Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userSemantic Frame Forecast
توقعات الإطار الدلالي
285
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تقدم هذه الورقة توقعات إطارات دلالية، وهي مهمة تتوقع الإطارات الدلالية التي ستحدث في الجمل العشرة أو 100 أو حتى 1000 شخص في قصة تشغيل. ركز العمل السابق على التنبؤ بالمستقبل الفوري للقصة، مثل واحد إلى بعض الأحكام المقبلة. ومع ذلك، عندما يكتب الروائيون قصص طويلة، فإن توليد بعض الجمل لا يكفي لمساعدتهم على اكتساب نظرة ثاقبة رفيعة المستوى لتطوير قصة المتابعة. في هذه الورقة، نقوم بصياغة قصة طويلة كسلسلة من كتل القصة، "حيث تحتوي كل كتلة على عدد ثابت من الجمل (E.G.، 10 أو 100، أو 200). يسمح لنا هذه الصياغة بالتنبؤ بقص القصة المتابعة تتجاوز نطاق بعض الجمل. نحن نمثل كتلة قصة باستخدام الترددات المصطلح (TF) من الإطارات الدلالية فيها، وتطبيعها من خلال تردد المستندات العكسية لكل إطار (IDF). نجري تجارب توقعات دلالية للإطار على 4794 كتابا من Bookcorpus و 7،962 من الملخصات العلمية من CODA-19، مع أحجام الكتلة تتراوح بين 5 إلى 1000 جمل. تظهر النتائج أن النماذج الآلية يمكن أن تتوقع كتل قصة المتابعة أفضل من خطوط الأساس العشوائية السابقة والإعادة، مما يشير إلى جدوى المهمة. نتعلم أيضا أن النماذج التي تستخدم تمثيل الإطار كيزات تفوق جميع الأساليب الموجودة عندما يكون حجم الكتلة أكثر من 150 جمل. يوضح التقييم البشري أيضا تمثيل الإطار المقترح، عند تصوره كدولة كلمة، مفهومة وممثلا ومحددة للبشر.
This paper introduces Semantic Frame Forecast, a task that predicts the semantic frames that will occur in the next 10, 100, or even 1,000 sentences in a running story. Prior work focused on predicting the immediate future of a story, such as one to a few sentences ahead. However, when novelists write long stories, generating a few sentences is not enough to help them gain high-level insight to develop the follow-up story. In this paper, we formulate a long story as a sequence of story blocks,'' where each block contains a fixed number of sentences (e.g., 10, 100, or 200). This formulation allows us to predict the follow-up story arc beyond the scope of a few sentences. We represent a story block using the term frequencies (TF) of semantic frames in it, normalized by each frame's inverse document frequency (IDF). We conduct semantic frame forecast experiments on 4,794 books from the Bookcorpus and 7,962 scientific abstracts from CODA-19, with block sizes ranging from 5 to 1,000 sentences. The results show that automated models can forecast the follow-up story blocks better than the random, prior, and replay baselines, indicating the feasibility of the task. We also learn that the models using the frame representation as features outperform all the existing approaches when the block size is over 150 sentences. The human evaluation also shows that the proposed frame representation, when visualized as word clouds, is comprehensible, representative, and specific to humans.
References used
https://aclanthology.org/
rate research
Read More
Sentence-level extractive text summarization aims to select important sentences from a given document. However, it is very challenging to model the importance of sentences. In this paper, we propose a novel Frame Semantic-Enhanced Sentence Modeling f
or Extractive Summarization, which leverages Frame semantics to model sentences from both intra-sentence level and inter-sentence level, facilitating the text summarization task. In particular, intra-sentence level semantics leverage Frames and Frame Elements to model internal semantic structure within a sentence, while inter-sentence level semantics leverage Frame-to-Frame relations to model relationships among sentences. Extensive experiments on two benchmark corpus CNN/DM and NYT demonstrate that our model outperforms six state-of-the-art methods significantly.
Frame semantic parsing is a semantic analysis task based on FrameNet which has received great attention recently. The task usually involves three subtasks sequentially: (1) target identification, (2) frame classification and (3) semantic role labelin
g. The three subtasks are closely related while previous studies model them individually, which ignores their intern connections and meanwhile induces error propagation problem. In this work, we propose an end-to-end neural model to tackle the task jointly. Concretely, we exploit a graph-based method, regarding frame semantic parsing as a graph construction problem. All predicates and roles are treated as graph nodes, and their relations are taken as graph edges. Experiment results on two benchmark datasets of frame semantic parsing show that our method is highly competitive, resulting in better performance than pipeline models.
Frame-semantic parsers traditionally predict predicates, frames, and semantic roles in a fixed order. This paper explores the chicken-or-egg' problem of interdependencies between these components theoretically and practically. We introduce a flexible
BERT-based sequence labeling architecture that allows for predicting frames and roles independently from each other or combining them in several ways. Our results show that our setups can approximate more complex traditional models' performance, while allowing for a clearer view of the interdependencies between the pipeline's components, and of how frame and role prediction models make different use of BERT's layers.
Eye-tracking psycholinguistic studies have suggested that context-word semantic coherence and predictability influence language processing during the reading activity. In this study, we investigate the correlation between the cosine similarities comp
uted with word embedding models (both static and contextualized) and eye-tracking data from two naturalistic reading corpora. We also studied the correlations of surprisal scores computed with three state-of-the-art language models. Our results show strong correlation for the scores computed with BERT and GloVe, suggesting that similarity can play an important role in modeling reading times.
We propose a structured extension to bidirectional-context conditional language generation, or infilling,'' inspired by Frame Semantic theory. Guidance is provided through one of two approaches: (1) model fine-tuning, conditioning directly on observe
d symbolic frames, and (2) a novel extension to disjunctive lexically constrained decoding that leverages frame semantic lexical units. Automatic and human evaluations confirm that frame-guided generation allows for explicit manipulation of intended infill semantics, with minimal loss in distinguishability from human-generated text. Our methods flexibly apply to a variety of use scenarios, and we provide an interactive web demo.
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
