Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userDocument-level Event Extraction with Efficient End-to-end Learning of Cross-event Dependencies
استخراج الأحداث على مستوى المستند مع التعلم الفعال نهاية إلى نهاية التبعيات عبر الأحداث
228
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
غالبا ما يتطلب فهم الروايات بالكامل من الأحداث في سياق المستندات بأكملها ونمذجة علاقات الحدث.ومع ذلك، فإن استخراج الأحداث على مستوى المستند هو مهمة صعبة لأنها تتطلب استخراج الحدث والكيان الأساسية، والتقاط الحجج التي تمتد عبر جمل مختلفة.تعمل الأعمال الموجودة على استخراج الأحداث عادة على استخراج الأحداث من جمل واحدة، والتي تفشل في التقاط العلاقات بين الحدث تذكر على نطاق المستند، وكذلك حجج الحدث التي تظهر في جملة مختلفة عن مشغل الحدث.في هذه الورقة، نقترح نماذج طراز نهاية إلى نهاية شبكات القيمة العميقة (DVN)، خوارزمية التنبؤ منظم، لالتقاط التبعيات عبر الأحداث بكفاءة لاستخراج الأحداث على مستوى المستند.تظهر النتائج التجريبية أن نهجنا يحقق أداء قابلا للمقارنة مع النماذج القائمة على CRF على ACE05، بينما تتمتع بكفاءة حسابية أعلى بكثير.
Fully understanding narratives often requires identifying events in the context of whole documents and modeling the event relations. However, document-level event extraction is a challenging task as it requires the extraction of event and entity coreference, and capturing arguments that span across different sentences. Existing works on event extraction usually confine on extracting events from single sentences, which fail to capture the relationships between the event mentions at the scale of a document, as well as the event arguments that appear in a different sentence than the event trigger. In this paper, we propose an end-to-end model leveraging Deep Value Networks (DVN), a structured prediction algorithm, to efficiently capture cross-event dependencies for document-level event extraction. Experimental results show that our approach achieves comparable performance to CRF-based models on ACE05, while enjoys significantly higher computational efficiency.
References used
https://aclanthology.org/
rate research
Read More
Document-level event extraction is critical to various natural language processing tasks for providing structured information. Existing approaches by sequential modeling neglect the complex logic structures for long texts. In this paper, we leverage
the entity interactions and sentence interactions within long documents and transform each document into an undirected unweighted graph by exploiting the relationship between sentences. We introduce the Sentence Community to represent each event as a subgraph. Furthermore, our framework SCDEE maintains the ability to extract multiple events by sentence community detection using graph attention networks and alleviate the role overlapping issue by predicting arguments in terms of roles. Experiments demonstrate that our framework achieves competitive results over state-of-the-art methods on the large-scale document-level event extraction dataset.
Extracting relation triplets from raw text is a crucial task in Information Extraction, enabling multiple applications such as populating or validating knowledge bases, factchecking, and other downstream tasks. However, it usually involves multiple-s
tep pipelines that propagate errors or are limited to a small number of relation types. To overcome these issues, we propose the use of autoregressive seq2seq models. Such models have previously been shown to perform well not only in language generation, but also in NLU tasks such as Entity Linking, thanks to their framing as seq2seq tasks. In this paper, we show how Relation Extraction can be simplified by expressing triplets as a sequence of text and we present REBEL, a seq2seq model based on BART that performs end-to-end relation extraction for more than 200 different relation types. We show our model's flexibility by fine-tuning it on an array of Relation Extraction and Relation Classification benchmarks, with it attaining state-of-the-art performance in most of them.
Successful conversational search systems can present natural, adaptive and interactive shopping experience for online shopping customers. However, building such systems from scratch faces real word challenges from both imperfect product schema/knowle
dge and lack of training dialog data. In this work we first propose ConvSearch, an end-to-end conversational search system that deeply combines the dialog system with search. It leverages the text profile to retrieve products, which is more robust against imperfect product schema/knowledge compared with using product attributes alone. We then address the lack of data challenges by proposing an utterance transfer approach that generates dialogue utterances by using existing dialog from other domains, and leveraging the search behavior data from e-commerce retailer. With utterance transfer, we introduce a new conversational search dataset for online shopping. Experiments show that our utterance transfer method can significantly improve the availability of training dialogue data without crowd-sourcing, and the conversational search system significantly outperformed the best tested baseline.
We propose a novel problem within end-to-end learning of task oriented dialogs (TOD), in which the dialog system mimics a troubleshooting agent who helps a user by diagnosing their problem (e.g., car not starting). Such dialogs are grounded in domain
-specific flowcharts, which the agent is supposed to follow during the conversation. Our task exposes novel technical challenges for neural TOD, such as grounding an utterance to the flowchart without explicit annotation, referring to additional manual pages when user asks a clarification question, and ability to follow unseen flowcharts at test time. We release a dataset (FLODIAL) consisting of 2,738 dialogs grounded on 12 different troubleshooting flowcharts. We also design a neural model, FLONET, which uses a retrieval-augmented generation architecture to train the dialog agent. Our experiments find that FLONET can do zero-shot transfer to unseen flowcharts, and sets a strong baseline for future research.
Most previous studies on information status (IS) classification and bridging anaphora recognition assume that the gold mention or syntactic tree information is given (Hou et al., 2013; Roesiger et al., 2018; Hou, 2020; Yu and Poesio, 2020). In this p
aper, we propose an end-to-end neural approach for information status classification. Our approach consists of a mention extraction component and an information status assignment component. During the inference time, our system takes a raw text as the input and generates mentions together with their information status. On the ISNotes corpus (Markert et al., 2012), we show that our information status assignment component achieves new state-of-the-art results on fine-grained IS classification based on gold mentions. Furthermore, our system performs significantly better than other baselines for both mention extraction and fine-grained IS classification in the end-to-end setting. Finally, we apply our system on BASHI (Roesiger, 2018) and SciCorp (Roesiger, 2016) to recognize referential bridging anaphora. We find that our end-to-end system trained on ISNotes achieves competitive results on bridging anaphora recognition compared to the previous state-of-the-art system that relies on syntactic information and is trained on the in-domain datasets (Yu and Poesio, 2020).
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
