Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userLet's be explicit about that: Distant supervision for implicit discourse relation classification via connective prediction
دعونا نكون صريحا حول ما يلي: الإشراف البعيد لتصنيف علاقة الشريط الضمني عبر التنبؤ الضام
375
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
في تصنيف علاقة الخطاب الضمني، نريد التنبؤ بالعلاقة بين الجمل المجاورة في غياب أي اتصال خطاب علني. هذا أمر صعب حتى بالنسبة للبشر، مما يؤدي إلى نقص البيانات المشروح، وهي حقيقة تجعل المهمة أكثر صعوبة في نهج التعلم الآلي الإشراف. في الدراسة الحالية، نؤدي تصنيف علاقة الخطاب الضمني دون الاعتماد على أي علاقة ضمنية المسمى. نحن غاضب من عدم وجود بيانات من خلال تفسير العلاقات الضمنية لتقليل المهمة إلى مشكلتين فرعيين: نمذجة اللغة وتصنيف علاقة خطاب صريحة، مشكلة أسهل بكثير. تبين نتائجنا التجريبية أن هذه الطريقة يمكن أن تتفوق حتى الآن على الرغم من أن الحديث، على الرغم من أن تكون أبسط بكثير من النماذج البديلة لأداء مماثل. علاوة على ذلك، نوضح أن الأداء المحقق قوي عبر المجالات كما اقترحته التجارب الصفرية في مجال مختلف تماما. يشير هذا إلى أن التطورات الحديثة في النمذجة اللغوية جعلت نماذج لغة جيدة بما فيه الكفاية في التقاط علاقات بين الجملة دون مساعدة من علامات الخطاب الصريحة.
In implicit discourse relation classification, we want to predict the relation between adjacent sentences in the absence of any overt discourse connectives. This is challenging even for humans, leading to shortage of annotated data, a fact that makes the task even more difficult for supervised machine learning approaches. In the current study, we perform implicit discourse relation classification without relying on any labeled implicit relation. We sidestep the lack of data through explicitation of implicit relations to reduce the task to two sub-problems: language modeling and explicit discourse relation classification, a much easier problem. Our experimental results show that this method can even marginally outperform the state-of-the-art, in spite of being much simpler than alternative models of comparable performance. Moreover, we show that the achieved performance is robust across domains as suggested by the zero-shot experiments on a completely different domain. This indicates that recent advances in language modeling have made language models sufficiently good at capturing inter-sentence relations without the help of explicit discourse markers.
References used
https://aclanthology.org/
rate research
Read More
Implicit discourse relation recognition (IDRR) aims to identify logical relations between two adjacent sentences in the discourse. Existing models fail to fully utilize the contextual information which plays an important role in interpreting each loc
al sentence. In this paper, we thus propose a novel graph-based Context Tracking Network (CT-Net) to model the discourse context for IDRR. The CT-Net firstly converts the discourse into the paragraph association graph (PAG), where each sentence tracks their closely related context from the intricate discourse through different types of edges. Then, the CT-Net extracts contextual representation from the PAG through a specially designed cross-grained updating mechanism, which can effectively integrate both sentence-level and token-level contextual semantics. Experiments on PDTB 2.0 show that the CT-Net gains better performance than models that roughly model the context.
For over thirty years, researchers have developed and analyzed methods for latent tree induction as an approach for unsupervised syntactic parsing. Nonetheless, modern systems still do not perform well enough compared to their supervised counterparts
to have any practical use as structural annotation of text. In this work, we present a technique that uses distant supervision in the form of span constraints (i.e. phrase bracketing) to improve performance in unsupervised constituency parsing. Using a relatively small number of span constraints we can substantially improve the output from DIORA, an already competitive unsupervised parsing system. Compared with full parse tree annotation, span constraints can be acquired with minimal effort, such as with a lexicon derived from Wikipedia, to find exact text matches. Our experiments show span constraints based on entities improves constituency parsing on English WSJ Penn Treebank by more than 5 F1. Furthermore, our method extends to any domain where span constraints are easily attainable, and as a case study we demonstrate its effectiveness by parsing biomedical text from the CRAFT dataset.
We present ReasonBert, a pre-training method that augments language models with the ability to reason over long-range relations and multiple, possibly hybrid contexts. Unlike existing pre-training methods that only harvest learning signals from local
contexts of naturally occurring texts, we propose a generalized notion of distant supervision to automatically connect multiple pieces of text and tables to create pre-training examples that require long-range reasoning. Different types of reasoning are simulated, including intersecting multiple pieces of evidence, bridging from one piece of evidence to another, and detecting unanswerable cases. We conduct a comprehensive evaluation on a variety of extractive question answering datasets ranging from single-hop to multi-hop and from text-only to table-only to hybrid that require various reasoning capabilities and show that ReasonBert achieves remarkable improvement over an array of strong baselines. Few-shot experiments further demonstrate that our pre-training method substantially improves sample efficiency.
Scientific literature analysis needs fine-grained named entity recognition (NER) to provide a wide range of information for scientific discovery. For example, chemistry research needs to study dozens to hundreds of distinct, fine-grained entity types
, making consistent and accurate annotation difficult even for crowds of domain experts. On the other hand, domain-specific ontologies and knowledge bases (KBs) can be easily accessed, constructed, or integrated, which makes distant supervision realistic for fine-grained chemistry NER. In distant supervision, training labels are generated by matching mentions in a document with the concepts in the knowledge bases (KBs). However, this kind of KB-matching suffers from two major challenges: incomplete annotation and noisy annotation. We propose ChemNER, an ontology-guided, distantly-supervised method for fine-grained chemistry NER to tackle these challenges. It leverages the chemistry type ontology structure to generate distant labels with novel methods of flexible KB-matching and ontology-guided multi-type disambiguation. It significantly improves the distant label generation for the subsequent sequence labeling model training. We also provide an expert-labeled, chemistry NER dataset with 62 fine-grained chemistry types (e.g., chemical compounds and chemical reactions). Experimental results show that ChemNER is highly effective, outperforming substantially the state-of-the-art NER methods (with .25 absolute F1 score improvement).
Implicit discourse relation recognition (IDRR) is a critical task in discourse analysis. Previous studies only regard it as a classification task and lack an in-depth understanding of the semantics of different relations. Therefore, we first view IDR
R as a generation task and further propose a method joint modeling of the classification and generation. Specifically, we propose a joint model, CG-T5, to recognize the relation label and generate the target sentence containing the meaning of relations simultaneously. Furthermore, we design three target sentence forms, including the question form, for the generation model to incorporate prior knowledge. To address the issue that large discourse units are hardly embedded into the target sentence, we also propose a target sentence construction mechanism that automatically extracts core sentences from those large discourse units. Experimental results both on Chinese MCDTB and English PDTB datasets show that our model CG-T5 achieves the best performance against several state-of-the-art systems.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
