Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userSalience-Aware Event Chain Modeling for Narrative Understanding
نماذج سلسلة الحدث Aware Aware للتفاهم السردي
310
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
يمكن التفكير في رواية القصص، سواء عبر الخرافات أو التقارير الإخبارية أو الأفلام الوثائقية أو المذكرات، باعتبارها اتصال بالأحداث المثيرة للاهتمام والذين يرتبطون معا عملية ملموسة. من المستحسن استخراج سلاسل الحدث التي تمثل هذه العمليات. ومع ذلك، لا تزال هذه الاستخراج مشكلة صعبة. نؤخر أن هذا يرجع إلى طبيعة النصوص التي يتم اكتشاف السلاسل منها. ينبط نص اللغة الطبيعية على سرد من الأحداث الخرسانية والبرية مع معلومات أساسية، والسياق، والرأي، والعناصر الأخرى التي تعتبر مهمة لمجموعة متنوعة من الخطاب الضروري وأعمال البراغماتية ولكنها ليست جزءا من سلسلة الأحداث الرئيسية التي يتم إبلاغها. نقدم طرق لاستخراج هذه السلسلة الرئيسية من نص اللغة الطبيعية، عن طريق تصفية الأحداث غير البارزة والجمل الداعمة. نوضح فعالية أساليبنا بمعزل سلاسل الأحداث الهامة من خلال مقارنة تأثيرها على مهام المصب. نظرا لأنه من خلال نماذج لغة كبيرة مسبقا على سلاسلنا المستخرجة لدينا، نحصل على تحسينات في مهمتين تستفيد من فهم واضح لسلاسل الأحداث: التنبؤ السردي والمسألة الزمنية القائمة على الأحداث الرد. تؤكد التحسينات الواجب والدراسات الودي أن طريقة استخراجنا تعزز سلاسل الأحداث الهامة.
Storytelling, whether via fables, news reports, documentaries, or memoirs, can be thought of as the communication of interesting and related events that, taken together, form a concrete process. It is desirable to extract the event chains that represent such processes. However, this extraction remains a challenging problem. We posit that this is due to the nature of the texts from which chains are discovered. Natural language text interleaves a narrative of concrete, salient events with background information, contextualization, opinion, and other elements that are important for a variety of necessary discourse and pragmatics acts but are not part of the principal chain of events being communicated. We introduce methods for extracting this principal chain from natural language text, by filtering away non-salient events and supportive sentences. We demonstrate the effectiveness of our methods at isolating critical event chains by comparing their effect on downstream tasks. We show that by pre-training large language models on our extracted chains, we obtain improvements in two tasks that benefit from a clear understanding of event chains: narrative prediction and event-based temporal question answering. The demonstrated improvements and ablative studies confirm that our extraction method isolates critical event chains.
References used
https://aclanthology.org/
rate research
Read More
Recent QA with logical reasoning questions requires passage-level relations among the sentences. However, current approaches still focus on sentence-level relations interacting among tokens. In this work, we explore aggregating passage-level clues fo
r solving logical reasoning QA by using discourse-based information. We propose a discourse-aware graph network (DAGN) that reasons relying on the discourse structure of the texts. The model encodes discourse information as a graph with elementary discourse units (EDUs) and discourse relations, and learns the discourse-aware features via a graph network for downstream QA tasks. Experiments are conducted on two logical reasoning QA datasets, ReClor and LogiQA, and our proposed DAGN achieves competitive results. The source code is available at https://github.com/Eleanor-H/DAGN.
Recent evidence supports a role for coreference processing in guiding human expectations about upcoming words during reading, based on covariation between reading times and word surprisal estimated by a coreference-aware semantic processing model (Ja
ffe et al. 2020).The present study reproduces and elaborates on this finding by (1) enabling the parser to process subword information that might better approximate human morphological knowledge, and (2) extending evaluation of coreference effects from self-paced reading to human brain imaging data. Results show that an expectation-based processing effect of coreference is still evident even in the presence of the stronger psycholinguistic baseline provided by the subword model, and that the coreference effect is observed in both self-paced reading and fMRI data, providing evidence of the effect's robustness.
Abstract We present a new conjunctivist framework, neural event semantics (NES), for compositional grounded language understanding. Our approach treats all words as classifiers that compose to form a sentence meaning by multiplying output scores. The
se classifiers apply to spatial regions (events) and NES derives its semantic structure from language by routing events to different classifier argument inputs via soft attention. NES is trainable end-to-end by gradient descent with minimal supervision. We evaluate our method on compositional grounded language tasks in controlled synthetic and real-world settings. NES offers stronger generalization capability than standard function-based compositional frameworks, while improving accuracy over state-of-the-art neural methods on real-world language tasks.
Growing polarization of the news media has been blamed for fanning disagreement, controversy and even violence. Early identification of polarized topics is thus an urgent matter that can help mitigate conflict. However, accurate measurement of topic-
wise polarization is still an open research challenge. To address this gap, we propose Partisanship-aware Contextualized Topic Embeddings (PaCTE), a method to automatically detect polarized topics from partisan news sources. Specifically, utilizing a language model that has been finetuned on recognizing partisanship of the news articles, we represent the ideology of a news corpus on a topic by corpus-contextualized topic embedding and measure the polarization using cosine distance. We apply our method to a dataset of news articles about the COVID-19 pandemic. Extensive experiments on different news sources and topics demonstrate the efficacy of our method to capture topical polarization, as indicated by its effectiveness of retrieving the most polarized topics.
Although many end-to-end context-aware neural machine translation models have been proposed to incorporate inter-sentential contexts in translation, these models can be trained only in domains where parallel documents with sentential alignments exist
. We therefore present a simple method to perform context-aware decoding with any pre-trained sentence-level translation model by using a document-level language model. Our context-aware decoder is built upon sentence-level parallel data and target-side document-level monolingual data. From a theoretical viewpoint, our core contribution is the novel representation of contextual information using point-wise mutual information between context and the current sentence. We demonstrate the effectiveness of our method on English to Russian translation, by evaluating with BLEU and contrastive tests for context-aware translation.
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
