Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userGrouping Words with Semantic Diversity
تجميع الكلمات مع التنوع الدلالي
390
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
يمكن أن تكون أنظمة NLP المستندة إلى التعلم العميق حساسة للرموز غير المرئية ويصعب التعلم مع المدخلات عالية الأبعاد التي تعيق التعلم بشكل خطير.نقدم نهجا من خلال تجميع كلمات الإدخال على أساس التنوع الدلالي الخاص بهم لتبسيط تمثيل لغة الإدخال مع غموض منخفض.نظرا لأن الكلمات المتنوعة الدلوية موجودة في سياقات مختلفة، فإننا قادرون على استبدال الكلمات مع مجموعاتهم وما زالت تميز معاني الكلمة التي تعتمد على سياقاتها.نقوم بتصميم العديد من الخوارزميات التي تحسب تجمعات متنوعة تستند إلى أخذ العينات العشوائية، مسافات هندسية، وتعظيم انتروبيا، ونثبت ضمانات رسمية للخوارزميات القائمة على الانتروبوي.تظهر النتائج التجريبية أن أساليبنا تعمم طرازات NLP وإظهار الدقة المعززة على وضع علامات نقاط البيع ومهام LM وتحسينات كبيرة على مهام الترجمة الآلية المتوسطة الحجم، ما يصل إلى +6.5 نقطة بلو.يتوفر شفرة المصدر لدينا في https://github.com/abdulrafae/dg.
Deep Learning-based NLP systems can be sensitive to unseen tokens and hard to learn with high-dimensional inputs, which critically hinder learning generalization. We introduce an approach by grouping input words based on their semantic diversity to simplify input language representation with low ambiguity. Since the semantically diverse words reside in different contexts, we are able to substitute words with their groups and still distinguish word meanings relying on their contexts. We design several algorithms that compute diverse groupings based on random sampling, geometric distances, and entropy maximization, and we prove formal guarantees for the entropy-based algorithms. Experimental results show that our methods generalize NLP models and demonstrate enhanced accuracy on POS tagging and LM tasks and significant improvements on medium-scale machine translation tasks, up to +6.5 BLEU points. Our source code is available at https://github.com/abdulrafae/dg.
References used
https://aclanthology.org/
rate research
Read More
The task of semantic code search is to retrieve code snippets from a source code corpus based on an information need expressed in natural language. The semantic gap between natural language and programming languages has for long been regarded as one
of the most significant obstacles to the effectiveness of keyword-based information retrieval (IR) methods. It is a common assumption that traditional'' bag-of-words IR methods are poorly suited for semantic code search: our work empirically investigates this assumption. Specifically, we examine the effectiveness of two traditional IR methods, namely BM25 and RM3, on the CodeSearchNet Corpus, which consists of natural language queries paired with relevant code snippets. We find that the two keyword-based methods outperform several pre-BERT neural models. We also compare several code-specific data pre-processing strategies and find that specialized tokenization improves effectiveness.
Word segmentation, the problem of finding word boundaries in speech, is of interest for a range of tasks. Previous papers have suggested that for sequence-to-sequence models trained on tasks such as speech translation or speech recognition, attention
can be used to locate and segment the words. We show, however, that even on monolingual data this approach is brittle. In our experiments with different input types, data sizes, and segmentation algorithms, only models trained to predict phones from words succeed in the task. Models trained to predict words from either phones or speech (i.e., the opposite direction needed to generalize to new data), yield much worse results, suggesting that attention-based segmentation is only useful in limited scenarios.
Dialogue systems pretrained with large language models generate locally coherent responses, but lack fine-grained control over responses necessary to achieve specific goals. A promising method to control response generation is exemplar-based generati
on, in which models edit exemplar responses that are retrieved from training data, or hand-written to strategically address discourse-level goals, to fit new dialogue contexts. We present an Exemplar-based Dialogue Generation model, EDGE, that uses the semantic frames present in exemplar responses to guide response generation. We show that controlling dialogue generation based on the semantic frames of exemplars improves the coherence of generated responses, while preserving semantic meaning and conversation goals present in exemplar responses.
The benchmark performance of cross-database semantic parsing has climbed steadily in recent years, catalyzed by the wide adoption of pre-trained language models. Yet existing work have shown that state-of-the-art cross-database semantic parsers strug
gle to generalize to novel user utterances, databases and query structures. To obtain transparent details on the strengths and limitation of these models, we propose a diagnostic testing approach based on controlled synthesis of canonical natural language and SQL pairs. Inspired by the CheckList, we characterize a set of essential capabilities for cross-database semantic parsing models, and detailed the method for synthesizing the corresponding test data. We evaluated a variety of high performing models using the proposed approach, and identified several non-obvious weaknesses across models (e.g. unable to correctly select many columns). Our dataset and code are released as a test suite at http://github.com/hclent/BehaviorCheckingSemPar.
In this paper, we proposed a BERT-based dimensional semantic analyzer, which is designed by incorporating with word-level information. Our model achieved three of the best results in four metrics on ROCLING 2021 Shared Task: Dimensional Sentiment Ana
lysis for Educational Texts''. We conducted a series of experiments to compare the effectiveness of different pre-trained methods. Besides, the results also proofed that our method can significantly improve the performances than classic methods. Based on the experiments, we also discussed the impact of model architectures and datasets.
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
