Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userSyntagmatic Word Embeddings for Unsupervised Learning of Selectional Preferences
كلمة Syntagmatic Word Tembedings للتعلم غير المزعوم للتفضيلات التفضيلية
220
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
يلتقط التفضيلات التجريبية (SP) إلى ميل كلمة لإجراء كلمات أخرى بشكل صحيح لتكون في العلاقة النحوية المباشرة معها، وبالتالي تبلغنا عن تكوينات الكلمات الأساسية التي هي ذات معنى. لذلك SP هو مورد قيمة لأنظمة معالجة اللغة الطبيعية (NLP) ولتكل الأسلاك. تعتبر التعلم SP عموما بمثابة مهمة خاضعة للإشراف، لأنها تتطلب جثة محاطة كمصدر لأزواج الكلمات ذات الصلة بمجرد. في هذه الورقة نظهر أن التحليل التوزيعي البسيط يمكن أن يتعلم كمية جيدة من SP دون الحاجة إلى كائن مشروح. نحن نقوم بتوسيع تقنية تضمين الكلمة العامة مع ويندوز سياق كلمة الاتجاهات لإعطاء تمثيلات الكلمات التي تلتقط العلاقات التجميعية بشكل أفضل. نقوم باختبار مجموعة بيانات SP-10K وإظهار أن تضمين التضمين الجزيئي تتفوق على الأدوات النموذجية. نقوم أيضا بتقييم النسخة الخاضعة للإشراف من هذه المدينات وإظهار أن المدينات التجميعية غير الخاضعة للكشف يمكن أن تكون جيدة مثل المضبوطات الخاضعة للإشراف. نحن نوفر أيضا شفرة المصدر لتنفيذنا.
Selectional Preference (SP) captures the tendency of a word to semantically select other words to be in direct syntactic relation with it, and thus informs us about syntactic word configurations that are meaningful. Therefore SP is a valuable resource for Natural Language Processing (NLP) systems and for semanticists. Learning SP has generally been seen as a supervised task, because it requires a parsed corpus as a source of syntactically related word pairs. In this paper we show that simple distributional analysis can learn a good amount of SP without the need for an annotated corpus. We extend the general word embedding technique with directional word context windows giving word representations that better capture syntagmatic relations. We test on the SP-10K dataset and demonstrate that syntagmatic embeddings outperform the paradigmatic embeddings. We also evaluate supervised version of these embeddings and show that unsupervised syntagmatic embeddings can be as good as supervised embeddings. We also make available the source code of our implementation.
References used
https://aclanthology.org/
rate research
Read More
Generative adversarial networks (GANs) have succeeded in inducing cross-lingual word embeddings - maps of matching words across languages - without supervision. Despite these successes, GANs' performance for the difficult case of distant languages is
still not satisfactory. These limitations have been explained by GANs' incorrect assumption that source and target embedding spaces are related by a single linear mapping and are approximately isomorphic. We assume instead that, especially across distant languages, the mapping is only piece-wise linear, and propose a multi-adversarial learning method. This novel method induces the seed cross-lingual dictionary through multiple mappings, each induced to fit the mapping for one subspace. Our experiments on unsupervised bilingual lexicon induction and cross-lingual document classification show that this method improves performance over previous single-mapping methods, especially for distant languages.
We present Query2Prod2Vec, a model that grounds lexical representations for product search in product embeddings: in our model, meaning is a mapping between words and a latent space of products in a digital shop. We leverage shopping sessions to lear
n the underlying space and use merchandising annotations to build lexical analogies for evaluation: our experiments show that our model is more accurate than known techniques from the NLP and IR literature. Finally, we stress the importance of data efficiency for product search outside of retail giants, and highlight how Query2Prod2Vec fits with practical constraints faced by most practitioners.
Weakly-supervised text classification aims to induce text classifiers from only a few user-provided seed words. The vast majority of previous work assumes high-quality seed words are given. However, the expert-annotated seed words are sometimes non-t
rivial to come up with. Furthermore, in the weakly-supervised learning setting, we do not have any labeled document to measure the seed words' efficacy, making the seed word selection process a walk in the dark''. In this work, we remove the need for expert-curated seed words by first mining (noisy) candidate seed words associated with the category names. We then train interim models with individual candidate seed words. Lastly, we estimate the interim models' error rate in an unsupervised manner. The seed words that yield the lowest estimated error rates are added to the final seed word set. A comprehensive evaluation of six binary classification tasks on four popular datasets demonstrates that the proposed method outperforms a baseline using only category name seed words and obtained comparable performance as a counterpart using expert-annotated seed words.
Word Embedding maps words to vectors of real numbers. It is derived from a large corpus and is known to capture semantic knowledge from the corpus. Word Embedding is a critical component of many state-of-the-art Deep Learning techniques. However, gen
erating good Word Embeddings is a special challenge for low-resource languages such as Nepali due to the unavailability of large text corpus. In this paper, we present NPVec1 which consists of 25 state-of-art Word Embeddings for Nepali that we have derived from a large corpus using Glove, Word2Vec, FastText, and BERT. We further provide intrinsic and extrinsic evaluations of these Embeddings using well established metrics and methods. These models are trained using 279 million word tokens and are the largest Embeddings ever trained for Nepali language. Furthermore, we have made these Embeddings publicly available to accelerate the development of Natural Language Processing (NLP) applications in Nepali.
Evaluating the quality of responses generated by open-domain conversation systems is a challenging task. This is partly because there can be multiple appropriate responses to a given dialogue history. Reference-based metrics that rely on comparisons
to a set of known correct responses often fail to account for this variety, and consequently correlate poorly with human judgment. To address this problem, researchers have investigated the possibility of assessing response quality without using a set of known correct responses. RUBER demonstrated that an automatic response evaluation model could be made using unsupervised learning for the next-utterance prediction (NUP) task. For the unsupervised learning of such model, we propose a method of manipulating a golden response to create a new negative response that is designed to be inappropriate within the context while maintaining high similarity with the original golden response. We find, from our experiments on English datasets, that using the negative samples generated by our method alongside random negative samples can increase the model's correlation with human evaluations. The process of generating such negative samples is automated and does not rely on human annotation.
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
