Neural table-to-text generation models have achieved remarkable progress on an array of tasks. However, due to the data-hungry nature of neural models, their performances strongly rely on large-scale training examples, limiting their applicability in
real-world applications. To address this, we propose a new framework: Prototype-to-Generate (P2G), for table-to-text generation under the few-shot scenario. The proposed framework utilizes the retrieved prototypes, which are jointly selected by an IR system and a novel prototype selector to help the model bridging the structural gap between tables and texts. Experimental results on three benchmark datasets with three state-of-the-art models demonstrate that the proposed framework significantly improves the model performance across various evaluation metrics.
In parataxis languages like Chinese, word meanings are constructed using specific word-formations, which can help to disambiguate word senses. However, such knowledge is rarely explored in previous word sense disambiguation (WSD) methods. In this pap
er, we propose to leverage word-formation knowledge to enhance Chinese WSD. We first construct a large-scale Chinese lexical sample WSD dataset with word-formations. Then, we propose a model FormBERT to explicitly incorporate word-formations into sense disambiguation. To further enhance generalizability, we design a word-formation predictor module in case word-formation annotations are unavailable. Experimental results show that our method brings substantial performance improvement over strong baselines.
Translation Memory (TM) system, a major component of computer-assisted translation (CAT), is widely used to improve human translators' productivity by making effective use of previously translated resource. We propose a method to achieve high-speed r
etrieval from a large translation memory by means of similarity evaluation based on vector model, and present the experimental result. Through our experiment using Lucene, an open source information retrieval search engine, we conclude that it is possible to achieve real-time retrieval speed of about tens of microseconds even for a large translation memory with 5 million segment pairs.
Despite the enormous popularity of Translation Memory systems and the active research in the field, their language processing features still suffer from certain limitations. While many recent papers focus on semantic matching capabilities of TMs, thi
s planned study will address how these tools perform when dealing with longer segments and whether this could be a cause of lower match scores. An experiment will be carried out on corpora from two different (repetitive) domains. Following the results, recommendations for future developments of new TMs will be made.
Although general question answering has been well explored in recent years, temporal question answering is a task which has not received as much focus. Our work aims to leverage a popular approach used for general question answering, answer extractio
n, in order to find answers to temporal questions within a paragraph. To train our model, we propose a new dataset, inspired by SQuAD, a state-of-the-art question answering corpus, specifically tailored to provide rich temporal information by adapting the corpus WikiWars, which contains several documents on history's greatest conflicts. Our evaluation shows that a pattern matching deep learning model, often used in general question answering, can be adapted to temporal question answering, if we accept to ask questions whose answers must be directly present within a text.
Translation memory systems (TMS) are the main component of computer-assisted translation (CAT) tools. They store translations allowing to save time by presenting translations on the database through matching of several types such as fuzzy matches, wh
ich are calculated by algorithms like the edit distance. However, studies have demonstrated the linguistic deficiencies of these systems and the difficulties in data retrieval or obtaining a high percentage of matching, especially after the application of syntactic and semantic transformations as the active/passive voice change, change of word order, substitution by a synonym or a personal pronoun, for instance. This paper presents the results of a pilot study where we analyze the qualitative and quantitative data of questionnaires conducted with professional translators of Spanish, French and Arabic in order to improve the effectiveness of TMS and explore all possibilities to integrate further linguistic processing from ten transformation types. The results are encouraging, and they allowed us to find out about the translation process itself; from which we propose a pre-editing processing tool to improve the matching and retrieving processes.
Despite the increasingly good quality of Machine Translation (MT) systems, MT outputs require corrections. Automatic Post-Editing (APE) models have been introduced to perform these corrections without human intervention. However, no system has been a
ble to fully automate the Post-Editing (PE) process. Moreover, while numerous translation tools, such as Translation Memories (TMs), largely benefit from translators' input, Human-Computer Interaction (HCI) remains limited when it comes to PE. This research-in-progress paper discusses APE models and suggests that they could be improved in more interactive scenarios, as previously done in MT with the creation of Interactive MT (IMT) systems. Based on the hypothesis that PE would benefit from HCI, two methodologies are proposed. Both suggest that traditional batch learning settings are not optimal for PE. Instead, online techniques are recommended to train and update PE models on the fly, via either real or simulated interactions with the translator.
The development of Translation Technologies, like Translation Memory and Machine Translation, has completely changed the translation industry and translator's workflow in the last decades. Nevertheless, TM and MT have been developed separately until
very recently. This ongoing project will study the external integration of TM and MT, examining if the productivity and post-editing efforts of translators are higher or lower than using only TM. To this end, we will conduct an experiment where Translation students and professional translators will be asked to translate two short texts; then we will check the post-editing efforts (temporal, technical and cognitive efforts) and the quality of the translated texts.
We introduce a taxonomic study of parallel programming models
on High-Performance architectures. We review the parallel
architectures(shared and distributed memory), and then the
development of the architectures through the emergence of the
heter
ogeneous and hybrid parallel architectures.
We review important parallel programming model as the
Partitioned Global Address Space (PGAS) model, as model for
distributed memory architectures and the Data Flow model as
model to heterogeneous and hybrid parallel programming. Finally
we present several scenarios for the use of this taxonomic study.
In this paper the effect of the distinctive properties of Shape Memory Alloy (SMA)
―the ability to undergo large deformation and restore it after stress removal‖ has been
studied to see to what degree it may affect the structural performance of mul
ti-storey tall
buildings.
Using ANSYS software, two 3D Finite Element (FE) models are built for a
composite multi-storey building (20 story) which is resistant to lateral loads by bracing
system. One of them is with steel bracing and the other is with SMA bracing. Both models
take into account nonlinear material properties of elements and geometric nonlinearity.
The model with SMA material shows improved performance compared with the
model of steel bracing in terms of residual deformations and ductile performance.
