Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userModeling the Evolution of Word Senses with Force-Directed Layouts of Co-occurrence Networks
نمذجة تطور حواس الكلمات مع تخطيطات الموجهة نحو القوة لشبكات الحدوث المشترك
336
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تتطور اللغات بمرور الوقت ومعنى الكلمات التحول.علاوة على ذلك، يمكن أن تحتوي الكلمات الفردية على حواس متعددة.ومع ذلك، غالبا ما تعكس نماذج اللغة الحالية فقط معنى كلمة واحدة لكل كلمة ولا تعكس التغييرات الدلالية بمرور الوقت.في حين أن هناك نماذج لغة يمكن أن تكون إما نموذج التغيير الدلالي من الكلمات أو حواس الكلمات المتعددة، لا يغطي أي منها كلا الجانبين في وقت واحد.نقترح خوارزمية تخطيط رسم بياني من القوات الرواية لرسم شبكة من الكلمات التي تحدث كثيرا في كثير من الأحيان.بهذه الطريقة، نحن قادرون على استخدام الرسم البياني المرسوم لتصور تطور حواس الكلمات.بالإضافة إلى ذلك، نأمل أن نمذجة بشكل مشترك التغيير الدلالي والحواس المتعددة من الكلمات النتائج في تحسينات للمهام الفردية.
Languages evolve over time and the meaning of words can shift. Furthermore, individual words can have multiple senses. However, existing language models often only reflect one word sense per word and do not reflect semantic changes over time. While there are language models that can either model semantic change of words or multiple word senses, none of them cover both aspects simultaneously. We propose a novel force-directed graph layout algorithm to draw a network of frequently co-occurring words. In this way, we are able to use the drawn graph to visualize the evolution of word senses. In addition, we hope that jointly modeling semantic change and multiple senses of words results in improvements for the individual tasks.
References used
https://aclanthology.org/
rate research
Read More
The performance of NMT systems has improved drastically in the past few years but the translation of multi-sense words still poses a challenge. Since word senses are not represented uniformly in the parallel corpora used for training, there is an exc
essive use of the most frequent sense in MT output. In this work, we propose CmBT (Contextually-mined Back-Translation), an approach for improving multi-sense word translation leveraging pre-trained cross-lingual contextual word representations (CCWRs). Because of their contextual sensitivity and their large pre-training data, CCWRs can easily capture word senses that are missing or very rare in parallel corpora used to train MT. Specifically, CmBT applies bilingual lexicon induction on CCWRs to mine sense-specific target sentences from a monolingual dataset, and then back-translates these sentences to generate a pseudo parallel corpus as additional training data for an MT system. We test the translation quality of ambiguous words on the MuCoW test suite, which was built to test the word sense disambiguation effectiveness of MT systems. We show that our system improves on the translation of difficult unseen and low frequency word senses.
Short text nowadays has become a more fashionable form of text data, e.g., Twitter posts, news titles, and product reviews. Extracting semantic topics from short texts plays a significant role in a wide spectrum of NLP applications, and neural topic
modeling is now a major tool to achieve it. Motivated by learning more coherent and semantic topics, in this paper we develop a novel neural topic model named Dual Word Graph Topic Model (DWGTM), which extracts topics from simultaneous word co-occurrence and semantic correlation graphs. To be specific, we learn word features from the global word co-occurrence graph, so as to ingest rich word co-occurrence information; we then generate text features with word features, and feed them into an encoder network to get topic proportions per-text; finally, we reconstruct texts and word co-occurrence graph with topical distributions and word features, respectively. Besides, to capture semantics of words, we also apply word features to reconstruct a word semantic correlation graph computed by pre-trained word embeddings. Upon those ideas, we formulate DWGTM in an auto-encoding paradigm and efficiently train it with the spirit of neural variational inference. Empirical results validate that DWGTM can generate more semantically coherent topics than baseline topic models.
Most natural languages have a predominant or fixed word order. For example in English the word order is usually Subject-Verb-Object. This work attempts to explain this phenomenon as well as other typological findings regarding word order from a funct
ional perspective. In particular, we examine whether fixed word order provides a functional advantage, explaining why these languages are prevalent. To this end, we consider an evolutionary model of language and demonstrate, both theoretically and using genetic algorithms, that a language with a fixed word order is optimal. We also show that adding information to the sentence, such as case markers and noun-verb distinction, reduces the need for fixed word order, in accordance with the typological findings.
The study was conducted during the period 2010-2012 in the Faculty of agriculture at the University of Tishreen, with a view to obtain organic fertilizer (sludge with plant waste), through
compost it in the form of a pile within an isolated device.
The changes have been monitoring with some physical and chemical properties of the fermented substance for the duration of fermentation, by taking samples each month and analyzed them in the laboratory.
The study has included change physical and chemical residue during the fermentation process, where the temperature has reached in the center of pile to 70 degrees Celsius and the device temperature exceeded 70 degrees Celsius to 72 degrees Celsius, and either of the pH in the fermented substance had arrived to the 7.4in the pile and 7.45 in the device, the percentage had
dropped C/N from 30/1 to 18/1 of the pile and 17/1 of the device, showing the death of 99% of the huminth eggs of the intestinal worms after 26 days from the beginning of the composting process by crumpling and 97% of the huminth eggs intestinal worms had died after 10 days from the beginning of the composting process in the device.
Spoken language understanding, usually including intent detection and slot filling, is a core component to build a spoken dialog system. Recent research shows promising results by jointly learning of those two tasks based on the fact that slot fillin
g and intent detection are sharing semantic knowledge. Furthermore, attention mechanism boosts joint learning to achieve state-of-the-art results. However, current joint learning models ignore the following important facts: 1. Long-term slot context is not traced effectively, which is crucial for future slot filling. 2. Slot tagging and intent detection could be mutually rewarding, but bi-directional interaction between slot filling and intent detection remains seldom explored. In this paper, we propose a novel approach to model long-term slot context and to fully utilize the semantic correlation between slots and intents. We adopt a key-value memory network to model slot context dynamically and to track more important slot tags decoded before, which are then fed into our decoder for slot tagging. Furthermore, gated memory information is utilized to perform intent detection, mutually improving both tasks through global optimization. Experiments on benchmark ATIS and Snips datasets show that our model achieves state-of-the-art performance and outperforms other methods, especially for the slot filling task.
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
