Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userConverting Multilayer Glosses into Semantic and Pragmatic forms with GENLIS
تحويل اللمعان متعدد الطبقات إلى أشكال دلالية وبراجمية مع جنل
278
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تقدم هذه الورقة العمل نفذت لتحويل اللمعان في لغة الإشارة الإيطالية (LIS) إلى نص ثم يقرأه بعد ذلك بواسطة Windows TTS Synthesizer من إصدار تعديل SSML من نفس النص. في حين أن العديد من الأنظمة موجودة تولد لغة الإشارة من نص، قررنا القيام بعملية عكسية وإنشاء نص من LIS. لهذا الغرض، استخدمنا نسخة من القبلات السلحفاة والأرنب، الموقعة والمتاحة على YouTube by Alba Cooperativa Sociale، التي تم تفاحها يدويا من قبل المؤلف الثاني لأطروحة سيدها. من أجل تحقيق هدفنا، قامنا بتحويل المصطلحات متعددة الطبقات إلى شروط ProLolog الخطية التي ستغذيها للمولد. في الورقة نركز على المشكلات الرئيسية التي واجهتها في تحويل اللمعان إلى تمثيل متسق من الناحية الدلوية والبرادة. الناجمة عن المشاكل الرئيسية بسبب تعقيد نص مثل الخرافة التي تتطلب تنفيذ آليات Aquerence و Action الكلام في التمثيل والتي غالبا ما تكون غير مسبوقة وتشكل معلومات ضمنية.
This paper presents work carried out to transform glosses of a fable in Italian Sign Language (LIS) into a text which is then read by a TTS synthesizer from an SSML modified version of the same text. Whereas many systems exist that generate sign language from a text, we decided to do the reverse operation and generate text from LIS. For that purpose we used a version of the fable The Tortoise and the Hare, signed and made available on Youtube by ALBA cooperativa sociale, which was annotated manually by second author for her master's thesis. In order to achieve our goal, we converted the multilayer glosses into linear Prolog terms to be fed to the generator. In the paper we focus on the main problems encountered in the transformation of the glosses into a semantically and pragmatically consistent representation. The main problems have been caused by the complexities of a text like a fable which requires coreference mechanisms and speech acts to be implemented in the representation which are often unexpressed and constitute implicit information.
References used
https://aclanthology.org/
rate research
Read More
In this paper, we describe the process of developing a multilayer semantic annotation scheme designed for extracting information from a European Portuguese corpus of news articles, at three levels, temporal, referential and semantic role labelling. T
he novelty of this scheme is the harmonization of parts 1, 4 and 9 of the ISO 24617 Language resource management - Semantic annotation framework. This annotation framework includes a set of entity structures (participants, events, times) and a set of links (temporal, aspectual, subordination, objectal and semantic roles) with several tags and attribute values that ensure adequate semantic and visual representations of news stories.
We implement the formalization of natural logic-like monotonic inference using Unscoped Episodic Logical Forms (ULFs) by Kim et al. (2020). We demonstrate this system's capacity to handle a variety of challenging semantic phenomena using the FraCaS d
ataset (Cooper et al., 1996). These results give empirical evidence for prior claims that ULF is an appropriate representation to mediate natural logic-like inferences.
Neural models trained for next utterance generation in dialogue task learn to mimic the n-gram sequences in the training set with training objectives like negative log-likelihood (NLL) or cross-entropy. Such commonly used training objectives do not f
oster generating alternate responses to a context. But, the effects of minimizing an alternate training objective that fosters a model to generate alternate response and score it on semantic similarity has not been well studied. We hypothesize that a language generation model can improve on its diversity by learning to generate alternate text during training and minimizing a semantic loss as an auxiliary objective. We explore this idea on two different sized data sets on the task of next utterance generation in goal oriented dialogues. We make two observations (1) minimizing a semantic objective improved diversity in responses in the smaller data set (Frames) but only as-good-as minimizing the NLL in the larger data set (MultiWoZ) (2) large language model embeddings can be more useful as a semantic loss objective than as initialization for token embeddings.
Style transfer has been widely explored in natural language generation with non-parallel corpus by directly or indirectly extracting a notion of style from source and target domain corpus. A common shortcoming of existing approaches is the prerequisi
te of joint annotations across all the stylistic dimensions under consideration. Availability of such dataset across a combination of styles limits the extension of these setups to multiple style dimensions. While cascading single-dimensional models across multiple styles is a possibility, it suffers from content loss, especially when the style dimensions are not completely independent of each other. In our work, we relax this requirement of jointly annotated data across multiple styles by using independently acquired data across different style dimensions without any additional annotations. We initialize an encoder-decoder setup with transformer-based language model pre-trained on a generic corpus and enhance its re-writing capability to multiple target style dimensions by employing multiple style-aware language models as discriminators. Through quantitative and qualitative evaluation, we show the ability of our model to control styles across multiple style dimensions while preserving content of the input text. We compare it against baselines involving cascaded state-of-the-art uni-dimensional style transfer models.
Most of existing extractive multi-document summarization (MDS) methods score each sentence individually and extract salient sentences one by one to compose a summary, which have two main drawbacks: (1) neglecting both the intra and cross-document rel
ations between sentences; (2) neglecting the coherence and conciseness of the whole summary. In this paper, we propose a novel MDS framework (SgSum) to formulate the MDS task as a sub-graph selection problem, in which source documents are regarded as a relation graph of sentences (e.g., similarity graph or discourse graph) and the candidate summaries are its sub-graphs. Instead of selecting salient sentences, SgSum selects a salient sub-graph from the relation graph as the summary. Comparing with traditional methods, our method has two main advantages: (1) the relations between sentences are captured by modeling both the graph structure of the whole document set and the candidate sub-graphs; (2) directly outputs an integrate summary in the form of sub-graph which is more informative and coherent. Extensive experiments on MultiNews and DUC datasets show that our proposed method brings substantial improvements over several strong baselines. Human evaluation results also demonstrate that our model can produce significantly more coherent and informative summaries compared with traditional MDS methods. Moreover, the proposed architecture has strong transfer ability from single to multi-document input, which can reduce the resource bottleneck in MDS tasks.
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
