Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userWhat can Neural Referential Form Selectors Learn?
ماذا يمكن أن تتعلم محددات النموذج المرجعي العصبي؟
149
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
على الرغم من تحقيق النتائج المشجعة، غالبا ما يعتقد أن نماذج توليد تعبير التعبير العصبي لا تفتقر إلى الشفافية.بركأنا نماذج اختيار النماذج المرجعية العصبية (RFS) لمعرفة إلى أي مدى يتم تعلم الميزات اللغوية التي تؤثر على شكل RE وأسرها نماذج RFS الحديثة.تظهر نتائج 8 مهام التحقيق أن جميع الميزات المحددة تعلمت إلى حد ما.تعرض المهام التحقيق المتعلقة بالحالة المرجعية والموقف النحوي أعلى أداء.تم تحقيق أدنى أداء من خلال النماذج التحقيقية المصممة للتنبؤ خصائص هيكل الخطاب خارج مستوى الجملة.
Despite achieving encouraging results, neural Referring Expression Generation models are often thought to lack transparency. We probed neural Referential Form Selection (RFS) models to find out to what extent the linguistic features influencing the RE form are learned and captured by state-of-the-art RFS models. The results of 8 probing tasks show that all the defined features were learned to some extent. The probing tasks pertaining to referential status and syntactic position exhibited the highest performance. The lowest performance was achieved by the probing models designed to predict discourse structure properties beyond the sentence level.
References used
https://aclanthology.org/
rate research
Read More
Generative language models trained on large, diverse corpora can answer questions about a passage by generating the most likely continuation of the passage followed by a question/answer pair. However, accuracy rates vary depending on the type of ques
tion asked. In this paper we keep the passage fixed, and test with a wide variety of question types, exploring the strengths and weaknesses of the GPT-3 language model. We provide the passage and test questions as a challenge set for other language models.
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.
Latent alignment objectives such as CTC and AXE significantly improve non-autoregressive machine translation models. Can they improve autoregressive models as well? We explore the possibility of training autoregressive machine translation models with
latent alignment objectives, and observe that, in practice, this approach results in degenerate models. We provide a theoretical explanation for these empirical results, and prove that latent alignment objectives are incompatible with teacher forcing.
Sub-tasks of intent classification, such as robustness to distribution shift, adaptation to specific user groups and personalization, out-of-domain detection, require extensive and flexible datasets for experiments and evaluation. As collecting such
datasets is time- and labor-consuming, we propose to use text generation methods to gather datasets. The generator should be trained to generate utterances that belong to the given intent. We explore two approaches to the generation of task-oriented utterances: in the zero-shot approach, the model is trained to generate utterances from seen intents and is further used to generate utterances for intents unseen during training. In the one-shot approach, the model is presented with a single utterance from a test intent. We perform a thorough automatic, and human evaluation of the intrinsic properties of two-generation approaches. The attributes of the generated data are close to original test sets, collected via crowd-sourcing.
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.
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
