Sentence-Chain Based Seq2seq Model for Corpus Expansion

Corpus-based approaches to sentence structures (review)

High Temperature Expansion for a Chain Model

We consider an arbitrary translationally invariant chain model, with nearest neighbors interaction and satisfying periodic boundary condition. The approach developed here allows a thermodynamic description of the chain model directly in terms of grand potential per site. This thermodynamic function is derived from an auxiliary function constructed only from open connected sub-chains. To exempli...

Corpus based coreference resolution for Farsi text

"Coreference resolution" or "finding all expressions that refer to the same entity" in a text, is one of the important requirements in natural language processing. Two words are coreference when both refer to a single entity in the text or the real world. So the main task of coreference resolution systems is to identify terms that refer to a unique entity. A coreference resolution tool could be...

Seq2seq-Attention Question Answering Model

A sequence-to-sequence attention reading comprehension model was implemented to fulfill Question Answering task defined in Stanford Question Answering Dataset (SQuAD). The basic structure was bidirectional LSTM (BiLSTM) encodings with attention mechanism as well as BiLSTM decoding. Several adjustments such as dropout, learning rate decay, and gradients clipping were used. Finally, the model ach...

Sentence Complexity in French: a Corpus-Based Approach

Language complexity is a notion widely used in a number of linguistic elds and language applications, and can be described by a number of linguistic features and practical measures. This work proposes a closer, data-oriented look at sentence complexity. Starting from a number of di erent studies, we selected and implemented 52 linguistic features and measured them on a corpus of varied French t...