Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userFine-grained Semantic Alignment Network for Weakly Supervised Temporal Language Grounding
شبكة محاذاة الدلالات الدلالية الجميلة لتأريض اللغة الزمنية الخاضعة للإشراف
214
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تهدف أساس التأريض اللغوي (TLG) إلى توطين شريحة فيديو في فيديو غير جذاب بناء على وصف لغة طبيعية. لتخفيف التكلفة الباهظة الثمن التوضيحية للشروح اليدوية لملصقات الحدود الزمنية، نحن مخصصة للإعداد الإشراف ضعيف، حيث يتم توفير أوصاف على مستوى الفيديو فقط للتدريب. تولد معظم الأساليب الإشرافية الأكثر إشرافا ضعفا مجموعة شريحة مرشحة وتعلم محاذاة متعددة الوسائط من خلال إطار مستمد من MIL. ومع ذلك، يتم فقد الهيكل الزمني للفيديو وكذلك الدلالات المعقدة في الجملة أثناء التعلم. في هذا العمل، نقترح إطار رواية خالية من المرشحين: شبكة محاذاة الدلالات الدلالية الجميلة (FSAN)، ل TLG الإشراف ضعيف. بدلا من عرض الجملة واللحظات المرشحة ككل، يتعلم FSAN محاذاة الدلالات المسلقة عبر الأقراص من قبل وحدة التفاعل عبر مشروط تكرارية، وتولد خريطة محاذاة من الدلالات القابلة للتكنولوجيا الراقية، وتشغيل التأريض مباشرة على أعلى الخريطة. يتم إجراء تجارب واسعة على معايير اثنين واستخدامها على نطاق واسع: تعويضات ActivityNet، و Didemo، حيث تحقق FSAN لدينا أداء حديثة من بين الفن.
Temporal language grounding (TLG) aims to localize a video segment in an untrimmed video based on a natural language description. To alleviate the expensive cost of manual annotations for temporal boundary labels,we are dedicated to the weakly supervised setting, where only video-level descriptions are provided for training. Most of the existing weakly supervised methods generate a candidate segment set and learn cross-modal alignment through a MIL-based framework. However, the temporal structure of the video as well as the complicated semantics in the sentence are lost during the learning. In this work, we propose a novel candidate-free framework: Fine-grained Semantic Alignment Network (FSAN), for weakly supervised TLG. Instead of view the sentence and candidate moments as a whole, FSAN learns token-by-clip cross-modal semantic alignment by an iterative cross-modal interaction module, generates a fine-grained cross-modal semantic alignment map, and performs grounding directly on top of the map. Extensive experiments are conducted on two widely-used benchmarks: ActivityNet-Captions, and DiDeMo, where our FSAN achieves state-of-the-art performance.
References used
https://aclanthology.org/
rate research
Read More
Temporal language grounding in videos aims to localize the temporal span relevant to the given query sentence. Previous methods treat it either as a boundary regression task or a span extraction task. This paper will formulate temporal language groun
ding into video reading comprehension and propose a Relation-aware Network (RaNet) to address it. This framework aims to select a video moment choice from the predefined answer set with the aid of coarse-and-fine choice-query interaction and choice-choice relation construction. A choice-query interactor is proposed to match the visual and textual information simultaneously in sentence-moment and token-moment levels, leading to a coarse-and-fine cross-modal interaction. Moreover, a novel multi-choice relation constructor is introduced by leveraging graph convolution to capture the dependencies among video moment choices for the best choice selection. Extensive experiments on ActivityNet-Captions, TACoS, and Charades-STA demonstrate the effectiveness of our solution. Codes will be available at https://github.com/Huntersxsx/RaNet.
Fine-grained temporal relation extraction (FineTempRel) aims to recognize the durations and timeline of event mentions in text. A missing part in the current deep learning models for FineTempRel is their failure to exploit the syntactic structures of
the input sentences to enrich the representation vectors. In this work, we propose to fill this gap by introducing novel methods to integrate the syntactic structures into the deep learning models for FineTempRel. The proposed model focuses on two types of syntactic information from the dependency trees, i.e., the syntax-based importance scores for representation learning of the words and the syntactic connections to identify important context words for the event mentions. We also present two novel techniques to facilitate the knowledge transfer between the subtasks of FineTempRel, leading to a novel model with the state-of-the-art performance for this task.
In this paper we compare the performance of three models: SGNS (skip-gram negative sampling) and augmented versions of SVD (singular value decomposition) and PPMI (Positive Pointwise Mutual Information) on a word similarity task. We particularly focu
s on the role of hyperparameter tuning for Hindi based on recommendations made in previous work (on English). Our results show that there are language specific preferences for these hyperparameters. We extend the best settings for Hindi to a set of related languages: Punjabi, Gujarati and Marathi with favourable results. We also find that a suitably tuned SVD model outperforms SGNS for most of our languages and is also more robust in a low-resource setting.
An intelligent dialogue system in a multi-turn setting should not only generate the responses which are of good quality, but it should also generate the responses which can lead to long-term success of the dialogue. Although, the current approaches i
mproved the response quality, but they over-look the training signals present in the dialogue data. We can leverage these signals to generate the weakly supervised training data for learning dialog policy and reward estimator, and make the policy take actions (generates responses) which can foresee the future direction for a successful (rewarding) conversation. We simulate the dialogue between an agent and a user (modelled similar to an agent with supervised learning objective) to interact with each other. The agent uses dynamic blocking to generate ranked diverse responses and exploration-exploitation to select among the Top-K responses. Each simulated state-action pair is evaluated (works as a weak annotation) with three quality modules: Semantic Relevant, Semantic Coherence and Consistent Flow. Empirical studies with two benchmarks indicate that our model can significantly out-perform the response quality and lead to a successful conversation on both automatic evaluation and human judgment.
Unsupervised cross-domain dependency parsing is to accomplish domain adaptation for dependency parsing without using labeled data in target domain. Existing methods are often of the pseudo-annotation type, which generates data through self-annotation
of the base model and performing iterative training. However, these methods fail to consider the change of model structure for domain adaptation. In addition, the structural information contained in the text cannot be fully exploited. To remedy these drawbacks, we propose a Semantics-Structure Adaptative Dependency Parser (SSADP), which accomplishes unsupervised cross-domain dependency parsing without relying on pseudo-annotation or data selection. In particular, we design two feature extractors to extract semantic and structural features respectively. For each type of features, a corresponding feature adaptation method is utilized to achieve domain adaptation to align the domain distribution, which effectively enhances the unsupervised cross-domain transfer capability of the model. We validate the effectiveness of our model by conducting experiments on the CODT1 and CTB9 respectively, and the results demonstrate that our model can achieve consistent performance improvement. Besides, we verify the structure transfer ability of the proposed model by introducing Weisfeiler-Lehman Test.
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
