Using theano to implement maximum likelihood learning in neural probability language model Python

Question

I'm trying to implement maximum likelihood learning for neural probability language model in python from code of log-bilinear model: https://github.com/wenjieguan/Log-bilinear-language-models/blob/master/lbl.py

I used grad function in theano to compute gradient and try using function train to update parameters of model, but it got errors. Here is my code:

def train(self, sentences, alpha = 0.001, batches = 1000):
    print('Start training...')
    self.alpha = alpha
    count = 0

    RARE = self.vocab['<>']
    #print RARE
    q = np.zeros(self.dim, np.float32)
    #print q
    delta_context = [np.zeros((self.dim, self.dim), np.float32) for i in range(self.context) ]
    #print delta_context
    delta_feature = np.zeros((len(self.vocab), self.dim), np.float32)
    #print delta_feature
    for sentence in sentences:
        sentence = self.start_sen + sentence + self.end_sen
        for pos in range(self.context, len(sentence) ):
            count += 1
            q.fill(0)
            featureW = []
            contextMatrix = []
            indices = []
            for i, r in enumerate(sentence[pos - self.context : pos]):
                if r == '<_>':
                    continue
                index = self.vocab.get(r, RARE)
                print index
                indices.append(index)
                ri = self.featureVectors[index]
                #print ri
                ci = self.contextMatrix[i]
                #print ci
                featureW.append(ri)
                contextMatrix.append(ci)
                #Caculating predicted representation for the target word
                q += np.dot(ci, ri)
            #Computing energy function
            energy = np.exp(np.dot(self.featureVectors, q) + self.biases)
            #print energy
            #Computing the conditional distribution
            probs = energy / np.sum(energy)
            #print probs
            w_index = self.vocab.get(sentence[pos], RARE)


            #Computing gradient
            logProbs = T.log(probs[w_index])
            print 'Gradient start...'
            delta_context, delta_feature = T.grad(logProbs, [self.contextMatrix, self.featureVectors])
            print 'Gradient completed!'
            train = theano.function(
                                    inputs = [self.vocab],
                                    outputs = [logProbs],
                                    updates=((self.featureVectors,self.featureVectors - self.alpha * delta_feature), 
                                             (self.contextMatrix,self.contextMatrix - self.alpha * delta_context)),
                                    name="train"
                                    )



    print('Training is finished!')

I have just learnt about Python and neural probability language model, so it is quite difficult to me. Could you help me, please! Thank you!