Neural Networks for Natural Language Inference
نویسنده
چکیده
Predicting whether a sentence entails another sentence, contradicts another sentence, or is in a neutral entailment relation with another sentence is both an important NLP task as well as a sophisticated way of testing semantic sentence encoding models. In this project, I evaluate three sentence encoding models on the Stanford Natural Language Inference (SNLI) corpus. In particular, I investigate whether the incorporation of syntactic information in the form of dependency tree labels into a recurrent model leads to better sentence representations. I confirm previous results that show that LSTM-RNNs outperform a simple sum-of-words baseline but my results also suggest that this simple method of incorporating syntactic information has no stable positive effects on the performance of the model.
منابع مشابه
Identification of Crack Location and Depth in a Structure by GMDH- type Neural Networks and ANFIS
The Existence of crack in a structure leads to local flexibility and changes the stiffness and dynamic behavior of the structure. The dynamic behavior of the cracked structure depends on the depth and the location of the crack. Hence, the changes in the dynamic behavior in the structure due to the crack can be used for identifying the location and depth of the crack. In this study the first th...
متن کاملModeling environmental indicators for land leveling, using Artificial Neural Networks and Adaptive Neuron-Fuzzy Inference System
Land leveling is one of the most important steps in soil preparation and cultivation. Although land leveling with machines requires considerable amount of energy, it delivers a suitable surface slope with minimal soil deterioration as well as damage to plants and other organisms in the soil. Notwithstanding, in recent years researchers have tried to reduce fossil fuel consumption and its delete...
متن کاملForecasting Industrial Production in Iran: A Comparative Study of Artificial Neural Networks and Adaptive Nero-Fuzzy Inference System
Forecasting industrial production is essential for efficient planning by managers. Although there are many statistical and mathematical methods for prediction, the use of intelligent algorithms with desirable features has made significant progress in recent years. The current study compared the accuracy of the Artificial Neural Networks (ANN) and Adaptive Nero-Fuzzy Inference System (ANFIS) app...
متن کاملExtensions to Tree-Recursive Neural Networks for Natural Language Inference
Understanding textual entailment and contradiction is considered fundamental to natural language understanding. Tree-recursive neural networks, which exploit valuable syntactic parse information, achieve state-of-the-art accuracy among pure sentence encoding models for this task. In this course project for CS224D, we explore two extensions to tree-recursive neural networks deep TreeLSTMs and at...
متن کاملModeling environmental indicators for land leveling, using Artificial Neural Networks and Adaptive Neuron-Fuzzy Inference System
Land leveling is one of the most important steps in soil preparation and cultivation. Although land leveling with machines requires considerable amount of energy, it delivers a suitable surface slope with minimal soil deterioration as well as damage to plants and other organisms in the soil. Notwithstanding, in recent years researchers have tried to reduce fossil fuel consumption and its delete...
متن کاملPotential Assessment of ANNs and Adaptative Neuro Fuzzy Inference systems (ANFIS) for Simulating Soil Temperature at diffrent Soil Profile Depths
Objective: Soil temperature serves as a key variable in hydrological investigations to determine soil moisture content as well as hydrological balance in watersheds. The ingoing research aims to shed lights on potential of artificial neural networks (ANNs) and Neuro-Fuzzy inference system (ANFIS) to simulate soil temperature at 5-100 cm depths. To satisfy this end, climatic and...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2016