into a single embedding v
ector, making it hard to capture different notions of document similarity or explain why two documents are considered similar. In this work, we propose our Faceted Domain Encoder, a novel approach to learn multifaceted embeddings for domain-specific documents. It is based on a Siamese neural network architecture and leverages knowledge graphs to further enhance the embeddings even if only a few training samples are available. The model identifies different types of domain knowledge and encodes them into separate dimensions of the embedding, thereby enabling multiple ways of finding and comparing related documents in the vector space. We evaluate our approach on two benchmark datasets and find that it achieves the same embedding quality as state-of-the-art models while requiring only a tiny fraction of their training data. An interactive demo, our source code, and the evaluation datasets are available online: https://hpi.de/naumann/s/multifaceted-embeddings and a screencast is available on YouTube: https://youtu.be/HHcsX2clEwg
In this thesis proposal, we explore the application of event extraction to literary texts. Considering the lengths of literary documents modeling events in different granularities may be more adequate to extract meaningful information, as individual
elements contribute little to the overall semantics. We adapt the concept of schemas as sequences of events all describing a single process, connected through shared participants extending it to for multiple schemas in a document. Segmentation of event sequences into schemas is approached by modeling event sequences, on such task as the narrative cloze task, the prediction of missing events in sequences. We propose building on sequences of event embeddings to form schema embeddings, thereby summarizing sections of documents using a single representation. This approach will allow for the comparisons of different sections of documents and entire literary works. Literature is a challenging domain based on its variety of genres, yet the representation of literary content has received relatively little attention.
أصبحت قضية استرجاع المعلومات في يومنا هذا من أهم القضايا والتحدّيات التي تشغل العالم كنتيجة منطقية للتطوّر التكنولوجي المتسارع والتقدم الهائل في الفكر الإنساني والبحوث والدراسات العلمية في شتى فروع المعرفة وما رافقه من ازدياد في كميات المعلومات إلى ح
دّ يصعب التحكم بها والتعامل معها.
لذا نهدف في مشروعنا إلى تقديم نظام استرجاع معلومات يقوم بتصنيف المستندات حسب محتواها إلا أن عمليّة استرجاع المعلومات تحوي درجة من عدم التأكد في كل مرحلة من مراحلها لذا اعتمدنا على شبكات بيز للقيام بعملية التصنيف وهي شبكات احتماليّة تحوّل المعلومات إلى علاقات cause-and-effect و تعتبر واحدة من أهم الطرق الواعدة لمعالجة حالة عدم التأكد .
في البدء نقوم بالتعريف بأساسيّات شبكات بيز ونشرح مجموعة من خوارزميّات بنائها وخوارزميّات الاستدلال المستخدمة ( ولها نوعان دقيق وتقريبي).
يقوم هذه النظام بإجراء مجموعة من عمليّات المعالجة الأوليّة لنصوص المستندات ثم تطبيق عمليات إحصائية واحتمالية في مرحلة تدريب النظام والحصول على بنية شبكة بيز الموافقة لبيانات التدريب و يتم تصنيف مستند مدخل باستخدام مجموعة من خوارزميات الاستدلال الدقيق في شبكة بيز الناتجة لدينا.
بما أنّ أداء أي نظام استرجاع معلومات عادة ما يزداد دقّة عند استخدام العلاقات بين المفردات (terms) المتضمّنة في مجموعة مستندات فسنأخذ بعين الاعتبار نوعين من العلاقات في بناء الشبكة:
1- العلاقات بين المفردات(terms).
2- العلاقات بين المفردات والأصناف(classes).
In this paper, we'll proposing a new way of labeling "Grouped
OrdPath" depends on OrdPath to improve its performance, the
important goals is to get the small storage space. We will group
nodes into sub-trees (parent and childes), except the root n
ode.
We then labeling each sub tree also held an internal sequence
labeling to distinguish a sequence of nodes.
