Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userShould Semantic Vector Composition be Explicit? Can it be Linear?
يجب أن تكون تكوين ناقلات الدلالات واضحة؟هل يمكن أن يكون خطيا؟
484
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
أصبحت تمثيلات ناقلات عنصر مركزي في نمذجة اللغة الدلالية، مما يؤدي إلى التداخل الرياضي مع العديد من الحقول بما في ذلك النظرية الكمومية. التركيز هو الهدف الأساسي لهذه التمثيل: تمثيل تمثيلات مع الرطب "والأسماك"، كيف ينبغي تمثيل مفهوم السمك الرطب؟ يستطلع ورقة الموضع هذه هذه السؤال من نقطتين من الرأي. الأول يعتبر أول سؤال حول ما إذا كان يمكن أن ينجح التمثيل الرياضي الصريح باستخدام الأدوات فقط من داخل الجبر الخطي، أو ما إذا كانت هناك حاجة إلى أدوات رياضية أخرى. والثاني تعتبر ما إذا كان ينبغي وصف تكوين ناقلات دلالي بصراحة رياضيا، أو ما إذا كان يمكن أن يكون تأثير جانبي نموذجي على تدريب شبكة عصبية. سؤال ثالث وأحدث هو ما إذا كان يمكن تنفيذ نموذج تركيبي على كمبيوتر Quantum. بالنظر إلى الطبيعة الخطية الجوهرية لميكانيكا الكم، نقترح أن هذه الأسئلة مرتبطة، وأن هذا الاستطلاع قد يساعد في تسليط الضوء على عمليات المرشحين لتنفيذ الكم في المستقبل.
Vector representations have become a central element in semantic language modelling, leading to mathematical overlaps with many fields including quantum theory. Compositionality is a core goal for such representations: given representations for wet' and fish', how should the concept wet fish' be represented? This position paper surveys this question from two points of view. The first considers the question of whether an explicit mathematical representation can be successful using only tools from within linear algebra, or whether other mathematical tools are needed. The second considers whether semantic vector composition should be explicitly described mathematically, or whether it can be a model-internal side-effect of training a neural network. A third and newer question is whether a compositional model can be implemented on a quantum computer. Given the fundamentally linear nature of quantum mechanics, we propose that these questions are related, and that this survey may help to highlight candidate operations for future quantum implementation.
References used
https://aclanthology.org/
rate research
Read More
Improving model generalization on held-out data is one of the core objectives in common- sense reasoning. Recent work has shown that models trained on the dataset with superficial cues tend to perform well on the easy test set with superficial cues b
ut perform poorly on the hard test set without superficial cues. Previous approaches have resorted to manual methods of encouraging models not to overfit to superficial cues. While some of the methods have improved performance on hard instances, they also lead to degraded performance on easy in- stances. Here, we propose to explicitly learn a model that does well on both the easy test set with superficial cues and the hard test set without superficial cues. Using a meta-learning objective, we learn such a model that improves performance on both the easy test set and the hard test set. By evaluating our models on Choice of Plausible Alternatives (COPA) and Commonsense Explanation, we show that our proposed method leads to improved performance on both the easy test set and the hard test set upon which we observe up to 16.5 percentage points improvement over the baseline.
Natural Language Processing (NLP) is defined by specific, separate tasks, with each their own literature, benchmark datasets, and definitions. In this position paper, we argue that for a complex problem such as the threat to democracy by non-diverse
news recommender systems, it is important to take into account a higher-order, normative goal and its implications. Experts in ethics, political science and media studies have suggested that news recommendation systems could be used to support a deliberative democracy. We reflect on the role of NLP in recommendation systems with this specific goal in mind and show that this theory of democracy helps to identify which NLP tasks and techniques can support this goal, and what work still needs to be done. This leads to recommendations for NLP researchers working on this specific problem as well as researchers working on other complex multidisciplinary problems.
The research aims to optimize the investment in solar cooling process using two
models of vessels (clay- mineral).The study was conducted at the site of Tartous in the
month (the fourth - fifth - sixth) years (2013) and that the fruits of the tomat
o study, she
stated that the pottery is causing a drop in temperature between )4-6( degrees Celsius, and
that the metal causes the low temperature range between (3-5 ) degrees Celsius although
the fruits of tomatoes preserved pottery vessels have not undergone any damage of its
structure or texture during the period of conservation (27 days) compared to the control
which is exposed to damage during the (12 days) .
To build robust question answering systems, we need the ability to verify whether answers to questions are truly correct, not just good enough'' in the context of imperfect QA datasets. We explore the use of natural language inference (NLI) as a way
to achieve this goal, as NLI inherently requires the premise (document context) to contain all necessary information to support the hypothesis (proposed answer to the question). We leverage large pre-trained models and recent prior datasets to construct powerful question conversion and decontextualization modules, which can reformulate QA instances as premise-hypothesis pairs with very high reliability. Then, by combining standard NLI datasets with NLI examples automatically derived from QA training data, we can train NLI models to evaluate QA models' proposed answers. We show that our approach improves the confidence estimation of a QA model across different domains, evaluated in a selective QA setting. Careful manual analysis over the predictions of our NLI model shows that it can further identify cases where the QA model produces the right answer for the wrong reason, i.e., when the answer sentence cannot address all aspects of the question.
Multilingual Neural Machine Translation (MNMT) trains a single NMT model that supports translation between multiple languages, rather than training separate models for different languages. Learning a single model can enhance the low-resource translat
ion by leveraging data from multiple languages. However, the performance of an MNMT model is highly dependent on the type of languages used in training, as transferring knowledge from a diverse set of languages degrades the translation performance due to negative transfer. In this paper, we propose a Hierarchical Knowledge Distillation (HKD) approach for MNMT which capitalises on language groups generated according to typological features and phylogeny of languages to overcome the issue of negative transfer. HKD generates a set of multilingual teacher-assistant models via a selective knowledge distillation mechanism based on the language groups, and then distills the ultimate multilingual model from those assistants in an adaptive way. Experimental results derived from the TED dataset with 53 languages demonstrate the effectiveness of our approach in avoiding the negative transfer effect in MNMT, leading to an improved translation performance (about 1 BLEU score in average) compared to strong baselines.
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
